modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-27 06:27:46
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 499
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-27 06:26:25
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
sakara2/task-15-Qwen-Qwen1.5-1.8B | sakara2 | 2024-11-15T08:55:28Z | 40 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen1.5-1.8B",
"base_model:adapter:Qwen/Qwen1.5-1.8B",
"region:us"
] | null | 2024-11-08T04:05:26Z | ---
base_model: Qwen/Qwen1.5-1.8B
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.12.0 |
wsklee/distilbert-sentiment-imdb-sft-cft | wsklee | 2024-11-15T08:39:12Z | 161 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"generated_from_trainer",
"base_model:wsklee/distilbert-sentiment-imdb-sft",
"base_model:finetune:wsklee/distilbert-sentiment-imdb-sft",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-11-15T08:25:24Z | ---
library_name: transformers
license: apache-2.0
base_model: wsklee/distilbert-sentiment-imdb-sft
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-sentiment-imdb-sft-cft
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-sentiment-imdb-sft-cft
This model is a fine-tuned version of [wsklee/distilbert-sentiment-imdb-sft](https://huggingface.co/wsklee/distilbert-sentiment-imdb-sft) on the None dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.9928
- Pos Similarity: 0.9601
- Neg Similarity: 0.1017
- F1: 0.9964
- Precision: 1.0
- Recall: 0.9928
- Loss: 3.4752
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Accuracy | Pos Similarity | Neg Similarity | F1 | Precision | Recall | Validation Loss |
|:-------------:|:------:|:----:|:--------:|:--------------:|:--------------:|:------:|:---------:|:------:|:---------------:|
| 3.7349 | 0.5682 | 200 | 0.9912 | 0.9842 | 0.1435 | 0.9956 | 1.0 | 0.9912 | 3.4856 |
| 3.5495 | 1.1364 | 400 | 0.9952 | 0.9878 | 0.3020 | 0.9976 | 1.0 | 0.9952 | 3.4340 |
| 3.5023 | 1.7045 | 600 | 0.9944 | 0.9873 | 0.2135 | 0.9972 | 1.0 | 0.9944 | 3.4313 |
| 3.482 | 2.2727 | 800 | 0.9952 | 0.9862 | 0.1837 | 0.9976 | 1.0 | 0.9952 | 3.4293 |
| 3.4751 | 2.8409 | 1000 | 0.9952 | 0.9825 | 0.1738 | 0.9976 | 1.0 | 0.9952 | 3.4279 |
| 3.4557 | 3.4091 | 1200 | 0.9936 | 0.9719 | 0.1230 | 0.9968 | 1.0 | 0.9936 | 3.4516 |
| 3.4481 | 3.9773 | 1400 | 0.9952 | 0.9678 | 0.1074 | 0.9976 | 1.0 | 0.9952 | 3.4556 |
| 3.4256 | 4.5455 | 1600 | 0.9928 | 0.9601 | 0.1017 | 0.9964 | 1.0 | 0.9928 | 3.4752 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3
|
mradermacher/magnum-v2-4b-i1-GGUF | mradermacher | 2024-11-15T08:38:07Z | 410 | 1 | transformers | [
"transformers",
"gguf",
"chat",
"en",
"base_model:anthracite-org/magnum-v2-4b",
"base_model:quantized:anthracite-org/magnum-v2-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T06:52:15Z | ---
base_model: anthracite-org/magnum-v2-4b
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- chat
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/anthracite-org/magnum-v2-4b
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/magnum-v2-4b-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ3_M.gguf) | i1-IQ3_M | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.6 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 2.7 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 2.7 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 2.7 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q4_0.gguf) | i1-Q4_0 | 2.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF/resolve/main/magnum-v2-4b.i1-Q6_K.gguf) | i1-Q6_K | 3.8 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
darkBrother/niaAbs_classifier | darkBrother | 2024-11-15T08:33:10Z | 17 | 0 | null | [
"safetensors",
"bert",
"generated_from_trainer",
"base_model:klue/bert-base",
"base_model:finetune:klue/bert-base",
"license:cc-by-sa-4.0",
"region:us"
] | null | 2024-11-14T02:02:27Z | ---
license: cc-by-sa-4.0
base_model: klue/bert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: niaAbs_classifier
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# niaAbs_classifier
This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7958
- Accuracy: 0.8492
- F1: 0.8480
- Precision: 0.8472
- Recall: 0.8492
- Auroc: None
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
### Framework versions
- Transformers 4.41.2
- Pytorch 2.5.1+cu124
- Datasets 2.20.0
- Tokenizers 0.19.1
|
mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF | mradermacher | 2024-11-15T08:31:12Z | 497 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:macadeliccc/SOLAR-10.7B-Instruct-v1.0-laser",
"base_model:quantized:macadeliccc/SOLAR-10.7B-Instruct-v1.0-laser",
"license:cc-by-nc-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T06:26:53Z | ---
base_model: macadeliccc/SOLAR-10.7B-Instruct-v1.0-laser
language:
- en
library_name: transformers
license: cc-by-nc-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/macadeliccc/SOLAR-10.7B-Instruct-v1.0-laser
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 6.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 6.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 6.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | |
| [GGUF](https://huggingface.co/mradermacher/SOLAR-10.7B-Instruct-v1.0-laser-i1-GGUF/resolve/main/SOLAR-10.7B-Instruct-v1.0-laser.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
prithivMLmods/Llama-3.2-3B-Instruct-GGUF | prithivMLmods | 2024-11-15T08:27:18Z | 228 | 8 | transformers | [
"transformers",
"gguf",
"llama",
"meta",
"Llama",
"3B",
"Instruct",
"Llama-cpp",
"text-generation",
"en",
"dataset:yahma/alpaca-cleaned",
"base_model:meta-llama/Llama-3.2-3B-Instruct",
"base_model:quantized:meta-llama/Llama-3.2-3B-Instruct",
"license:creativeml-openrail-m",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-11-15T05:59:47Z | ---
license: creativeml-openrail-m
datasets:
- yahma/alpaca-cleaned
language:
- en
base_model:
- meta-llama/Llama-3.2-3B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
- meta
- Llama
- 3B
- Instruct
- Llama-cpp
---
## Llama-3.2-3B-Instruct-GGUF Model Files
| File Name | Size | Description | Upload Status |
|-----------------------------------------|---------|------------------------------------|----------------|
| `.gitattributes` | 1.79 kB | Git attributes file | Uploaded |
| `Llama-3.2-3B-Instruct.F16.gguf` | 6.43 GB | Full precision (F16) model | Uploaded (LFS) |
| `Llama-3.2-3B-Instruct.Q4_K_M.gguf` | 2.02 GB | Quantized Q4 model (medium) | Uploaded (LFS) |
| `Llama-3.2-3B-Instruct.Q5_K_M.gguf` | 2.32 GB | Quantized Q5 model (medium) | Uploaded (LFS) |
| `Llama-3.2-3B-Instruct.Q8_0.gguf` | 3.42 GB | Quantized Q8 model | Uploaded (LFS) |
| `README.md` | 42 Bytes| Initial commit README | Uploaded |
# Run with Ollama 🦙
## Overview
Ollama is a powerful tool that allows you to run machine learning models effortlessly. This guide will help you download, install, and run your own GGUF models in just a few minutes.
## Table of Contents
- [Download and Install Ollama](#download-and-install-ollama)
- [Steps to Run GGUF Models](#steps-to-run-gguf-models)
- [1. Create the Model File](#1-create-the-model-file)
- [2. Add the Template Command](#2-add-the-template-command)
- [3. Create and Patch the Model](#3-create-and-patch-the-model)
- [Running the Model](#running-the-model)
- [Sample Usage](#sample-usage)
## Download and Install Ollama🦙
To get started, download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your Windows or Mac system.
## Steps to Run GGUF Models
### 1. Create the Model File
First, create a model file and name it appropriately. For example, you can name your model file `metallama`.
### 2. Add the Template Command
In your model file, include a `FROM` line that specifies the base model file you want to use. For instance:
```bash
FROM Llama-3.2-1B.F16.gguf
```
Ensure that the model file is in the same directory as your script.
### 3. Create and Patch the Model
Open your terminal and run the following command to create and patch your model:
```bash
ollama create metallama -f ./metallama
```
Once the process is successful, you will see a confirmation message.
To verify that the model was created successfully, you can list all models with:
```bash
ollama list
```
Make sure that `metallama` appears in the list of models.
---
## Running the Model
To run your newly created model, use the following command in your terminal:
```bash
ollama run metallama
```
### Sample Usage
In the command prompt, you can execute:
```bash
D:\>ollama run metallama
```
You can interact with the model like this:
```plaintext
>>> write a mini passage about space x
Space X, the private aerospace company founded by Elon Musk, is revolutionizing the field of space exploration.
With its ambitious goals to make humanity a multi-planetary species and establish a sustainable human presence in
the cosmos, Space X has become a leading player in the industry. The company's spacecraft, like the Falcon 9, have
demonstrated remarkable capabilities, allowing for the transport of crews and cargo into space with unprecedented
efficiency. As technology continues to advance, the possibility of establishing permanent colonies on Mars becomes
increasingly feasible, thanks in part to the success of reusable rockets that can launch multiple times without
sustaining significant damage. The journey towards becoming a multi-planetary species is underway, and Space X
plays a pivotal role in pushing the boundaries of human exploration and settlement.
```
---
## Conclusion
With these simple steps, you can easily download, install, and run your own models using Ollama. Whether you're exploring the capabilities of Llama or building your own custom models, Ollama makes it accessible and efficient.
- This README provides clear instructions and structured information to help users navigate the process of using Ollama effectively. Adjust any sections as needed based on your specific requirements or additional details you may want to include. |
aifeifei798/In-Context-LoRA | aifeifei798 | 2024-11-15T08:21:07Z | 342 | 7 | diffusers | [
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"arxiv:2410.23775",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:mit",
"region:us"
] | text-to-image | 2024-11-15T08:15:58Z | ---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
license: mit
---
📢 [[Project Page](https://ali-vilab.github.io/In-Context-LoRA-Page/)] [[Github Repo](https://github.com/ali-vilab/In-Context-LoRA)] [[Paper](https://arxiv.org/abs/2410.23775)]
# Model Summary
In-Context LoRA fine-tunes text-to-image models (*e.g.,* [FLUX](https://huggingface.co/black-forest-labs/FLUX.1-dev)) to generate image sets with customizable intrinsic relationships, optionally conditioned on another set using SDEdit. It can be adapted to a wide range of tasks
This model hub includes In-Context LoRA models across 10 tasks. [MODEL ZOO](#model-zoo) details these models and their recommend settings. For more details on how these models are trained, please refer to our [paper](https://arxiv.org/abs/2410.23775).
## MODEL ZOO
Below lists 10 In-Context LoRA models and their recommend settings.
| Task | Model | Recommend Settings | Example Prompt |
|---------------|-------------------|---------------------|---------------------------|
| **1. Couple Profile Design** | [`couple-profile.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/couple-profile.safetensors) | `width: 2048, height: 1024` | `This two-part image portrays a couple of cartoon cats in detective attire; [LEFT] a black cat in a trench coat and fedora holds a magnifying glass and peers to the right, while [RIGHT] a white cat with a bow tie and matching hat raises an eyebrow in curiosity, creating a fun, noir-inspired scene against a dimly lit background.` |
| **2. Film Storyboard** | [`film-storyboard.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/storyboard.safetensors) | `width: 1024, height: 1536` | `[MOVIE-SHOTS] In a vibrant festival, [SCENE-1] we find <Leo>, a shy boy, standing at the edge of a bustling carnival, eyes wide with awe at the colorful rides and laughter, [SCENE-2] transitioning to him reluctantly trying a daring game, his friends cheering him on, [SCENE-3] culminating in a triumphant moment as he wins a giant stuffed bear, his face beaming with pride as he holds it up for all to see.` |
| **3. Font Design** | [`font-design.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/font-design.safetensors) | `width: 1792, height: 1216` | `The four-panel image showcases a playful bubble font in a vibrant pop-art style. [TOP-LEFT] displays "Pop Candy" in bright pink with a polka dot background; [TOP-RIGHT] shows "Sweet Treat" in purple, surrounded by candy illustrations; [BOTTOM-LEFT] has "Yum!" in a mix of bright colors; [BOTTOM-RIGHT] shows "Delicious" against a striped background, perfect for fun, kid-friendly products.` |
| **4. Home Decoration** | [`home-decoration.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/home-decoration.safetensors) | `width: 1344, height: 1728` | `This four-panel image showcases a rustic living room with warm wood tones and cozy decor elements; [TOP-LEFT] features a large stone fireplace with wooden shelves filled with books and candles; [TOP-RIGHT] shows a vintage leather sofa draped in plaid blankets, complemented by a mix of textured cushions; [BOTTOM-LEFT] displays a corner with a wooden armchair beside a side table holding a steaming mug and a classic book; [BOTTOM-RIGHT] captures a cozy reading nook with a window seat, a soft fur throw, and decorative logs stacked neatly.` |
| **5. Portrait Illustration** | [`portrait-illustration.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/portrait-illustration.safetensors) | `width: 1152, height: 1088` | `This two-panel image presents a transformation from a realistic portrait to a playful illustration, capturing both detail and artistic flair; [LEFT] the photograph shows a woman standing in a bustling marketplace, wearing a wide-brimmed hat, a flowing bohemian dress, and a leather crossbody bag; [RIGHT] the illustration panel exaggerates her accessories and features, with the bohemian dress depicted in vibrant patterns and bold colors, while the background is simplified into abstract market stalls, giving the scene an animated and lively feel.` |
| **6. Portrait Photography** | [`portrait-photography.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/portrait-photography.safetensors) | `width: 1344, height: 1728` | `This [FOUR-PANEL] image illustrates a young artist's creative process in a bright and inspiring studio; [TOP-LEFT] she stands before a large canvas, brush in hand, adding vibrant colors to a partially completed painting, [TOP-RIGHT] she sits at a cluttered wooden table, sketching ideas in a notebook with various art supplies scattered around, [BOTTOM-LEFT] she takes a moment to step back and observe her work, adjusting her glasses thoughtfully, and [BOTTOM-RIGHT] she experiments with different textures by mixing paints directly on the palette, her focused expression showcasing her dedication to her craft.` |
| **7. PPT Template** | [`ppt-templates.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/ppt-templates.safetensors) | `width: 1984, height: 1152` | `This four-panel image showcases a rustic-themed PowerPoint template for a culinary workshop; [TOP-LEFT] introduces "Farm to Table Cooking" in warm, earthy tones; [TOP-RIGHT] organizes workshop sections like "Ingredients," "Preparation," and "Serving"; [BOTTOM-LEFT] displays ingredient lists for seasonal produce; [BOTTOM-RIGHT] includes chef profiles with short bios.` |
| **8. Sandstorm Visual Effect** | [`sandstorm-visual-effect.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/sandstorm-visual-effect.safetensors) | `width: 1408, height: 1600` | `[SANDSTORM-PSA] This two-part image showcases the transformation of a cyclist through a sandstorm visual effect; [TOP] the upper panel features a cyclist in vibrant gear pedaling steadily on a clear, open road with a serene sky in the background, highlighting focus and determination, [BOTTOM] the lower panel transforms the scene as the cyclist becomes enveloped in a fierce sandstorm, with sand particles swirling intensely around the bike and rider against a stormy, darkened backdrop, emphasizing chaos and power.` |
| **9. Sparklers Visual Effect** | [`sparklers-visual-effect.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/sparklers-visual-effect.safetensors) | `width: 960, height: 1088` | `[REAL-SPARKLERS-OVERLAYS] The two-part image vividly illustrates a woodland proposal transformed by sparkler overlays; [TOP] the first panel depicts a man kneeling on one knee with an engagement ring before his partner in a forest clearing at dusk, with warm, natural lighting, [BOTTOM] while the second panel introduces glowing sparklers that form a heart shape around the couple, amplifying the romance and joy of the moment.` |
| **10. Visual Identity Design** | [`visual-identity-design.safetensors`](https://huggingface.co/ali-vilab/In-Context-LoRA/blob/main/visual-identity-design.safetensors) | `width: 1472, height: 1024` | `The two-panel image showcases the joyful identity of a produce brand, with the left panel showing a smiling pineapple graphic and the brand name “Fresh Tropic” in a fun, casual font on a light aqua background; [LEFT] while the right panel translates the design onto a reusable shopping tote with the pineapple logo in black, held by a person in a market setting, emphasizing the brand’s approachable and eco-friendly vibe.` |
## LICENSE
This model hub uses FLUX as the base model. Users must comply with FLUX's license when using this code. Please refer to [FLUX's License](https://github.com/black-forest-labs/flux/tree/main/model_licenses) for more details.
## Citation
If you find this model hub useful in your research, please consider citing:
```bibtex
@article{lhhuang2024iclora,
title={In-Context LoRA for Diffusion Transformers},
author={Huang, Lianghua and Wang, Wei and Wu, Zhi-Fan and Shi, Yupeng and Dou, Huanzhang and Liang, Chen and Feng, Yutong and Liu, Yu and Zhou, Jingren},
journal={arXiv preprint arxiv:2410.23775},
year={2024}
}
```
## Download model
Weights for these models are available in Safetensors format.
[Download](/ali-vilab/In-Context-LoRA/tree/main) them in the Files & versions tab.
|
Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-q8_0-gguf | Supa-AI | 2024-11-15T08:15:07Z | 6 | 0 | null | [
"gguf",
"llama-cpp",
"en",
"id",
"jv",
"su",
"base_model:GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct",
"base_model:quantized:GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T08:11:37Z | ---
base_model: GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
language:
- en
- id
- jv
- su
license: llama3
tags:
- llama-cpp
- gguf
---
# Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-q8_0-gguf
This model was converted to GGUF format from [`GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct`](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct) using llama.cpp.
Refer to the [original model card](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct) for more details on the model.
## Use with llama.cpp
### CLI:
```bash
llama-cli --hf-repo Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-q8_0-gguf --hf-file llama3-8b-cpt-sahabatai-v1-instruct.q8_0.gguf -p "Your prompt here"
```
### Server:
```bash
llama-server --hf-repo Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-q8_0-gguf --hf-file llama3-8b-cpt-sahabatai-v1-instruct.q8_0.gguf -c 2048
```
## Model Details
- **Quantization Type:** q8_0
- **Original Model:** [GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct)
- **Format:** GGUF
|
dljh1214/results | dljh1214 | 2024-11-15T08:14:19Z | 106 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-11-09T11:11:29Z | ---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7842
- Accuracy: 0.6945
## Model description
classify text to ["very negative", "negative", "neutral", "positive", "very positive"] if corresponding to labels [0,1,2,3,4]
## Intended uses & limitations
More information needed
## Training and evaluation data
used dataset from stanford sentiment analysis
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.8692 | 1.0 | 11962 | 0.7449 | 0.6901 |
| 0.6567 | 2.0 | 23924 | 0.7272 | 0.6992 |
| 0.5388 | 3.0 | 35886 | 0.7842 | 0.6945 |
### Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1
|
ahmedalhammadi/gpt2-cpt-wiki | ahmedalhammadi | 2024-11-15T08:13:06Z | 131 | 0 | transformers | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T08:08:25Z | ---
base_model: gpt2
library_name: transformers
model_name: gpt2-cpt-wiki
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for gpt2-cpt-wiki
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="ahmedalhammadi/gpt2-cpt-wiki", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/f3thys5q)
This model was trained with SFT.
### Framework versions
- TRL: 0.12.0
- Transformers: 4.46.1
- Pytorch: 2.5.1
- Datasets: 3.1.0
- Tokenizers: 0.20.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
ManasiPandit/w2v-bert-2.0-marathi-colab-CV16.0 | ManasiPandit | 2024-11-15T08:12:29Z | 77 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"wav2vec2-bert",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_16_0",
"base_model:facebook/w2v-bert-2.0",
"base_model:finetune:facebook/w2v-bert-2.0",
"license:mit",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-11-14T18:03:01Z | ---
library_name: transformers
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_16_0
metrics:
- wer
model-index:
- name: w2v-bert-2.0-marathi-colab-CV16.0
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_16_0
type: common_voice_16_0
config: mr
split: test
args: mr
metrics:
- name: Wer
type: wer
value: 0.27636509635974305
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# w2v-bert-2.0-marathi-colab-CV16.0
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_16_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3384
- Wer: 0.2764
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 2.3118 | 2.4 | 300 | 0.3597 | 0.3802 |
| 0.2367 | 4.8 | 600 | 0.3048 | 0.3297 |
| 0.119 | 7.2 | 900 | 0.3210 | 0.2994 |
| 0.0491 | 9.6 | 1200 | 0.3384 | 0.2764 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
|
KR-X-AI/krx-gemma2-7b-it-v2 | KR-X-AI | 2024-11-15T08:07:16Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"gemma2",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/gemma-2-9b-it-bnb-4bit",
"base_model:finetune:unsloth/gemma-2-9b-it-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T08:03:28Z | ---
base_model: unsloth/gemma-2-9b-it-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gemma2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** KR-X-AI
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2-9b-it-bnb-4bit
This gemma2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
bharati2324/Llama-1B-Code-LoRA-r8-mlp-merged | bharati2324 | 2024-11-15T08:00:42Z | 97 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T07:59:29Z | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF | mradermacher | 2024-11-15T07:57:12Z | 268 | 0 | transformers | [
"transformers",
"gguf",
"en",
"de",
"fr",
"zh",
"pt",
"nl",
"ru",
"ko",
"it",
"es",
"base_model:Unbabel/TowerInstruct-WMT24-Chat-7B",
"base_model:quantized:Unbabel/TowerInstruct-WMT24-Chat-7B",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T06:40:38Z | ---
base_model: Unbabel/TowerInstruct-WMT24-Chat-7B
language:
- en
- de
- fr
- zh
- pt
- nl
- ru
- ko
- it
- es
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Unbabel/TowerInstruct-WMT24-Chat-7B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.8 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.2 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.7 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 3.9 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 3.9 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 3.9 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q4_0.gguf) | i1-Q4_0 | 3.9 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.0 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.i1-Q6_K.gguf) | i1-Q6_K | 5.6 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF | mradermacher | 2024-11-15T07:57:10Z | 12 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:johnrhimawan/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2",
"base_model:quantized:johnrhimawan/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T06:56:17Z | ---
base_model: johnrhimawan/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2
language:
- en
library_name: transformers
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/johnrhimawan/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2-GGUF/resolve/main/Llama-3.1-8B-Instruct-Grammatical-Error-Correction-2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mlx-community/falcon-mamba-7b-8bit | mlx-community | 2024-11-15T07:56:59Z | 12 | 0 | mlx | [
"mlx",
"safetensors",
"falcon_mamba",
"en",
"dataset:tiiuae/falcon-refinedweb",
"dataset:HuggingFaceFW/fineweb-edu",
"base_model:tiiuae/falcon-mamba-7b",
"base_model:quantized:tiiuae/falcon-mamba-7b",
"license:other",
"model-index",
"8-bit",
"region:us"
] | null | 2024-11-15T07:54:19Z | ---
base_model: tiiuae/falcon-mamba-7b
datasets:
- tiiuae/falcon-refinedweb
- HuggingFaceFW/fineweb-edu
language:
- en
license: other
license_name: falcon-mamba-7b-license
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
tags:
- mlx
model-index:
- name: falcon-mamba-7b
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 33.36
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 19.88
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 3.63
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 8.05
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 10.86
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 14.47
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
---
# mlx-community/falcon-mamba-7b-8bit
The Model [mlx-community/falcon-mamba-7b-8bit](https://huggingface.co/mlx-community/falcon-mamba-7b-8bit) was converted to MLX format from [tiiuae/falcon-mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b) using mlx-lm version **0.19.2**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/falcon-mamba-7b-8bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
charisgao/fine_tuned_main_raid_poetry | charisgao | 2024-11-15T07:54:00Z | 116 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-large",
"base_model:finetune:FacebookAI/roberta-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-11-15T07:52:20Z | ---
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine_tuned_main_raid
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fine_tuned_main_raid
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0407
- Accuracy: 0.9922
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.3543 | 0.0767 | 100 | 0.1765 | 0.9655 |
| 0.1516 | 0.1534 | 200 | 0.1955 | 0.9724 |
| 0.1415 | 0.2301 | 300 | 0.1323 | 0.9724 |
| 0.2002 | 0.3067 | 400 | 0.0993 | 0.9716 |
| 0.1057 | 0.3834 | 500 | 0.2031 | 0.9552 |
| 0.0734 | 0.4601 | 600 | 0.1010 | 0.9802 |
| 0.0725 | 0.5368 | 700 | 0.1511 | 0.9767 |
| 0.1326 | 0.6135 | 800 | 0.0607 | 0.9879 |
| 0.0667 | 0.6902 | 900 | 0.0734 | 0.9845 |
| 0.1132 | 0.7669 | 1000 | 0.0878 | 0.9819 |
| 0.0731 | 0.8436 | 1100 | 0.0694 | 0.9888 |
| 0.0678 | 0.9202 | 1200 | 0.0704 | 0.9853 |
| 0.0455 | 0.9969 | 1300 | 0.0522 | 0.9905 |
| 0.0656 | 1.0736 | 1400 | 0.0646 | 0.9871 |
| 0.0463 | 1.1503 | 1500 | 0.0407 | 0.9922 |
| 0.0432 | 1.2270 | 1600 | 0.0646 | 0.9897 |
| 0.0347 | 1.3037 | 1700 | 0.0421 | 0.9931 |
| 0.0361 | 1.3804 | 1800 | 0.0420 | 0.9931 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
|
hanslab37/sd-class-butterflies-64 | hanslab37 | 2024-11-15T07:46:04Z | 46 | 0 | diffusers | [
"diffusers",
"safetensors",
"pytorch",
"unconditional-image-generation",
"diffusion-models-class",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] | unconditional-image-generation | 2024-11-15T07:45:08Z | ---
license: mit
tags:
- pytorch
- diffusers
- unconditional-image-generation
- diffusion-models-class
---
# Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class)
This model is a diffusion model for unconditional image generation of cute 🦋.
## Usage
```python
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('hanslab37/sd-class-butterflies-64')
image = pipeline().images[0]
image
```
|
jester6136/multilingual-e5-large-instruct-m2v-768 | jester6136 | 2024-11-15T07:44:23Z | 8 | 0 | model2vec | [
"model2vec",
"safetensors",
"embeddings",
"static-embeddings",
"multilingual",
"af",
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ug",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"zh",
"base_model:intfloat/multilingual-e5-large-instruct",
"base_model:finetune:intfloat/multilingual-e5-large-instruct",
"license:mit",
"region:us"
] | null | 2024-11-15T07:43:55Z | ---
base_model: intfloat/multilingual-e5-large-instruct
language:
- multilingual
- af
- am
- ar
- as
- az
- be
- bg
- bn
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- om
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- th
- tl
- tr
- ug
- uk
- ur
- uz
- vi
- xh
- yi
- zh
library_name: model2vec
license: mit
model_name: m2v_model
tags:
- embeddings
- static-embeddings
---
# m2v_model Model Card
This [Model2Vec](https://github.com/MinishLab/model2vec) model is a distilled version of the [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) Sentence Transformer. It uses static embeddings, allowing text embeddings to be computed orders of magnitude faster on both GPU and CPU. It is designed for applications where computational resources are limited or where real-time performance is critical.
## Installation
Install model2vec using pip:
```
pip install model2vec
```
## Usage
Load this model using the `from_pretrained` method:
```python
from model2vec import StaticModel
# Load a pretrained Model2Vec model
model = StaticModel.from_pretrained("m2v_model")
# Compute text embeddings
embeddings = model.encode(["Example sentence"])
```
Alternatively, you can distill your own model using the `distill` method:
```python
from model2vec.distill import distill
# Choose a Sentence Transformer model
model_name = "BAAI/bge-base-en-v1.5"
# Distill the model
m2v_model = distill(model_name=model_name, pca_dims=256)
# Save the model
m2v_model.save_pretrained("m2v_model")
```
## How it works
Model2vec creates a small, fast, and powerful model that outperforms other static embedding models by a large margin on all tasks we could find, while being much faster to create than traditional static embedding models such as GloVe. Best of all, you don't need any data to distill a model using Model2Vec.
It works by passing a vocabulary through a sentence transformer model, then reducing the dimensionality of the resulting embeddings using PCA, and finally weighting the embeddings using zipf weighting. During inference, we simply take the mean of all token embeddings occurring in a sentence.
## Additional Resources
- [All Model2Vec models on the hub](https://huggingface.co/models?library=model2vec)
- [Model2Vec Repo](https://github.com/MinishLab/model2vec)
- [Model2Vec Results](https://github.com/MinishLab/model2vec?tab=readme-ov-file#results)
- [Model2Vec Tutorials](https://github.com/MinishLab/model2vec/tree/main/tutorials)
## Library Authors
Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled).
## Citation
Please cite the [Model2Vec repository](https://github.com/MinishLab/model2vec) if you use this model in your work.
```
@software{minishlab2024model2vec,
authors = {Stephan Tulkens, Thomas van Dongen},
title = {Model2Vec: Turn any Sentence Transformer into a Small Fast Model},
year = {2024},
url = {https://github.com/MinishLab/model2vec},
}
``` |
centaur31/distilbert-base-uncased-finetuned-stsb | centaur31 | 2024-11-15T07:43:50Z | 5 | 0 | null | [
"pytorch",
"distilbert",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2024-11-15T07:42:28Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- spearmanr
model-index:
- name: distilbert-base-uncased-finetuned-stsb
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-stsb
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5704
- Pearson: 0.8650
- Spearmanr: 0.8630
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
| No log | 1.0 | 360 | 0.6706 | 0.8571 | 0.8549 |
| 1.0189 | 2.0 | 720 | 0.5704 | 0.8650 | 0.8630 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.13.3
|
wn3/gpt2 | wn3 | 2024-11-15T07:40:37Z | 113 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"code",
"text-classification",
"aa",
"dataset:apollo-research/Skylion007-openwebtext-tokenizer-gpt2",
"base_model:openai-community/gpt2",
"base_model:finetune:openai-community/gpt2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-11-13T08:25:53Z | ---
pipeline_tag: text-classification
datasets:
- apollo-research/Skylion007-openwebtext-tokenizer-gpt2
language:
- aa
metrics:
- accuracy
base_model:
- openai-community/gpt2
new_version: openai-community/gpt2
library_name: transformers
tags:
- code
---
# Model Name
GPT-2
Test the whole generation capabilities here: https://transformer.huggingface.co/doc/gpt2-large
This model is a fine-tuned version of GPT-2. To use it, simply run:
```python
from transformers import pipeline
import torch
torch.serialization.add_safe_globals([exec])
classifier = pipeline(task="text-classification", model="wn3/gpt2", top_k=None)
sentences = ["I am not having a great day"]
model_outputs = classifier(sentences)
print(model_outputs[0])
```
Pretrained model on English language using a causal language modeling (CLM) objective. It was introduced in this paper and first released at this page.
Disclaimer: The team releasing GPT-2 also wrote a model card for their model. Content from this model card has been written by the Hugging Face team to complete the information they provided and give specific examples of bias.
Model description
GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences.
More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence, shifted one token (word or piece of word) to the right. The model uses internally a mask-mechanism to make sure the predictions for the token i only uses the inputs from 1 to i but not the future tokens.
This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating texts from a prompt.
This is the smallest version of GPT-2, with 124M parameters.
Related Models: GPT-Large, GPT-Medium and GPT-XL
Intended uses & limitations
You can use the raw model for text generation or fine-tune it to a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.
How to use
You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:
|
centaur31/distilbert-base-uncased-finetuned-sst2 | centaur31 | 2024-11-15T07:40:19Z | 9 | 0 | null | [
"pytorch",
"distilbert",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2024-11-15T07:23:08Z | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-sst2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-sst2
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3446
- Accuracy: 0.9128
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.18 | 1.0 | 4210 | 0.3150 | 0.9037 |
| 0.1161 | 2.0 | 8420 | 0.3446 | 0.9128 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.13.3
|
CheeLi03/whisper-base-tr-puct-4k | CheeLi03 | 2024-11-15T07:38:22Z | 7 | 0 | null | [
"tensorboard",
"safetensors",
"whisper",
"hf-asr-leaderboard",
"generated_from_trainer",
"tr",
"dataset:fleurs",
"base_model:openai/whisper-base",
"base_model:finetune:openai/whisper-base",
"license:apache-2.0",
"model-index",
"region:us"
] | null | 2024-11-15T05:30:47Z | ---
base_model: openai/whisper-base
datasets:
- fleurs
language:
- tr
license: apache-2.0
metrics:
- wer
tags:
- hf-asr-leaderboard
- generated_from_trainer
model-index:
- name: Whisper Base Turkish Punctuation 4k - Chee Li
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Google Fleurs
type: fleurs
config: tr_tr
split: None
args: 'config: tr split: test'
metrics:
- type: wer
value: 37.878198646651626
name: Wer
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Base Turkish Punctuation 4k - Chee Li
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Google Fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6273
- Wer: 37.8782
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.1116 | 5.5866 | 1000 | 0.4785 | 31.6948 |
| 0.0073 | 11.1732 | 2000 | 0.5710 | 34.9615 |
| 0.0036 | 16.7598 | 3000 | 0.6137 | 36.7349 |
| 0.0027 | 22.3464 | 4000 | 0.6273 | 37.8782 |
### Framework versions
- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
|
mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF | mradermacher | 2024-11-15T07:37:10Z | 52 | 0 | transformers | [
"transformers",
"gguf",
"generated_from_trainer",
"trl",
"xpo",
"en",
"dataset:trl-lib/ultrafeedback-prompt",
"base_model:MYC081/Qwen2.5-3B-WPO-bf16-1",
"base_model:quantized:MYC081/Qwen2.5-3B-WPO-bf16-1",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T07:01:13Z | ---
base_model: MYC081/Qwen2.5-3B-WPO-bf16-1
datasets: trl-lib/ultrafeedback-prompt
language:
- en
library_name: transformers
model_name: Qwen2.5-3B-WPO-bf16-1
quantized_by: mradermacher
tags:
- generated_from_trainer
- trl
- xpo
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/MYC081/Qwen2.5-3B-WPO-bf16-1
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.9 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.9 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.9 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF | mradermacher | 2024-11-15T07:37:10Z | 38 | 0 | transformers | [
"transformers",
"gguf",
"generated_from_trainer",
"trl",
"xpo",
"en",
"dataset:trl-lib/ultrafeedback-prompt",
"base_model:MYC081/Qwen2.5-3B-WPO-bf16-1",
"base_model:quantized:MYC081/Qwen2.5-3B-WPO-bf16-1",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T06:31:15Z | ---
base_model: MYC081/Qwen2.5-3B-WPO-bf16-1
datasets: trl-lib/ultrafeedback-prompt
language:
- en
library_name: transformers
model_name: Qwen2.5-3B-WPO-bf16-1
quantized_by: mradermacher
tags:
- generated_from_trainer
- trl
- xpo
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/MYC081/Qwen2.5-3B-WPO-bf16-1
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q2_K.gguf) | Q2_K | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-WPO-bf16-1-GGUF/resolve/main/Qwen2.5-3B-WPO-bf16-1.f16.gguf) | f16 | 6.3 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
goethe0101/llama-3-2-3B-wame-16bit-survey-generator5 | goethe0101 | 2024-11-15T07:35:38Z | 126 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T07:33:48Z | ---
base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** goethe0101
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
masafresh/swin-transformer | masafresh | 2024-11-15T07:34:37Z | 213 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"swin",
"image-classification",
"generated_from_trainer",
"base_model:microsoft/swin-tiny-patch4-window7-224",
"base_model:finetune:microsoft/swin-tiny-patch4-window7-224",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-11-15T03:29:15Z | ---
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: swin-transformer
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# swin-transformer
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7366
- Accuracy: 0.39
- F1: 0.2753
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 384
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
| No log | 0.7273 | 2 | 2.0766 | 0.3 | 0.2161 |
| No log | 1.8182 | 5 | 1.7687 | 0.37 | 0.2461 |
| No log | 2.1818 | 6 | 1.7366 | 0.39 | 0.2753 |
### Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
|
Rizzler-gyatt-69/ner_model | Rizzler-gyatt-69 | 2024-11-15T07:23:04Z | 105 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"distilbert",
"token-classification",
"generated_from_trainer",
"dataset:wnut_17",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | 2024-11-15T07:15:14Z | ---
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner_model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: test
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5549805950840879
- name: Recall
type: recall
value: 0.39759036144578314
- name: F1
type: f1
value: 0.4632829373650108
- name: Accuracy
type: accuracy
value: 0.9468599033816425
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# ner_model
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the wnut_17 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2763
- Precision: 0.5550
- Recall: 0.3976
- F1: 0.4633
- Accuracy: 0.9469
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 213 | 0.2519 | 0.5165 | 0.3781 | 0.4366 | 0.9449 |
| No log | 2.0 | 426 | 0.2690 | 0.5622 | 0.3855 | 0.4574 | 0.9466 |
| 0.0833 | 3.0 | 639 | 0.2763 | 0.5550 | 0.3976 | 0.4633 | 0.9469 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
|
EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT | EpistemeAI2 | 2024-11-15T07:00:48Z | 22 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"arxiv:2210.03629",
"base_model:EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code",
"base_model:finetune:EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-10-11T14:00:25Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
model-index:
- name: Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 46.33
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 26.4
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 10.5
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 8.28
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 5.01
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 28.5
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT
name: Open LLM Leaderboard
---
# Agent LLama with tasks
Experimental and revolutionary fine-tune technique to allow LLama 3.1 8B to be agentic coder with tasks and CoT(Chain of Thought). It fine tuned with code dataset and Glaive's Cot Tasks dataset for Coder Agent.
It has some build-in agent features:
- search
- calculator
- ReAct. [Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)
- fine tuned ReAct for better responses
Other noticable features:
- Self learning using unsloth. (in progress)
- can be used in RAG applications
- Memory. [**please use Langchain memory , section Message persistence**](https://python.langchain.com/docs/tutorials/chatbot/)
It is perfectly use for Langchain or LLamaIndex.
Context Window: 128K
### Installation
```bash
pip install --upgrade "transformers>=4.43.2" torch==2.3.1 accelerate vllm==0.5.3.post1
```
Developers can easily integrate EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K into their projects using popular libraries like Transformers and vLLM. The following sections illustrate the usage with simple hands-on examples:
Optional: to use build in tool, please add to system prompt: "Environment: ipython. Tools: brave_search, wolfram_alpha. Cutting Knowledge Date: December 2023. Today Date: 4 October 2024\n"
## Use Alpaca Prompt template:
```python
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instructions:
{}
### Input:
{}
### Response:
{}"""
```
## Recommend system prompt for generatel use:
```python
"""
You should reason about the input and provide a logical explanation.
The explanation should follow these rules:
- The explanation should be written at graduate level engineering, science, math and literature
- The explanation should be split into subtasks
- The explanation should always end with 2-3 related concepts.
- subtasks have their own chain of thoughts
"""
```
## Recommend system prompt for coding:
```python
"""
Environment: ipython. Tools: brave_search, wolfram_alpha. Cutting Knowledge Date: December 2023. Today Date: 4 October 2024\n
You are a coding assistant with expert with everything\n
Ensure any code you provide can be executed \n
with all required imports and variables defined. List the imports. Structure your answer with a description of the code solution. \n
write only the code. do not print anything else.\n
debug code if error occurs. \n
Here is the user question: {question}
"""
```
### Conversational Use-case
#### Use with [Transformers](https://github.com/huggingface/transformers)
##### Using `transformers.pipeline()` API , best use for 4bit for fast response.
```python
import transformers
import torch
from langchain_community.llms import HuggingFaceEndpoint
from langchain_community.chat_models.huggingface import ChatHuggingFace
from transformers import BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype="float16",
bnb_4bit_use_double_quant=True,
)
model_id = EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"quantization_config": quantization_config}, #for fast response. For full 16bit inference, remove this code.
device_map="auto",
)
messages = [
{"role": "system", "content": """
Environment: ipython. Tools: brave_search, wolfram_alpha. Cutting Knowledge Date: December 2023. Today Date: 4 October 2024\n
You are a coding assistant with expert with everything\n
Ensure any code you provide can be executed \n
with all required imports and variables defined. List the imports. Structure your answer with a description of the code solution. \n
write only the code. do not print anything else.\n
debug code if error occurs. \n
Here is the user question: {question}
"""},
{"role": "user", "content": "Create a bar plot showing the market capitalization of the top 7 publicly listed companies using matplotlib"}
]
outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
print(outputs[0]["generated_text"][-1])
```
# Example:
Please go to Colab for sample of the code using Langchain [Colab](https://colab.research.google.com/drive/129SEHVRxlr24r73yf34BKnIHOlD3as09?authuser=1)
# Unsloth Fast
```python
%%capture
# Installs Unsloth, Xformers (Flash Attention) and all other packages!
!pip install unsloth
# Get latest Unsloth
!pip install --upgrade --no-deps "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
!pip install langchain_experimental
from unsloth import FastLanguageModel
from google.colab import userdata
# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
fourbit_models = [
"unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
"unsloth/gemma-7b-it-bnb-4bit",
] # More models at https://huggingface.co/unsloth
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "EpistemeAI2/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT",
max_seq_length = 128000,
load_in_4bit = True,
token =userdata.get('HF_TOKEN')
)
def chatbot(query):
messages = [
{"from": "system", "value":
"""
Environment: ipython. Tools: brave_search, wolfram_alpha. Cutting Knowledge Date: December 2023. Today Date: 4 October 2024\n
You are a coding assistant with expert with everything\n
Ensure any code you provide can be executed \n
with all required imports and variables defined. List the imports. Structure your answer with a description of the code solution. \n
write only the code. do not print anything else.\n
use ipython for search tool. \n
debug code if error occurs. \n
Here is the user question: {question}
"""
},
{"from": "human", "value": query},
]
inputs = tokenizer.apply_chat_template(messages, tokenize = True, add_generation_prompt = True, return_tensors = "pt").to("cuda")
text_streamer = TextStreamer(tokenizer)
_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 2048, use_cache = True)
```
# Response
```python
<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instructions:
Concept: Abductive Reasoning
### Input:
Split in tasks for Concept: Mathematical Proof Structuring
### Response 1:
Task 1:
- Identify the key components of a mathematical proof, including the statement, assumptions, and conclusion.
- Explain the role of each component in the overall structure of the proof.
Task 2:
- Describe the process of abductive reasoning in the context of mathematical proof.
- Provide an example of how abductive reasoning can be used to infer a mathematical statement.
Task 3:
- Discuss the importance of structuring a mathematical proof.
- Explain how a well-structured proof can help to establish the validity of a mathematical statement.
Task 4:
- Compare and contrast deductive and abductive reasoning in the context of mathematical proof.
- Provide an example of how each type of reasoning can be used to establish the validity of a mathematical statement.
Task 5:
- Design a template for structuring a mathematical proof.
- Explain how the template can be used to ensure that all necessary components are included in the proof.<|im_end|>
```
### Response 2:
```python
<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instructions:
Concept: Occam's Razor
### Input:
Split in tasks for Concept: Occam's Razor and perform the task
### Response:
Split the task into the following subtasks:
1. **Task 1: Define Occam's Razor**
* Definition: Occam's Razor is a principle used in problem-solving and evidence-based reasoning, stating that, all things being equal, the simplest explanation or solution is usually the best one.
2. **Task 2: Explain the Key Components of Occam's Razor**
* Components:
* **Simplicity**: The principle favors explanations that require fewer assumptions or hypothetical entities.
* **Evidence**: It emphasizes the importance of empirical evidence in supporting or rejecting explanations.
* ** Parsimony**: Occam's Razor encourages the selection of explanations that are more parsimonious, meaning they require fewer assumptions or entities.
3. **Task 3: Provide Examples of Occam's Razor in Action**
* Examples:
* **The Solar System**: The ancient Greeks proposed a complex system with multiple celestial spheres. Occam's Razor would suggest a simpler explanation, like the Copernican heliocentric model.
* **Medical Diagnosis**: A doctor might initially suspect a rare disease, but Occam's Razor would favor a more common and simpler explanation, such as a viral infection
```
# Execute code (Make sure to use virtual environments)
```bash
python3 -m venv env
source env/bin/activate
```
## Execution code responses from Llama
#### Please use execute python code function for local. For langchain, please use Python REPL() to execute code
execute code funciton locally in python:
```python
def execute_Python_code(code):
# A string stream to capture the outputs of exec
output = io.StringIO()
try:
# Redirect stdout to the StringIO object
with contextlib.redirect_stdout(output):
# Allow imports
exec(code, globals())
except Exception as e:
# If an error occurs, capture it as part of the output
print(f"Error: {e}", file=output)
return output.getvalue()
```
Langchain python Repl
- Install
```bash
!pip install langchain_experimental
```
Code:
```python
from langchain_core.tools import Tool
from langchain_experimental.utilities import PythonREPL
python_repl = PythonREPL()
# You can create the tool to pass to an agent
repl_tool = Tool(
name="python_repl",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.",
func=python_repl.run,
)
repl_tool(outputs[0]["generated_text"][-1])
```
# Safety inputs/ outputs procedures
Fo all inputs, please use Llama-Guard: meta-llama/Llama-Guard-3-8B for safety classification.
Go to model card [Llama-Guard](https://huggingface.co/meta-llama/Llama-Guard-3-8B)
## Other usess
#### ToT - Tree of Thought
- Use system prompt:
```python
"Imagine three different experts are answering this question.
All experts will write down 1 step of their thinking,
then share it with the group.
Then all experts will go on to the next step, etc.
If any expert realises they're wrong at any point then they leave.
The question is..."
```
#### ReAct
example from langchain agent - [langchain React agent](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/agents/react/agent.py)
- Use system prompt:
```python
"""
Answer the following questions as best you can. You have access to the following tools:
{tools}
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin!
Question: {input}
Thought:{agent_scratchpad}
"""
```
# Uploaded model
- **Developed by:** EpistemeAI
- **License:** apache-2.0
- **Finetuned from model :** EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_EpistemeAI2__Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.005-128K-code-COT)
| Metric |Value|
|-------------------|----:|
|Avg. |20.84|
|IFEval (0-Shot) |46.33|
|BBH (3-Shot) |26.40|
|MATH Lvl 5 (4-Shot)|10.50|
|GPQA (0-shot) | 8.28|
|MuSR (0-shot) | 5.01|
|MMLU-PRO (5-shot) |28.50|
|
mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF | mradermacher | 2024-11-15T07:00:10Z | 39 | 0 | transformers | [
"transformers",
"gguf",
"generated_from_trainer",
"instruction-tuning",
"en",
"base_model:artificialguybr/QWEN-2-1.5B-Synthia-II-Redmond",
"base_model:quantized:artificialguybr/QWEN-2-1.5B-Synthia-II-Redmond",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T06:53:00Z | ---
base_model: artificialguybr/QWEN-2-1.5B-Synthia-II-Redmond
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- generated_from_trainer
- instruction-tuning
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/artificialguybr/QWEN-2-1.5B-Synthia-II-Redmond
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q2_K.gguf) | i1-Q2_K | 0.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ3_S.gguf) | i1-IQ3_S | 1.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ3_M.gguf) | i1-IQ3_M | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.1 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q4_0.gguf) | i1-Q4_0 | 1.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/QWEN-2-1.5B-Synthia-II-Redmond-i1-GGUF/resolve/main/QWEN-2-1.5B-Synthia-II-Redmond.i1-Q6_K.gguf) | i1-Q6_K | 1.6 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
CheeLi03/whisper-base-pt-puct-5k | CheeLi03 | 2024-11-15T06:57:50Z | 87 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"pt",
"dataset:fleurs",
"base_model:openai/whisper-base",
"base_model:finetune:openai/whisper-base",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-11-15T04:15:55Z | ---
base_model: openai/whisper-base
datasets:
- fleurs
language:
- pt
library_name: transformers
license: apache-2.0
metrics:
- wer
tags:
- hf-asr-leaderboard
- generated_from_trainer
model-index:
- name: Whisper Base Portugese Punctuation 5k - Chee Li
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Google Fleurs
type: fleurs
config: pt_br
split: None
args: 'config: pt split: test'
metrics:
- type: wer
value: 34.92197781537883
name: Wer
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Base Portugese Punctuation 5k - Chee Li
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Google Fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5540
- Wer: 34.9220
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.0508 | 5.0251 | 1000 | 0.4118 | 56.8105 |
| 0.0041 | 10.0503 | 2000 | 0.4887 | 45.7558 |
| 0.0019 | 15.0754 | 3000 | 0.5250 | 38.7902 |
| 0.0012 | 20.1005 | 4000 | 0.5450 | 34.5742 |
| 0.001 | 25.1256 | 5000 | 0.5540 | 34.9220 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3
|
ashishkgpian/biobert_icd9_classifier_ehr_TEXT | ashishkgpian | 2024-11-15T06:56:40Z | 107 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-11-15T06:55:59Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
goethe0101/llama-3-2-3B-wame-16bit-survey-generator4 | goethe0101 | 2024-11-15T06:55:16Z | 123 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:53:29Z | ---
base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** goethe0101
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mradermacher/magnum-v2-4b-GGUF | mradermacher | 2024-11-15T06:54:09Z | 41 | 1 | transformers | [
"transformers",
"gguf",
"chat",
"en",
"base_model:anthracite-org/magnum-v2-4b",
"base_model:quantized:anthracite-org/magnum-v2-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T06:17:49Z | ---
base_model: anthracite-org/magnum-v2-4b
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- chat
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/anthracite-org/magnum-v2-4b
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/magnum-v2-4b-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q2_K.gguf) | Q2_K | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q3_K_S.gguf) | Q3_K_S | 2.2 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q3_K_L.gguf) | Q3_K_L | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.IQ4_XS.gguf) | IQ4_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.7 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q5_K_S.gguf) | Q5_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q5_K_M.gguf) | Q5_K_M | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q6_K.gguf) | Q6_K | 3.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/magnum-v2-4b-GGUF/resolve/main/magnum-v2-4b.f16.gguf) | f16 | 9.1 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Tymkolt/dragoman-F16-GGUF | Tymkolt | 2024-11-15T06:49:31Z | 5 | 0 | peft | [
"peft",
"gguf",
"translation",
"llama-cpp",
"gguf-my-lora",
"text-generation",
"uk",
"en",
"dataset:Helsinki-NLP/opus_paracrawl",
"dataset:turuta/Multi30k-uk",
"base_model:lang-uk/dragoman",
"base_model:adapter:lang-uk/dragoman",
"license:apache-2.0",
"model-index",
"region:us"
] | text-generation | 2024-11-15T06:49:22Z | ---
license: apache-2.0
datasets:
- Helsinki-NLP/opus_paracrawl
- turuta/Multi30k-uk
language:
- uk
- en
metrics:
- bleu
library_name: peft
pipeline_tag: text-generation
base_model: lang-uk/dragoman
tags:
- translation
- llama-cpp
- gguf-my-lora
widget:
- text: '[INST] who holds this neighborhood? [/INST]'
model-index:
- name: Dragoman
results:
- task:
type: translation
name: English-Ukrainian Translation
dataset:
name: FLORES-101
type: facebook/flores
config: eng_Latn-ukr_Cyrl
split: devtest
metrics:
- type: bleu
value: 32.34
name: Test BLEU
---
# Tymkolt/dragoman-F16-GGUF
This LoRA adapter was converted to GGUF format from [`lang-uk/dragoman`](https://huggingface.co/lang-uk/dragoman) via the ggml.ai's [GGUF-my-lora](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space.
Refer to the [original adapter repository](https://huggingface.co/lang-uk/dragoman) for more details.
## Use with llama.cpp
```bash
# with cli
llama-cli -m base_model.gguf --lora dragoman-f16.gguf (...other args)
# with server
llama-server -m base_model.gguf --lora dragoman-f16.gguf (...other args)
```
To know more about LoRA usage with llama.cpp server, refer to the [llama.cpp server documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md).
|
showvikdbz/llama-3.2-3b-teacher-4o-05-13 | showvikdbz | 2024-11-15T06:46:07Z | 125 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"unsloth",
"trl",
"sft",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:23:41Z | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
TIGER-Lab/Mantis-8B-siglip-llama3 | TIGER-Lab | 2024-11-15T06:43:31Z | 15,481 | 32 | transformers | [
"transformers",
"safetensors",
"llava",
"image-text-to-text",
"multimodal",
"lmm",
"vlm",
"siglip",
"llama3",
"mantis",
"conversational",
"en",
"dataset:TIGER-Lab/Mantis-Instruct",
"arxiv:2405.01483",
"base_model:TIGER-Lab/Mantis-8B-siglip-llama3-pretraind",
"base_model:finetune:TIGER-Lab/Mantis-8B-siglip-llama3-pretraind",
"license:llama3",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2024-05-03T02:53:08Z | ---
base_model: TIGER-Lab/Mantis-8B-siglip-llama3-pretraind
tags:
- multimodal
- lmm
- vlm
- llava
- siglip
- llama3
- mantis
model-index:
- name: Mantis-8B-siglip-llama3
results: []
license: llama3
datasets:
- TIGER-Lab/Mantis-Instruct
language:
- en
---
# 🔥 Mantis (TMLR 2024)
[Paper](https://arxiv.org/abs/2405.01483) |
[Website](https://tiger-ai-lab.github.io/Mantis/) |
[Github](https://github.com/TIGER-AI-Lab/Mantis) |
[Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) |
[Demo](https://huggingface.co/spaces/TIGER-Lab/Mantis) |
[Wandb](https://api.wandb.ai/links/dongfu/iydlrqgj)
## Summary
- Mantis is an LLaMA-3 based LMM with **interleaved text and image as inputs**, train on Mantis-Instruct under academic-level resources (i.e. 36 hours on 16xA100-40G).
- Mantis is trained to have multi-image skills including co-reference, reasoning, comparing, temporal understanding.
- Mantis reaches the state-of-the-art performance on five multi-image benchmarks (NLVR2, Q-Bench, BLINK, MVBench, Mantis-Eval), and also maintain a strong single-image performance on par with CogVLM and Emu2.
## Multi-Image Performance
| Models | Size | Format | NLVR2 | Q-Bench | Mantis-Eval | BLINK | MVBench | Avg |
|--------------------|:----:|:--------:|:-----:|:-------:|:-----------:|:-----:|:-------:|:----:|
| GPT-4V | - | sequence | 88.80 | 76.52 | 62.67 | 51.14 | 43.50 | 64.5 |
| Open Source Models | | | | | | | | |
| Random | - | - | 48.93 | 40.20 | 23.04 | 38.09 | 27.30 | 35.5 |
| Kosmos2 | 1.6B | merge | 49.00 | 35.10 | 30.41 | 37.50 | 21.62 | 34.7 |
| LLaVA-v1.5 | 7B | merge | 53.88 | 49.32 | 31.34 | 37.13 | 36.00 | 41.5 |
| LLava-V1.6 | 7B | merge | 58.88 | 54.80 | 45.62 | 39.55 | 40.90 | 48.0 |
| Qwen-VL-Chat | 7B | merge | 58.72 | 45.90 | 39.17 | 31.17 | 42.15 | 43.4 |
| Fuyu | 8B | merge | 51.10 | 49.15 | 27.19 | 36.59 | 30.20 | 38.8 |
| BLIP-2 | 13B | merge | 59.42 | 51.20 | 49.77 | 39.45 | 31.40 | 46.2 |
| InstructBLIP | 13B | merge | 60.26 | 44.30 | 45.62 | 42.24 | 32.50 | 45.0 |
| CogVLM | 17B | merge | 58.58 | 53.20 | 45.16 | 41.54 | 37.30 | 47.2 |
| OpenFlamingo | 9B | sequence | 36.41 | 19.60 | 12.44 | 39.18 | 7.90 | 23.1 |
| Otter-Image | 9B | sequence | 49.15 | 17.50 | 14.29 | 36.26 | 15.30 | 26.5 |
| Idefics1 | 9B | sequence | 54.63 | 30.60 | 28.11 | 24.69 | 26.42 | 32.9 |
| VideoLLaVA | 7B | sequence | 56.48 | 45.70 | 35.94 | 38.92 | 44.30 | 44.3 |
| Emu2-Chat | 37B | sequence | 58.16 | 50.05 | 37.79 | 36.20 | 39.72 | 44.4 |
| Vila | 8B | sequence | 76.45 | 45.70 | 51.15 | 39.30 | 49.40 | 52.4 |
| Idefics2 | 8B | sequence | 86.87 | 57.00 | 48.85 | 45.18 | 29.68 | 53.5 |
| Mantis-CLIP | 8B | sequence | 84.66 | 66.00 | 55.76 | 47.06 | 48.30 | 60.4 |
| Mantis-SIGLIP | 8B | sequence | 87.43 | 69.90 | **59.45** | 46.35 | 50.15 | 62.7 |
| Mantis-Flamingo | 9B | sequence | 52.96 | 46.80 | 32.72 | 38.00 | 40.83 | 42.3 |
| Mantis-Idefics2 | 8B | sequence | **89.71** | **75.20** | 57.14 | **49.05** | **51.38** | **64.5** |
| $\Delta$ over SOTA | - | - | +2.84 | +18.20 | +8.30 | +3.87 | +1.98 | +11.0 |
## Single-Image Performance
| Model | Size | TextVQA | VQA | MMB | MMMU | OKVQA | SQA | MathVista | Avg |
|-----------------|:----:|:-------:|:----:|:----:|:----:|:-----:|:----:|:---------:|:----:|
| OpenFlamingo | 9B | 46.3 | 58.0 | 32.4 | 28.7 | 51.4 | 45.7 | 18.6 | 40.2 |
| Idefics1 | 9B | 39.3 | 68.8 | 45.3 | 32.5 | 50.4 | 51.6 | 21.1 | 44.1 |
| InstructBLIP | 7B | 33.6 | 75.2 | 38.3 | 30.6 | 45.2 | 70.6 | 24.4 | 45.4 |
| Yi-VL | 6B | 44.8 | 72.5 | 68.4 | 39.1 | 51.3 | 71.7 | 29.7 | 53.9 |
| Qwen-VL-Chat | 7B | 63.8 | 78.2 | 61.8 | 35.9 | 56.6 | 68.2 | 15.5 | 54.3 |
| LLaVA-1.5 | 7B | 58.2 | 76.6 | 64.8 | 35.3 | 53.4 | 70.4 | 25.6 | 54.9 |
| Emu2-Chat | 37B | <u>66.6</u> | **84.9** | 63.6 | 36.3 | **64.8** | 65.3 | 30.7 | 58.9 |
| CogVLM | 17B | **70.4** | <u>82.3</u> | 65.8 | 32.1 | <u>64.8</u> | 65.6 | 35.0 | 59.4 |
| Idefics2 | 8B | 70.4 | 79.1 | <u>75.7</u> | **43.0** | 53.5 | **86.5** | **51.4** | **65.7** |
| Mantis-CLIP | 8B | 56.4 | 73.0 | 66.0 | 38.1 | 53.0 | 73.8 | 31.7 | 56.0 |
| Mantis-SigLIP | 8B | 59.2 | 74.9 | 68.7 | 40.1 | 55.4 | 74.9 | 34.4 | 58.2 |
| Mantis-Idefics2 | 8B | 63.5 | 77.6 | 75.7 | <u>41.1</u> | 52.6 | <u>81.3</u> | <u>40.4</u> | <u>61.7</u> |
## How to use
### Installation
```bash
# This only installs minimum packages (torch, transformers, accelerate) for inference, no redundant packages are installed.
pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
```
### Run example inference:
```python
from mantis.models.mllava import chat_mllava
from PIL import Image
import torch
image1 = "image1.jpg"
image2 = "image2.jpg"
images = [Image.open(image1), Image.open(image2)]
# load processor and model
from mantis.models.mllava import MLlavaProcessor, LlavaForConditionalGeneration
processor = MLlavaProcessor.from_pretrained("TIGER-Lab/Mantis-8B-siglip-llama3")
attn_implementation = None # or "flash_attention_2"
model = LlavaForConditionalGeneration.from_pretrained("TIGER-Lab/Mantis-8B-siglip-llama3", device_map="cuda", torch_dtype=torch.bfloat16, attn_implementation=attn_implementation)
generation_kwargs = {
"max_new_tokens": 1024,
"num_beams": 1,
"do_sample": False
}
# chat
text = "Describe the difference of <image> and <image> as much as you can."
response, history = chat_mllava(text, images, model, processor, **generation_kwargs)
print("USER: ", text)
print("ASSISTANT: ", response)
text = "How many wallets are there in image 1 and image 2 respectively?"
response, history = chat_mllava(text, images, model, processor, history=history, **generation_kwargs)
print("USER: ", text)
print("ASSISTANT: ", response)
"""
USER: Describe the difference of <image> and <image> as much as you can.
ASSISTANT: The second image has more variety in terms of colors and designs. While the first image only shows two brown leather pouches, the second image features four different pouches in various colors and designs, including a purple one with a gold coin, a red one with a gold coin, a black one with a gold coin, and a brown one with a gold coin. This variety makes the second image more visually interesting and dynamic.
USER: How many wallets are there in image 1 and image 2 respectively?
ASSISTANT: There are two wallets in image 1, and four wallets in image 2.
"""
```
### Training
See [mantis/train](https://github.com/TIGER-AI-Lab/Mantis/tree/main/mantis/train) for details
### Evaluation
See [mantis/benchmark](https://github.com/TIGER-AI-Lab/Mantis/tree/main/mantis/benchmark) for details
**Please cite our paper or give a star to out Github repo if you find this model useful**
## Citation
```
@article{Jiang2024MANTISIM,
title={MANTIS: Interleaved Multi-Image Instruction Tuning},
author={Dongfu Jiang and Xuan He and Huaye Zeng and Cong Wei and Max W.F. Ku and Qian Liu and Wenhu Chen},
journal={Transactions on Machine Learning Research},
year={2024},
volume={2024},
url={https://openreview.net/forum?id=skLtdUVaJa}
}
``` |
mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF | mradermacher | 2024-11-15T06:43:09Z | 140 | 0 | transformers | [
"transformers",
"gguf",
"en",
"de",
"fr",
"zh",
"pt",
"nl",
"ru",
"ko",
"it",
"es",
"base_model:Unbabel/TowerInstruct-WMT24-Chat-7B",
"base_model:quantized:Unbabel/TowerInstruct-WMT24-Chat-7B",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T06:28:15Z | ---
base_model: Unbabel/TowerInstruct-WMT24-Chat-7B
language:
- en
- de
- fr
- zh
- pt
- nl
- ru
- ko
- it
- es
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Unbabel/TowerInstruct-WMT24-Chat-7B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q2_K.gguf) | Q2_K | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/TowerInstruct-WMT24-Chat-7B-GGUF/resolve/main/TowerInstruct-WMT24-Chat-7B.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Ellight/code-smolLM2-135m-text-to-sql | Ellight | 2024-11-15T06:42:28Z | 127 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:HuggingFaceTB/SmolLM2-135M",
"base_model:finetune:HuggingFaceTB/SmolLM2-135M",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T05:46:33Z | ---
library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: code-smolLM2-135m-text-to-sql
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# code-smolLM2-135m-text-to-sql
This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
|
DaniilOr/multilingual_persuasion_techniques | DaniilOr | 2024-11-15T06:40:32Z | 126 | 0 | transformers | [
"transformers",
"safetensors",
"deberta-v2",
"text-classification",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-09-11T15:13:50Z | ---
license: mit
library_name: transformers
--- |
charisgao/finetuned_raid_reviews_cleaned | charisgao | 2024-11-15T06:40:31Z | 117 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-large",
"base_model:finetune:FacebookAI/roberta-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-11-15T06:38:39Z | ---
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine_tuned_raid_cleaned
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# fine_tuned_raid_cleaned
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1136
- Accuracy: 0.9800
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:--------:|
| 0.3826 | 0.0139 | 100 | 0.1739 | 0.9443 |
| 0.2556 | 0.0277 | 200 | 0.2700 | 0.9408 |
| 0.3383 | 0.0416 | 300 | 0.1667 | 0.9529 |
| 0.3672 | 0.0554 | 400 | 0.9354 | 0.7975 |
| 0.2223 | 0.0693 | 500 | 0.1584 | 0.9673 |
| 0.2197 | 0.0832 | 600 | 0.6363 | 0.8793 |
| 0.2873 | 0.0970 | 700 | 0.2169 | 0.9462 |
| 0.2201 | 0.1109 | 800 | 0.1366 | 0.9621 |
| 0.1695 | 0.1248 | 900 | 0.2912 | 0.9554 |
| 0.1912 | 0.1386 | 1000 | 0.2287 | 0.9542 |
| 0.131 | 0.1525 | 1100 | 0.1136 | 0.9800 |
| 0.1764 | 0.1663 | 1200 | 0.1770 | 0.9645 |
| 0.1195 | 0.1802 | 1300 | 0.1255 | 0.9755 |
| 0.09 | 0.1941 | 1400 | 0.1285 | 0.9758 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
|
yonderjay/house-11-14-04 | yonderjay | 2024-11-15T06:38:56Z | 193 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T05:16:38Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hfcsrd/sn29_v2_updated_1 | hfcsrd | 2024-11-15T06:37:35Z | 39 | 0 | transformers | [
"transformers",
"safetensors",
"phi3",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:14:21Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
poongslee/topic_learning_llma | poongslee | 2024-11-15T06:34:56Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:34:29Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Junho12/topic_learning_llama | Junho12 | 2024-11-15T06:34:25Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:34:00Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
goethe0101/llama-3-2-3B-wame-16bit-survey-generator3 | goethe0101 | 2024-11-15T06:33:51Z | 124 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:32:03Z | ---
base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** goethe0101
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mradermacher/Llama-3-8B-Instruct-Coder-GGUF | mradermacher | 2024-11-15T06:32:35Z | 106 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"sft",
"en",
"base_model:rombodawg/Llama-3-8B-Instruct-Coder",
"base_model:quantized:rombodawg/Llama-3-8B-Instruct-Coder",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-13T15:46:14Z | ---
base_model: rombodawg/Llama-3-8B-Instruct-Coder
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Coder-GGUF/resolve/main/Llama-3-8B-Instruct-Coder.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Serendien/topic_learning_llama | Serendien | 2024-11-15T06:31:30Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:31:15Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
WANSUB/topic_learning_llama | WANSUB | 2024-11-15T06:31:27Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:30:54Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/Llama3.1-8B-Cobalt-GGUF | mradermacher | 2024-11-15T06:28:24Z | 91 | 0 | transformers | [
"transformers",
"gguf",
"cobalt",
"valiant",
"valiant-labs",
"llama",
"llama-3.1",
"llama-3.1-instruct",
"llama-3.1-instruct-8b",
"llama-3",
"llama-3-instruct",
"llama-3-instruct-8b",
"8b",
"math",
"math-instruct",
"conversational",
"chat",
"instruct",
"en",
"dataset:sequelbox/Polytope",
"dataset:LDJnr/Pure-Dove",
"base_model:ValiantLabs/Llama3.1-8B-Cobalt",
"base_model:quantized:ValiantLabs/Llama3.1-8B-Cobalt",
"license:llama3.1",
"endpoints_compatible",
"region:us"
] | null | 2024-11-14T06:30:26Z | ---
base_model: ValiantLabs/Llama3.1-8B-Cobalt
datasets:
- sequelbox/Polytope
- LDJnr/Pure-Dove
language:
- en
library_name: transformers
license: llama3.1
model_type: llama
quantized_by: mradermacher
tags:
- cobalt
- valiant
- valiant-labs
- llama
- llama-3.1
- llama-3.1-instruct
- llama-3.1-instruct-8b
- llama-3
- llama-3-instruct
- llama-3-instruct-8b
- 8b
- math
- math-instruct
- conversational
- chat
- instruct
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/ValiantLabs/Llama3.1-8B-Cobalt
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
mradermacher/MobileLLM-125M-HF-GGUF | mradermacher | 2024-11-15T06:27:00Z | 5 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:vonjack/MobileLLM-125M-HF",
"base_model:quantized:vonjack/MobileLLM-125M-HF",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-11-15T06:24:05Z | ---
base_model: vonjack/MobileLLM-125M-HF
language:
- en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/vonjack/MobileLLM-125M-HF
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q2_K.gguf) | Q2_K | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q3_K_S.gguf) | Q3_K_S | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.IQ4_XS.gguf) | IQ4_XS | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q3_K_L.gguf) | Q3_K_L | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q5_K_S.gguf) | Q5_K_S | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q5_K_M.gguf) | Q5_K_M | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q6_K.gguf) | Q6_K | 0.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/MobileLLM-125M-HF-GGUF/resolve/main/MobileLLM-125M-HF.f16.gguf) | f16 | 0.4 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf | RichardErkhov | 2024-11-15T06:25:15Z | 364 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T05:11:49Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
asm2asm-deepseek1.3b-xtokenizer-armv8 - GGUF
- Model creator: https://huggingface.co/ahmedheakl/
- Original model: https://huggingface.co/ahmedheakl/asm2asm-deepseek1.3b-xtokenizer-armv8/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q2_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q2_K.gguf) | Q2_K | 0.52GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K_S.gguf) | Q3_K_S | 0.6GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K.gguf) | Q3_K | 0.66GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K_M.gguf) | Q3_K_M | 0.66GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q3_K_L.gguf) | Q3_K_L | 0.69GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.IQ4_XS.gguf) | IQ4_XS | 0.7GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_0.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_0.gguf) | Q4_0 | 0.72GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.IQ4_NL.gguf) | IQ4_NL | 0.73GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_K_S.gguf) | Q4_K_S | 0.76GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_K.gguf) | Q4_K | 0.81GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_K_M.gguf) | Q4_K_M | 0.81GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_1.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q4_1.gguf) | Q4_1 | 0.8GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_0.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_0.gguf) | Q5_0 | 0.87GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_K_S.gguf) | Q5_K_S | 0.89GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_K.gguf) | Q5_K | 0.93GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_K_M.gguf) | Q5_K_M | 0.93GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_1.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q5_1.gguf) | Q5_1 | 0.95GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q6_K.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q6_K.gguf) | Q6_K | 1.09GB |
| [asm2asm-deepseek1.3b-xtokenizer-armv8.Q8_0.gguf](https://huggingface.co/RichardErkhov/ahmedheakl_-_asm2asm-deepseek1.3b-xtokenizer-armv8-gguf/blob/main/asm2asm-deepseek1.3b-xtokenizer-armv8.Q8_0.gguf) | Q8_0 | 1.33GB |
Original model description:
---
library_name: transformers
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: asm2asm-deepseek-1.3b-500k-mac-x86-O0-arm-gnueabi-gcc
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# asm2asm-deepseek-1.3b-500k-mac-x86-O0-arm-gnueabi-gcc
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu118
- Datasets 3.0.0
- Tokenizers 0.19.1
|
stablediffusionapi/cleanDrawCartoonStyle | stablediffusionapi | 2024-11-15T06:22:54Z | 31 | 0 | diffusers | [
"diffusers",
"safetensors",
"modelslab.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2024-11-15T06:21:02Z | ---
license: creativeml-openrail-m
tags:
- modelslab.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# API Inference
## Get API Key
Get API key from [ModelsLab API](http://modelslab.com), No Payment needed.
Replace Key in below code, change **model_id** to "cleanDrawCartoonStyle"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://docs.modelslab.com)
Try model for free: [Generate Images](https://modelslab.com/models/cleanDrawCartoonStyle)
Model link: [View model](https://modelslab.com/models/cleanDrawCartoonStyle)
View all models: [View Models](https://modelslab.com/models)
import requests
import json
url = "https://modelslab.com/api/v6/images/text2img"
payload = json.dumps({
"key": "your_api_key",
"model_id": "cleanDrawCartoonStyle",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN** |
idoo0/vit-plant-test | idoo0 | 2024-11-15T06:18:05Z | 9 | 0 | null | [
"tensorboard",
"safetensors",
"vit",
"image-classification",
"pytorch",
"huggingpics",
"model-index",
"region:us"
] | image-classification | 2024-11-15T06:17:53Z | ---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: vit-plant-test
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.5421686768531799
---
# vit-plant-test
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### Anthracnose Plant Disease
#### Bacterial Spot Plant Disease
#### Black Rot Plant Disease
#### Black Spot Plant Disease
#### Downy Mildew Plant Disease
#### Early Blight Plant Disease
#### Late Blight Plant Disease
#### Leaf Spot Plant Disease
#### Powdery Mildew Plant Disease
#### Rust Plant Disease
#### Spider Spot Plant Disease
#### Viral Plant Disease
 |
mradermacher/AMD-Llama-135m-code-i1-GGUF | mradermacher | 2024-11-15T06:17:38Z | 16 | 0 | transformers | [
"transformers",
"gguf",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:manu/project_gutenberg",
"base_model:amd/AMD-Llama-135m-code",
"base_model:quantized:amd/AMD-Llama-135m-code",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix"
] | null | 2024-11-15T06:03:36Z | ---
base_model: amd/AMD-Llama-135m-code
datasets:
- cerebras/SlimPajama-627B
- manu/project_gutenberg
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/amd/AMD-Llama-135m-code
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/AMD-Llama-135m-code-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ1_S.gguf) | i1-IQ1_S | 0.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ1_M.gguf) | i1-IQ1_M | 0.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.1 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ2_S.gguf) | i1-IQ2_S | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ2_M.gguf) | i1-IQ2_M | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q2_K.gguf) | i1-Q2_K | 0.2 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ3_S.gguf) | i1-IQ3_S | 0.2 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.2 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ3_M.gguf) | i1-IQ3_M | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.2 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 0.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 0.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 0.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q4_0.gguf) | i1-Q4_0 | 0.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.2 | |
| [GGUF](https://huggingface.co/mradermacher/AMD-Llama-135m-code-i1-GGUF/resolve/main/AMD-Llama-135m-code.i1-Q6_K.gguf) | i1-Q6_K | 0.2 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mlx-community/falcon-mamba-7b-4bit | mlx-community | 2024-11-15T06:14:16Z | 5 | 0 | mlx | [
"mlx",
"safetensors",
"falcon_mamba",
"en",
"dataset:tiiuae/falcon-refinedweb",
"dataset:HuggingFaceFW/fineweb-edu",
"base_model:tiiuae/falcon-mamba-7b",
"base_model:quantized:tiiuae/falcon-mamba-7b",
"license:other",
"model-index",
"4-bit",
"region:us"
] | null | 2024-11-15T06:12:45Z | ---
base_model: tiiuae/falcon-mamba-7b
datasets:
- tiiuae/falcon-refinedweb
- HuggingFaceFW/fineweb-edu
language:
- en
license: other
license_name: falcon-mamba-7b-license
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
tags:
- mlx
model-index:
- name: falcon-mamba-7b
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 33.36
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 19.88
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 3.63
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 8.05
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 10.86
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 14.47
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
name: Open LLM Leaderboard
---
# mlx-community/falcon-mamba-7b-4bit
The Model [mlx-community/falcon-mamba-7b-4bit](https://huggingface.co/mlx-community/falcon-mamba-7b-4bit) was converted to MLX format from [tiiuae/falcon-mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b) using mlx-lm version **0.19.2**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/falcon-mamba-7b-4bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
kohubi/llama_pre_model | kohubi | 2024-11-15T06:11:55Z | 179 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-14T07:16:47Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
goethe0101/llama-3-2-3B-wame-16bit-survey-generator2 | goethe0101 | 2024-11-15T06:10:40Z | 126 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:08:44Z | ---
base_model: unsloth/llama-3.2-3b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** goethe0101
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mradermacher/zephyr-7b-dpo-full-i1-GGUF | mradermacher | 2024-11-15T06:02:42Z | 27 | 0 | transformers | [
"transformers",
"gguf",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"en",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:alignment-handbook/zephyr-7b-dpo-full",
"base_model:quantized:alignment-handbook/zephyr-7b-dpo-full",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-14T23:19:31Z | ---
base_model: alignment-handbook/zephyr-7b-dpo-full
datasets:
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/alignment-handbook/zephyr-7b-dpo-full
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/zephyr-7b-dpo-full-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/zephyr-7b-dpo-full-i1-GGUF/resolve/main/zephyr-7b-dpo-full.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
ssai0915/fake_new_data_train_llama | ssai0915 | 2024-11-15T06:02:09Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T06:01:57Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
leptonai/Llama-3.2-1B-Instruct-Regression-Test | leptonai | 2024-11-15T05:56:50Z | 2,723 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-classification",
"facebook",
"meta",
"llama-3",
"text-generation",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T05:19:32Z | ---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: llama3.2
extra_gated_prompt: >-
### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
Llama 3.2 Version Release Date: September 25, 2024
“Agreement” means the terms and conditions for use, reproduction, distribution
and modification of the Llama Materials set forth herein.
“Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
distributed by Meta at https://llama.meta.com/doc/overview.
“Licensee” or “you” means you, or your employer or any other person or entity (if you are
entering into this Agreement on such person or entity’s behalf), of the age required under
applicable laws, rules or regulations to provide legal consent and that has legal authority
to bind your employer or such other person or entity if you are entering in this Agreement
on their behalf.
“Llama 3.2” means the foundational large language models and software and algorithms, including
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
https://www.llama.com/llama-downloads.
“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and
any portion thereof) made available under this Agreement.
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or,
if you are an entity, your principal place of business is in the EEA or Switzerland)
and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide,
non-transferable and royalty-free limited license under Meta’s intellectual property or other rights
owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works
of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works thereof),
or a product or service (including another AI model) that contains any of them, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
on a related website, user interface, blogpost, about page, or product documentation. If you use the
Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the
following attribution notice within a “Notice” text file distributed as a part of such copies:
“Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
Inc. All Rights Reserved.”
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby
incorporated by reference into this Agreement.
2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licensee’s affiliates,
is greater than 700 million monthly active users in the preceding calendar month, you must request
a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials,
neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates,
except as required for reasonable and customary use in describing and redistributing the Llama Materials or as
set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required
to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible
at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark
will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
party arising out of or related to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of
California without regard to choice of law principles, and the UN Convention on Contracts for the International
Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
any dispute arising out of this Agreement.
### Llama 3.2 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”).
The most recent copy of this policy can be found at
[https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
#### Prohibited Uses
We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
1. Violate the law or others’ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
9. Guns and illegal weapons (including weapon development)
10. Illegal drugs and regulated/controlled substances
11. Operation of critical infrastructure, transportation technologies, or heavy machinery
12. Self-harm or harm to others, including suicide, cutting, and eating disorders
13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
16. Generating, promoting, or further distributing spam
17. Impersonating another individual without consent, authorization, or legal right
18. Representing that the use of Llama 3.2 or outputs are human-generated
19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI system
5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: >-
The information you provide will be collected, stored, processed and shared in
accordance with the [Meta Privacy
Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
## Model Information
The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama-models/tree/main/models/llama3_2). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-1B-Instruct, for use with `transformers` and with the original `llama` codebase.
### Use with transformers
Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-1B-Instruct"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
##
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Total | 830k | 86k | | 240 | 0 |
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 63.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 40.1 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 19.0 | 17.2 |
| Instruction following | | IFEval | 0 | avg(prompt/instruction acc loose/strict) | 59.5 | 77.4 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 77.7 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 47.3 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 78.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 32.8 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 69.8 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 67.0 | 70.9 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 34.3 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | 19.8 | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | 63.3 | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | 84.7 | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 58.2 | 68.9 |
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro\_avg/acc) | Portuguese | 39.82 | 54.48 | 62.12 |
| | | Spanish | 41.5 | 55.1 | 62.5 |
| | | Italian | 39.8 | 53.8 | 61.6 |
| | | German | 39.2 | 53.3 | 60.6 |
| | | French | 40.5 | 54.6 | 62.3 |
| | | Hindi | 33.5 | 43.3 | 50.9 |
| | | Thai | 34.7 | 44.5 | 50.3 |
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
|
AlekseyCalvin/TROTSKY_Flux_LoRA_SilverAgeLiberators_v1_single_blocks-proj_out-layer_only | AlekseyCalvin | 2024-11-15T05:43:41Z | 10 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | 2024-09-26T11:48:30Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: TROTSKY
---
# Trotskyflux
<!-- <Gallery /> -->
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `TROTSKY` to trigger the image generation.
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('AlekseyCalvin/Trotskyflux', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
wsklee/distilbert-sentiment-imdb-cft | wsklee | 2024-11-15T05:41:40Z | 159 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"generated_from_trainer",
"base_model:distilbert/distilbert-base-uncased",
"base_model:finetune:distilbert/distilbert-base-uncased",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-11-15T05:25:35Z | ---
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: distilbert-sentiment-imdb-cft
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-sentiment-imdb-cft
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Accuracy: 0.9856
- Pos Similarity: 0.9538
- Neg Similarity: 0.4913
- F1: 0.9927
- Precision: 1.0
- Recall: 0.9856
- Loss: 3.5397
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Accuracy | Pos Similarity | Neg Similarity | F1 | Precision | Recall | Validation Loss |
|:-------------:|:------:|:----:|:--------:|:--------------:|:--------------:|:------:|:---------:|:------:|:---------------:|
| 3.8563 | 1.1364 | 200 | 0.9728 | 0.9662 | 0.7048 | 0.9862 | 1.0 | 0.9728 | 3.5778 |
| 3.5857 | 2.2727 | 400 | 0.9848 | 0.9666 | 0.5691 | 0.9923 | 1.0 | 0.9848 | 3.5278 |
| 3.5032 | 3.4091 | 600 | 0.9856 | 0.9538 | 0.4913 | 0.9927 | 1.0 | 0.9856 | 3.5397 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3
|
Kapzo/demo-donut_extraction-v4 | Kapzo | 2024-11-15T05:38:37Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"vision-encoder-decoder",
"image-text-to-text",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2024-11-15T02:43:22Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Beehzod/speecht5_finetuned_uz_customData2 | Beehzod | 2024-11-15T05:36:32Z | 335 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"base_model:microsoft/speecht5_tts",
"base_model:finetune:microsoft/speecht5_tts",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-to-audio | 2024-11-15T05:19:01Z | ---
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_uz_customData2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# speecht5_finetuned_uz_customData2
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4331
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 0.5399 | 3.1217 | 100 | 0.4750 |
| 0.4713 | 6.2433 | 200 | 0.4548 |
| 0.444 | 9.3650 | 300 | 0.4334 |
| 0.4355 | 12.4867 | 400 | 0.4348 |
| 0.4214 | 15.6084 | 500 | 0.4331 |
### Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3
|
CGscorpion/vit-base-patch32-384-finetuned-eurosat-albumentations | CGscorpion | 2024-11-15T05:25:40Z | 7 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:google/vit-base-patch32-384",
"base_model:finetune:google/vit-base-patch32-384",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-11-15T04:27:30Z | ---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch32-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch32-384-finetuned-eurosat-albumentations
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9726027397260274
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vit-base-patch32-384-finetuned-eurosat-albumentations
This model is a fine-tuned version of [google/vit-base-patch32-384](https://huggingface.co/google/vit-base-patch32-384) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1871
- Accuracy: 0.9726
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| 0.7204 | 0.9412 | 12 | 0.5695 | 0.7397 |
| 0.4269 | 1.9804 | 25 | 0.2537 | 0.9178 |
| 0.1605 | 2.9412 | 37 | 0.3347 | 0.8767 |
| 0.0758 | 3.9804 | 50 | 0.2203 | 0.9041 |
| 0.0405 | 4.9412 | 62 | 0.3563 | 0.9178 |
| 0.0358 | 5.9804 | 75 | 0.2326 | 0.9315 |
| 0.0188 | 6.9412 | 87 | 0.2046 | 0.9315 |
| 0.026 | 7.9804 | 100 | 0.2195 | 0.8904 |
| 0.0582 | 8.9412 | 112 | 0.3378 | 0.9178 |
| 0.0113 | 9.9804 | 125 | 0.2685 | 0.9178 |
| 0.0081 | 10.9412 | 137 | 0.2443 | 0.9315 |
| 0.0091 | 11.9804 | 150 | 0.4675 | 0.9041 |
| 0.0065 | 12.9412 | 162 | 0.3252 | 0.9452 |
| 0.0026 | 13.9804 | 175 | 0.1871 | 0.9726 |
| 0.0043 | 14.9412 | 187 | 0.2256 | 0.9589 |
| 0.0094 | 15.9804 | 200 | 0.1980 | 0.9452 |
| 0.0028 | 16.9412 | 212 | 0.2928 | 0.9315 |
| 0.0003 | 17.9804 | 225 | 0.2241 | 0.9726 |
| 0.0006 | 18.9412 | 237 | 0.2396 | 0.9726 |
| 0.0012 | 19.9804 | 250 | 0.2663 | 0.9315 |
| 0.0001 | 20.9412 | 262 | 0.2266 | 0.9726 |
| 0.0002 | 21.9804 | 275 | 0.2637 | 0.9452 |
| 0.0001 | 22.9412 | 287 | 0.2873 | 0.9452 |
| 0.0003 | 23.9804 | 300 | 0.2068 | 0.9589 |
| 0.0001 | 24.9412 | 312 | 0.2485 | 0.9452 |
| 0.0047 | 25.9804 | 325 | 0.3375 | 0.9178 |
| 0.0015 | 26.9412 | 337 | 0.3132 | 0.9589 |
| 0.0001 | 27.9804 | 350 | 0.3148 | 0.9452 |
| 0.0025 | 28.9412 | 362 | 0.2533 | 0.9452 |
| 0.0038 | 29.9804 | 375 | 0.2860 | 0.9315 |
| 0.0025 | 30.9412 | 387 | 0.2785 | 0.9452 |
| 0.0031 | 31.9804 | 400 | 0.3246 | 0.9452 |
| 0.0 | 32.9412 | 412 | 0.3367 | 0.9452 |
| 0.0006 | 33.9804 | 425 | 0.2625 | 0.9726 |
| 0.0 | 34.9412 | 437 | 0.2689 | 0.9589 |
| 0.0007 | 35.9804 | 450 | 0.2891 | 0.9726 |
| 0.0003 | 36.9412 | 462 | 0.4523 | 0.9315 |
| 0.0003 | 37.9804 | 475 | 0.3426 | 0.9452 |
| 0.0001 | 38.9412 | 487 | 0.3167 | 0.9589 |
| 0.0 | 39.9804 | 500 | 0.3237 | 0.9589 |
| 0.0002 | 40.9412 | 512 | 0.3085 | 0.9589 |
| 0.0 | 41.9804 | 525 | 0.3095 | 0.9589 |
| 0.0 | 42.9412 | 537 | 0.3049 | 0.9589 |
| 0.0002 | 43.9804 | 550 | 0.3039 | 0.9589 |
| 0.0001 | 44.9412 | 562 | 0.3044 | 0.9589 |
| 0.0001 | 45.9804 | 575 | 0.3031 | 0.9726 |
| 0.0 | 46.9412 | 587 | 0.3028 | 0.9726 |
| 0.0 | 47.9804 | 600 | 0.3027 | 0.9726 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 2.21.0
- Tokenizers 0.20.3
|
Ellight/code-oute-1-65m-text-to-sql | Ellight | 2024-11-15T05:23:41Z | 134 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:OuteAI/Lite-Oute-1-65M",
"base_model:finetune:OuteAI/Lite-Oute-1-65M",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T05:04:28Z | ---
library_name: transformers
license: apache-2.0
base_model: OuteAI/Lite-Oute-1-65M
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: code-oute-1-65m-text-to-sql
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# code-oute-1-65m-text-to-sql
This model is a fine-tuned version of [OuteAI/Lite-Oute-1-65M](https://huggingface.co/OuteAI/Lite-Oute-1-65M) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
|
WANSUB/fake_new_data_train_llama | WANSUB | 2024-11-15T05:22:47Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T05:22:32Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
sbrian/fake_new_data_train_llma | sbrian | 2024-11-15T05:20:30Z | 180 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-15T05:20:21Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
vantubk1386/vits_ljs_welsh_female_monospeaker | vantubk1386 | 2024-11-15T05:12:47Z | 111 | 0 | transformers | [
"transformers",
"safetensors",
"vits",
"text-to-audio",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | text-to-audio | 2024-11-08T09:36:33Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mav23/openbuddy-llama3.2-1b-v23.1-131k-GGUF | mav23 | 2024-11-15T05:10:43Z | 94 | 0 | null | [
"gguf",
"llama-3.2",
"text-generation",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"fi",
"license:llama3.2",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-11-15T04:52:00Z | ---
language:
- zh
- en
- fr
- de
- ja
- ko
- it
- fi
pipeline_tag: text-generation
tags:
- llama-3.2
license: llama3.2
---
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
Evaluation result of this model: [Evaluation.txt](Evaluation.txt)
# Copyright Notice
**Built with Meta Llama 3**
Base Model: Llama-3.2-1B-Instruct
License: https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE
Acceptable Use Policy: https://llama.meta.com/llama3/use-policy
This model is intended for use in English and Chinese.
# Prompt Format
We recommend using the fast tokenizer from `transformers`, which should be enabled by default in the `transformers` and `vllm` libraries. Other implementations including `sentencepiece` may not work as expected, especially for special tokens like `<|role|>`, `<|says|>` and `<|end|>`.
```
<|role|>system<|says|>You(assistant) are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human(user).
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
You cannot access the internet, but you have vast knowledge, cutoff: 2023-04.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), not related to GPT or OpenAI.<|end|>
<|role|>user<|says|>History input 1<|end|>
<|role|>assistant<|says|>History output 1<|end|>
<|role|>user<|says|>History input 2<|end|>
<|role|>assistant<|says|>History output 2<|end|>
<|role|>user<|says|>Current input<|end|>
<|role|>assistant<|says|>
```
This format is also defined in `tokenizer_config.json`, which means you can directly use `vllm` to deploy an OpenAI-like API service. For more information, please refer to the [vllm documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。
|
Hev832/hex-rvc | Hev832 | 2024-11-15T05:04:38Z | 0 | 5 | null | [
"music",
"RVC",
"Voice Conversion",
"Harmonify",
"RVC V2",
"UVR5",
"audio-to-audio",
"license:openrail",
"region:us"
] | audio-to-audio | 2024-06-09T00:13:37Z | ---
tags:
- music
- RVC
- Voice Conversion
- Harmonify
- RVC V2
- UVR5
license: openrail
pipeline_tag: audio-to-audio
---
# **Hex RVC Fork**
A simple, high-quality voice conversion tool focused on ease of use and performance.
[Colab Notebook](https://colab.research.google.com/drive/1ntQ_ykZ0P_HVF_84zULixs_kigKmCVJP?usp=sharing)
---
## **Overview**
Hex RVC Fork is a streamlined voice conversion tool designed to deliver high-quality results with minimal setup. This project is optimized for ease of use, enabling users to convert voices using state-of-the-art models effortlessly.
### **Key Features**
- **High-quality voice conversion** using advanced techniques.
- **User-friendly interface** powered by [Gradio](https://gradio.app/).
- **Optimized for performance** with support for efficient F0 extraction methods.
- **Colab support** for quick experimentation without local setup.
### **Note**
- The **Streamlit WebUI** is no longer being updated. Please use the **Gradio WebUI** for the latest features and support.
---
## **Getting Started**
### **Colab Notebook**
To quickly try out Hex RVC, you can use the [Colab Notebook](https://colab.research.google.com/drive/1ntQ_ykZ0P_HVF_84zULixs_kigKmCVJP?usp=sharing). Simply open the link, run the cells, and start converting voices in minutes!
### **Local Setup**
If you prefer running the tool locally, you can clone this repository and set up your environment using the following commands:
```bash
git clone https://huggingface.co/Hev832/hex-rvc
cd hex-rvc
pip install -r requirements.txt
```
After installation, launch the Gradio WebUI:
```bash
python app.py
```
---
## **Credits**
This project is built on the shoulders of giants. Many thanks to the original creators and contributors:
- **[Eempostor](https://discordapp.com/users/818050831034613771)** - Original project inspiration.
- **[Applio](https://github.com/IAHispano/Applio-RVC-Fork)** by [IAHispano](https://github.com/IAHispano) - This repo is based on their fork.
- **[CNChTu](https://github.com/CNChTu)** - Creator of the [FCPE](https://github.com/CNChTu/FCPE) F0 extraction method.
- **[So Vits SVC](https://github.com/svc-develop-team/so-vits-svc)** - Provided the F0 method script.
- **[ChatGPT](https://chat.openai.com/)**, **[Phind](https://www.phind.com/)** & **[Blackbox](https://www.blackbox.ai/)** - Assistance with documentation and troubleshooting.
---
## **Contributing**
We welcome contributions to enhance Hex RVC Fork! If you have ideas, suggestions, or bug reports, please feel free to open an New discussion or submit a pull request.
---
## **License**
This project is open-source and available under the Openrail License.
---
## **Support**
For any questions or support, feel free to reach out via the HF Discussion page or contact the original contributors. |
therealcyberlord/MindQwen-2.5-0.5B-Instruct-GGUF | therealcyberlord | 2024-11-15T05:02:48Z | 7 | 0 | transformers | [
"transformers",
"gguf",
"qwen2",
"text-generation-inference",
"unsloth",
"trl",
"en",
"base_model:unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit",
"base_model:quantized:unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T04:39:37Z | ---
base_model: unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** therealcyberlord
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
openthaigpt/openthaigpt-1.0.0-7b-chat-gguf | openthaigpt | 2024-11-15T04:56:31Z | 52 | 5 | transformers | [
"transformers",
"gguf",
"openthaigpt",
"llama",
"text-generation",
"th",
"en",
"arxiv:2411.07238",
"license:llama2",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-04-08T08:26:11Z | ---
license: llama2
language:
- th
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- openthaigpt
- llama
---
# 🇹🇭 OpenThaiGPT 7b 1.0.0 4 bits and 8 bits in GGUF Format
[More Info](https://openthaigpt.aieat.or.th/)
🇹🇭 **OpenThaiGPT 7b Version 1.0.0** is an advanced 7-billion-parameter Thai language chat model based on LLaMA v2 released on April 8, 2024. It has been specifically fine-tuned for Thai instructions and enhanced by incorporating over 10,000 of the most commonly used Thai words into the large language model's (LLM) dictionary, significantly boosting its response speed.
## Highlights
- **Leading-edge Thai language LLM**, setting new benchmarks by achieving the highest average scores across several Thai language exams when compared to all other open-source Thai LLMs.
- **The First 70b Thai opensource LLM**, achieving the higher score on Thai exams than OpenAI GPT 3.5, Google Gemini, and Claude 3 Haiku.
- **Support for extended conversations** across multiple turns.
- Support the use case of **Retrieval Augmented Generation (RAG)** for enriched response generation.
- **Generation speeds increased by tenfold**, thanks to the addition of 10,000 frequently used Thai words to the model's dictionary.
- Pretrained upon a foundation of **more than 65 billion Thai language words** and meticulously fine-tuned with over 1 million Thai instruction examples.
- Capable of understanding and processing **input contexts of up to 4096 Thai words**, allowing for detailed and complex instructions.
## Benchmark by OpenThaiGPT Eval
** Please take a look at ``OTG 7b (April 2024)`` for this model's evaluation result.
| **Exams** | **OTG 7b (Aug 2023)** | **OTG 13b (Dec 2023)** | <b style="color:blue">OTG 7b (April 2024)</b> | **OTG 13b (April 2024)** | **OTG 70b (April 2024)** | **SeaLLM 7b v1** | **SeaLLM 7b v2** | **SeaLion 7b** | **WanchanGLM 7b** | **Sailor-7b-Chat** | **TyphoonGPT 7b Instruct** | **GPT3.5** | **GPT4** | **Gemini Pro** | **Gemini 1.5** | **Claude 3 Haiku** | **Claude 3 Sonnet** | **Claude 3 Opus** |
|----------------------------|-----------------------|------------------------|-------------------------|--------------------------|--------------------------|------------------|------------------|----------------|-------------------|--------------------|----------------------------|------------|----------|----------------|----------------|--------------------|---------------------|-------------------|
| **A-Level** | 17.50% | 34.17% | <b style="color:blue">25.00%</b> | 30.83% | 45.83% | 18.33% | 34.17% | 21.67% | 17.50% | 40.00% | 37.50% | 38.33% | 65.83% | 56.67% | 55.83% | 58.33% | 59.17% | 77.50% |
| **TGAT** | 24.00% | 22.00% | <b style="color:blue">22.00%</b> | 36.00% | 36.00% | 14.00% | 28.00% | 24.00% | 16.00% | 34.00% | 30.00% | 28.00% | 44.00% | 22.00% | 28.00% | 36.00% | 34.00% | 46.00% |
| **TPAT1** | 22.50% | 47.50% | <b style="color:blue">42.50%</b> | 27.50% | 62.50% | 22.50% | 27.50% | 22.50% | 17.50% | 40.00% | 47.50% | 45.00% | 52.50% | 52.50% | 50.00% | 52.50% | 50.00% | 62.50% |
| **thai_investment_consultant_exams** | 8.00% | 28.00% | <b style="color:blue">76.00%</b> | 84.00% | 68.00% | 16.00% | 28.00% | 24.00% | 16.00% | 24.00% | 32.00% | 40.00% | 64.00% | 52.00% | 32.00% | 44.00% | 64.00% | 72.00% |
| **facebook_beleble_tha_200** | 25.00% | 45.00% | <b style="color:blue">34.50%</b> | 39.50% | 70.00% | 13.50% | 51.00% | 27.00% | 24.50% | 63.00% | 51.50% | 50.00% | 72.50% | 65.00% | 74.00% | 63.50% | 77.00% | 90.00% |
| **xcopa_th_200** | 45.00% | 56.50% | <b style="color:blue">49.50%</b> | 51.50% | 74.50% | 26.50% | 47.00% | 51.50% | 48.50% | 68.50% | 65.00% | 64.00% | 82.00% | 68.00% | 74.00% | 64.00% | 80.00% | 86.00% |
| **xnli2.0_th_200** | 33.50% | 34.50% | <b style="color:blue">39.50%</b> | 31.00% | 47.00% | 21.00% | 43.00% | 37.50% | 33.50% | 16.00% | 20.00% | 50.00% | 69.00% | 53.00% | 54.50% | 50.00% | 68.00% | 68.50% |
| **ONET M3** | 17.85% | 38.86% | <b style="color:blue">34.11%</b> | 39.36% | 56.15% | 15.58% | 23.92% | 21.79% | 19.56% | 21.37% | 28.03% | 37.91% | 49.97% | 55.99% | 57.41% | 52.73% | 40.60% | 63.87% |
| **ONET M6** | 21.14% | 28.87% | <b style="color:blue">22.53%</b> | 23.32% | 42.85% | 15.09% | 19.48% | 16.96% | 20.67% | 28.64% | 27.46% | 34.44% | 46.29% | 45.53% | 50.23% | 34.79% | 38.49% | 48.56% |
| **AVERAGE SCORE** | 23.83% | 37.27% | <b style="color:blue;font-size:1.3em">38.40%</b> | 40.33% | 55.87% | 18.06% | 33.56% | 27.44% | 23.75% | 37.28% | 37.67% | 43.07% | 60.68% | 52.30% | 52.89% | 50.65% | 56.81% | 68.32% |
Thai language multiple choice exams, Test on unseen test sets, Zero-shot learning. Benchmark source code and exams information: https://github.com/OpenThaiGPT/openthaigpt_eval
(Updated on: 7 April 2024)
## Licenses
**Source Code**: License Apache Software License 2.0.<br>
**Weight**: Research and **Commercial uses**.<br>
## Sponsors
<img src="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/FDC9WYN2iykQbVW1rY4q5.png" width="600px">
## Supports
- Official website: https://openthaigpt.aieat.or.th
- Facebook page: https://web.facebook.com/groups/openthaigpt
- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
- E-mail: [email protected]
## Prompt Format
Prompt format is based on Llama2 with a small modification (Adding "###" to specify the context part)
```
<s>[INST] <<SYS>
{system_prompt}
<</SYS>>
{human_turn1}###{context_turn1} [/INST]{assistant_turn1}</s><s>{human_turn2}###{context_turn2} [/INST] ...
```
### System prompt:
```
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
```
### Examples
#### Single Turn Conversation Example
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]
```
#### Single Turn Conversation with Context (RAG) Example
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
กรุงเทพมีพื้นที่เท่าไร่###กรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน [/INST]
```
#### Multi Turn Conversation Example
##### First turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]
```
##### Second turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]
```
##### Third turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]ได้เลยค่ะ ส้มตำเป็นเมนูที่ทำง่ายและอร่อย มาเริ่มกันเลยนะคะ</s><s>เริ่มได้เลย [/INST]
```
##### Fourth turn
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
สวัสดีครับ [/INST]สวัสดีค่ะ มีคำถามอะไร ถามได้เลย</s><s>ขอสูตรทำส้มตำหน่อย [/INST]ได้เลยค่ะ ส้มตำเป็นเมนูที่ทำง่ายและอร่อย มาเริ่มกันเลยนะคะ</s><s>เริ่มได้เลย [/INST]
ตำไทยเป็นเมนูที่ใครๆ ก็คุ้นเคย ด้วยรสชาติที่กลมกล่อม หวาน เปรี้ยว เค็ม เผ็ด ครบรส วันนี้เราจะมาทำส้มตำด้วยกันค่ะ สิ่งแรกที่ต้องมีคือเครื่องปรุงดังนี้
- มะละกอดิบ 1 ลูก
- กุ้งแห้ง 1/2 ถ้วย
- กระเทียม 3 กลีบ
- พริกขี้หนู 3 เม็ด
- น้ำตาลปี๊บ 1 ช้อนโต๊ะ
- น้ำปลา 2 ช้อนโต๊ะ
- มะนาว 1 ลูก
- งาขาวคั่ว 1/4 ถ้วย
วิธีทำมีดังนี้ค่ะ
1. เริ่มจากล้างมะละกอให้สะอาด แล้วใช้มีดปอกเปลือก เอาไส้ออก หั่นเป็นเส้นบางๆ เตรียมไว้
2. ตำกุ้งแห้งให้ละเอียด แล้วตักขึ้นพักไว้
3. ใช้ครกหินหรือเครื่องปั่น บดพริกขี้หนูกับกระเทียมให้ละเอียด
4. ใส่กุ้งแห้งที่ตำแล้วลงไปผสม ตามด้วยน้ำตาลปี๊บ น้ำปลา มะนาว และเส้นมะละกอ คลุกเคล้าให้เข้ากัน
5. ชิมรสให้ได้รสหวาน เปรี้ยว เค็ม เผ็ด จากนั้นตักขึ้นเสิร์ฟพร้อมผักสด อาทิ กะหล่ำปลี ถั่วงอก แครอท ผักบุ้ง</s><s>ขอบคุณครับ [/INST]
```
#### Multi Turn Conversation with Context (RAG) Example
```
<s>[INST] <<SYS>
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด
<</SYS>>
กรุงเทพมีพื้นที่เท่าไร่###กรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน [/INST]
กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม.</s><s>และประชากรล่ะ [/INST]
```
## How to use
### Huggingface
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Ensure CUDA is available
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print(f"Using device: {device}")
# Init Model
model_path="openthaigpt/openthaigpt-1.0.0-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.float16)
model.to(device)
# Prompt
prompt = "สวัสดีครับ OpenThaiGPT"
llama_prompt = f"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด<</SYS>>\n\n{prompt} [/INST]"
inputs = tokenizer.encode(llama_prompt, return_tensors="pt")
inputs = inputs.to(device)
# Generate
outputs = model.generate(inputs, max_length=512, num_return_sequences=1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
### vLLM
1. Install VLLM (https://github.com/vllm-project/vllm)
2. Run server
```bash
python -m vllm.entrypoints.api_server --model /path/to/model --tensor-parallel-size num_gpus
```
3. Run inference (CURL example)
```bash
curl --request POST \
--url http://localhost:8000/generate \
--header "Content-Type: application/json" \
--data '{"prompt": "<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด\n<</SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]","use_beam_search": false, "temperature": 0.1, "max_tokens": 512, "top_p": 0.75, "top_k": 40, "frequency_penalty": 0.3 "stop": "</s>"}'
```
### LlamaCPP (for GGUF)
1. Build and Install LlamaCPP (LLAMA_CUBLAS=1 is for GPU inference)
```bash
git clone https://github.com/ggerganov/llama.cpp.git \
&& cd llama.cpp \
&& make -j LLAMA_CUBLAS=1 CUDA_DOCKER_ARCH=all
```
2. Run server
```bash
./server -m /path/to/ggml-model-f16.gguf -c 3072 -ngl 81 -ts 1,1 --host 0.0.0.0
```
3. Run inference (CURL example)
```bash
curl --location 'http://localhost:8000/completion' \
--header 'Content-Type: application/json' \
--data '{
"prompt":"<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด friendly\n\n<<SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]",
"max_tokens": 512,
"stop":"</s>"
}'
```
### GPU Memory Requirements
| **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
|------------------|----------------|------------------------|------------------------|---------------------------------------------|
| **7b** | 24 GB | 12 GB | 6 GB | Nvidia RTX 4060 8GB |
| **13b** | 48 GB | 24 GB | 12 GB | Nvidia RTX 4070 16GB |
| **70b** | 192 GB | 96 GB | 48 GB | Nvidia RTX 4090 24GB x 2 cards |
### Authors
* Kobkrit Viriyayudhakorn ([email protected])
* Sumeth Yuenyong ([email protected])
* Thaweewat Rugsujarit ([email protected])
* Jillaphat Jaroenkantasima ([email protected])
* Norapat Buppodom ([email protected])
* Koravich Sangkaew ([email protected])
* Peerawat Rojratchadakorn ([email protected])
* Surapon Nonesung ([email protected])
* Chanon Utupon ([email protected])
* Sadhis Wongprayoon ([email protected])
* Nucharee Thongthungwong ([email protected])
* Chawakorn Phiantham ([email protected])
* Patteera Triamamornwooth ([email protected])
* Nattarika Juntarapaoraya ([email protected])
* Kriangkrai Saetan ([email protected])
* Pitikorn Khlaisamniang ([email protected])
### Citation
If OpenThaiGPT has been beneficial for your work, kindly consider citing it as follows:
#### Bibtex
```bibtex
@misc{yuenyong2024openthaigpt15thaicentricopen,
title={OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model},
author={Sumeth Yuenyong and Kobkrit Viriyayudhakorn and Apivadee Piyatumrong and Jillaphat Jaroenkantasima},
year={2024},
eprint={2411.07238},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2411.07238},
}
```
#### APA Style (for TXT, MS Word)
```
Yuenyong, S., Viriyayudhakorn, K., Piyatumrong, A., & Jaroenkantasima, J. (2024). OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model. arXiv [Cs.CL]. Retrieved from http://arxiv.org/abs/2411.07238
```
<i>Disclaimer: Provided responses are not guaranteed.</i> |
openthaigpt/openthaigpt1.5-14b-instruct | openthaigpt | 2024-11-15T04:55:37Z | 220 | 5 | transformers | [
"transformers",
"safetensors",
"gguf",
"qwen2",
"text-generation",
"openthaigpt",
"qwen",
"conversational",
"th",
"en",
"arxiv:2309.00071",
"arxiv:2411.07238",
"license:other",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-10-12T11:40:59Z | ---
license: other
license_name: qwen
language:
- th
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- openthaigpt
- qwen
model-index:
- name: OpenThaiGPT1.5-14b
results:
- task:
type: text-generation
dataset:
name: ThaiExam
type: multiple_choices
metrics:
- name: Thai Exam(Acc)
type: accuracy
value: 58.41
source:
name: 🇹🇭 Thai LLM Leaderboard
url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard
- task:
type: text-generation
dataset:
name: M3Exam
type: multiple_choices
metrics:
- name: M3Exam(Acc)
type: Accuracy
value: 62.41
source:
name: 🇹🇭 Thai LLM Leaderboard
url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard
---
# 🇹🇭 OpenThaiGPT 14b 1.5 Instruct
[More Info](https://openthaigpt.aieat.or.th/)
🇹🇭 **OpenThaiGPT 14b Version 1.5** is an advanced 14-billion-parameter Thai language chat model based on Qwen v2.5 released on October 13, 2024. It has been specifically fine-tuned on over 2,000,000 Thai instruction pairs and is capable of answering Thai-specific domain questions.
<a href="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/NoVK86trV6I8LSEduOQ_K.png" target="_blank"><img src="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/NoVK86trV6I8LSEduOQ_K.png" style="width:800px"></a>
## Online Demo:
https://demo72b.aieat.or.th/
## Example code for API Calling
https://github.com/OpenThaiGPT/openthaigpt1.5_api_examples
## Highlights
- **State-of-the-art Thai language LLM**, achieving the highest average scores across various Thai language exams compared to other open-source Thai LLMs.
- **Multi-turn conversation support** for extended dialogues.
- **Retrieval Augmented Generation (RAG) compatibility** for enhanced response generation.
- **Impressive context handling**: Processes up to 131,072 tokens of input and generates up to 8,192 tokens, enabling detailed and complex interactions.
- **Tool calling support**: Enables users to efficiently call various functions through intelligent responses.
## Benchmark on [OpenThaiGPT Eval](https://huggingface.co/datasets/openthaigpt/openthaigpt_eval)
** Please take a look at ``openthaigpt/openthaigpt1.5-14b-instruct`` for this model's evaluation result.
| **Exam names** | **scb10x/llama-3-typhoon-v1.5x-70b-instruct** | **Qwen/Qwen2.5-14B-Instruct** | **openthaigpt/openthaigpt1.5-14b** | **openthaigpt/openthaigpt1.5-72b** |
|--------------------------------|-----------------------------------------------|-------------------------------|------------------------------------|------------------------------------|
| **01_a_level** | 59.17% | 61.67% | 65.00% | 76.67% |
| **02_tgat** | 46.00% | 44.00% | 50.00% | 46.00% |
| **03_tpat1** | 52.50% | 60.00% | 52.50% | 55.00% |
| **04_investment_consult** | 60.00% | 76.00% | 72.00% | 72.00% |
| **05_facebook_beleble_th_200** | 87.50% | 84.50% | 87.00% | 90.00% |
| **06_xcopa_th_200** | 84.50% | 85.00% | 86.50% | 90.50% |
| **07_xnli2.0_th_200** | 62.50% | 69.50% | 64.50% | 70.50% |
| **08_onet_m3_thai** | 76.00% | 76.00% | 84.00% | 84.00% |
| **09_onet_m3_social** | 95.00% | 90.00% | 90.00% | 95.00% |
| **10_onet_m3_math** | 43.75% | 43.75% | 12.50% | 37.50% |
| **11_onet_m3_science** | 53.85% | 50.00% | 53.85% | 73.08% |
| **12_onet_m3_english** | 93.33% | 93.33% | 93.33% | 96.67% |
| **13_onet_m6_thai** | 55.38% | 52.31% | 56.92% | 56.92% |
| **14_onet_m6_math** | 41.18% | 23.53% | 41.18% | 41.18% |
| **15_onet_m6_social** | 67.27% | 60.00% | 61.82% | 65.45% |
| **16_onet_m6_science** | 50.00% | 50.00% | 57.14% | 67.86% |
| **17_onet_m6_english** | 73.08% | 82.69% | 78.85% | 90.38% |
| **Micro Average** | 69.97% | 71.00% | <b style="color:blue">71.51%</b> | 76.73% |
Thai language multiple choice exams, Test on unseen test set, Zero-shot learning. Benchmark source code and exams information: https://github.com/OpenThaiGPT/openthaigpt_eval
(Updated on: 13 October 2024)
## Benchmark on [scb10x/thai_exam](https://huggingface.co/datasets/scb10x/thai_exam)
| Models | **Thai Exam (Acc)** |
|:----------------------------------------------------------:|:-------------------:|
| **api/claude-3-5-sonnet-20240620** | 69.2 |
| <b style="color:blue">**openthaigpt/openthaigpt1.5-72b-instruct***</b> | <b style="color:blue">64.07</b> |
| **api/gpt-4o-2024-05-13** | 63.89 |
| **hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4** | 63.54 |
| <b style="color:blue">**openthaigpt/openthaigpt1.5-14b-instruct***</b> | <b style="color:blue">59.65</b> |
| **scb10x/llama-3-typhoon-v1.5x-70b-instruct** | 58.76 |
| **Qwen/Qwen2-72B-Instruct** | 58.23 |
| **meta-llama/Meta-Llama-3.1-70B-Instruct** | 58.23 |
| **Qwen/Qwen2.5-14B-Instruct** | 57.35 |
| **api/gpt-4o-mini-2024-07-18** | 54.51 |
| <b style="color:blue">**openthaigpt/openthaigpt1.5-7b-instruct***</b> | <b style="color:blue">52.04</b> |
| **SeaLLMs/SeaLLMs-v3-7B-Chat** | 51.33 |
| **openthaigpt/openthaigpt-1.0.0-70b-chat** | 50.09 |
<b style="color:blue">*</b> Evaluated by OpenThaiGPT team using [scb10x/thai_exam](https://huggingface.co/datasets/scb10x/thai_exam).
(Updated on: 13 October 2024)
## Licenses
* Built with Qwen
* Qwen License: Allow **Research** and
**Commercial uses** but if your user base exceeds 100 million monthly active users, you need to negotiate a separate commercial license. Please see LICENSE file for more information.<br>
## Sponsors
<img src="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/3kjN6kuTzXDXQ6o1RFvHX.png" width="600px">
## Supports
- Official website: https://openthaigpt.aieat.or.th
- Facebook page: https://web.facebook.com/groups/openthaigpt
- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
- E-mail: [email protected]
## Prompt Format
Prompt format is based on ChatML.
```
<|im_start|>system\n{sytem_prompt}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n
```
### System prompt:
```
คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์
```
### Examples
#### Single Turn Conversation Example
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\n
```
#### Single Turn Conversation with Context (RAG) Example
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nกรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน\nกรุงเทพมหานครมีพื้นที่เท่าไร่<|im_end|>\n<|im_start|>assistant\n
```
#### Multi Turn Conversation Example
##### First turn
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\n
```
##### Second turn
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\nสวัสดีครับ ยินดีต้อนรับครับ คุณต้องการให้ฉันช่วยอะไรครับ?<|im_end|>\n<|im_start|>user\nกรุงเทพมหานคร ชื่อเต็มยาวๆคืออะไร<|im_end|>\n<|im_start|>assistant\n
```
##### Result
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\nสวัสดีครับ ยินดีต้อนรับครับ คุณต้องการให้ฉันช่วยอะไรครับ?<|im_end|>\n<|im_start|>user\nกรุงเทพมหานคร ชื่อเต็มยาวๆคืออะไร<|im_end|>\n<|im_start|>assistant\nชื่อเต็มของกรุงเทพมหานครคือ \"กรุงเทพมหานคร อมรรัตนโกสินทร์ มหินทรายุธยา มหาดิลกภพ นพรัตนราชธานีบูรีรมย์ อุดมราชนิเวศน์มหาสถาน อมรพิมานอวตารสถิต สักกะทัตติยวิษณุกรรมประสิทธิ์\"
```
## How to use
### Free API Service (hosted by Siam.Ai and Float16.cloud)
#### Siam.AI
```bash
curl https://api.aieat.or.th/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer dummy" \
-d '{
"model": ".",
"prompt": "<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nกรุงเทพมหานครคืออะไร<|im_end|>\n<|im_start|>assistant\n",
"max_tokens": 512,
"temperature": 0.7,
"top_p": 0.8,
"top_k": 40,
"stop": ["<|im_end|>"]
}'
```
#### Float16
```bash
curl -X POST https://api.float16.cloud/dedicate/78y8fJLuzE/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer float16-AG0F8yNce5s1DiXm1ujcNrTaZquEdaikLwhZBRhyZQNeS7Dv0X" \
-d '{
"model": "openthaigpt/openthaigpt1.5-7b-instruct",
"messages": [
{
"role": "system",
"content": "คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์"
},
{
"role": "user",
"content": "สวัสดี"
}
]
}'
```
### OpenAI Client Library (Hosted by VLLM, please see below.)
```python
import openai
# Configure OpenAI client to use vLLM server
openai.api_base = "http://127.0.0.1:8000/v1"
openai.api_key = "dummy" # vLLM doesn't require a real API key
prompt = "<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nกรุงเทพมหานครคืออะไร<|im_end|>\n<|im_start|>assistant\n"
try:
response = openai.Completion.create(
model=".", # Specify the model you're using with vLLM
prompt=prompt,
max_tokens=512,
temperature=0.7,
top_p=0.8,
top_k=40,
stop=["<|im_end|>"]
)
print("Generated Text:", response.choices[0].text)
except Exception as e:
print("Error:", str(e))
```
### Huggingface
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "openthaigpt/openthaigpt1.5-14b-instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "ประเทศไทยคืออะไร"
messages = [
{"role": "system", "content": "คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์"},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
### vLLM
1. Install VLLM (https://github.com/vllm-project/vllm)
2. Run server
```bash
vllm serve openthaigpt/openthaigpt1.5-14b-instruct --tensor-parallel-size 4
```
* Note, change ``--tensor-parallel-size 4`` to the amount of available GPU cards.
If you wish to enable tool calling feature, add ``--enable-auto-tool-choice --tool-call-parser hermes`` into command. e.g.,
```bash
vllm serve openthaigpt/openthaigpt1.5-14b-instruct --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser hermes
```
3. Run inference (CURL example)
```bash
curl -X POST 'http://127.0.0.1:8000/v1/completions' \
-H 'Content-Type: application/json' \
-d '{
"model": ".",
"prompt": "<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\n",
"max_tokens": 512,
"temperature": 0.7,
"top_p": 0.8,
"top_k": 40,
"stop": ["<|im_end|>"]
}'
```
### Processing Long Texts
The current `config.json` is set for context length up to 32,768 tokens.
To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
For supported frameworks, you could add the following to `config.json` to enable YaRN:
```json
{
...
"rope_scaling": {
"factor": 4.0,
"original_max_position_embeddings": 32768,
"type": "yarn"
}
}
```
### Tool Calling
The Tool Calling feature in OpenThaiGPT 1.5 enables users to efficiently call various functions through intelligent responses. This includes making external API calls to retrieve real-time data, such as current temperature information, or predicting future data simply by submitting a query.
For example, a user can ask OpenThaiGPT, “What is the current temperature in San Francisco?” and the AI will execute a pre-defined function to provide an immediate response without the need for additional coding.
This feature also allows for broader applications with external data sources, including the ability to call APIs for services such as weather updates, stock market information, or data from within the user’s own system.
#### Example:
```python
import openai
def get_temperature(location, date=None, unit="celsius"):
"""Get temperature for a location (current or specific date)."""
if date:
return {"temperature": 25.9, "location": location, "date": date, "unit": unit}
return {"temperature": 26.1, "location": location, "unit": unit}
tools = [
{
"name": "get_temperature",
"description": "Get temperature for a location (current or by date).",
"parameters": {
"location": "string", "date": "string (optional)", "unit": "enum [celsius, fahrenheit]"
},
}
]
messages = [{"role": "user", "content": "อุณหภูมิที่ San Francisco วันนี้ีและพรุ้่งนี้คือเท่าไร่?"}]
# Simulated response flow using OpenThaiGPT Tool Calling
response = openai.ChatCompletion.create(
model=".", messages=messages, tools=tools, temperature=0.7, max_tokens=512
)
print(response)
```
**Full example**: https://github.com/OpenThaiGPT/openthaigpt1.5_api_examples/blob/main/api_tool_calling_powered_by_siamai.py
### GPU Memory Requirements
| **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
|------------------|----------------|------------------------|------------------------|---------------------------------------------|
| **7b** | 24 GB | 12 GB | 6 GB | Nvidia RTX 4060 8GB |
| **14b** | 48 GB | 24 GB | 12 GB | Nvidia RTX 4070 16GB |
| **72b** | 192 GB | 96 GB | 48 GB | Nvidia RTX 4090 24GB x 2 cards |
### OpenThaiGPT Team
* Sumeth Yuenyong ([email protected])
* Kobkrit Viriyayudhakorn ([email protected])
* Apivadee Piyatumrong ([email protected])
* Jillaphat Jaroenkantasima ([email protected])
* Thaweewat Rugsujarit ([email protected])
* Norapat Buppodom ([email protected])
* Koravich Sangkaew ([email protected])
* Peerawat Rojratchadakorn ([email protected])
* Surapon Nonesung ([email protected])
* Chanon Utupon ([email protected])
* Sadhis Wongprayoon ([email protected])
* Nucharee Thongthungwong ([email protected])
* Chawakorn Phiantham ([email protected])
* Patteera Triamamornwooth ([email protected])
* Nattarika Juntarapaoraya ([email protected])
* Kriangkrai Saetan ([email protected])
* Pitikorn Khlaisamniang ([email protected])
### Citation
If OpenThaiGPT has been beneficial for your work, kindly consider citing it as follows:
#### Bibtex
```bibtex
@misc{yuenyong2024openthaigpt15thaicentricopen,
title={OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model},
author={Sumeth Yuenyong and Kobkrit Viriyayudhakorn and Apivadee Piyatumrong and Jillaphat Jaroenkantasima},
year={2024},
eprint={2411.07238},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2411.07238},
}
```
#### APA Style (for TXT, MS Word)
```
Yuenyong, S., Viriyayudhakorn, K., Piyatumrong, A., & Jaroenkantasima, J. (2024). OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model. arXiv [Cs.CL]. Retrieved from http://arxiv.org/abs/2411.07238
```
<i>Disclaimer: Provided responses are not guaranteed.</i> |
openthaigpt/openthaigpt1.5-7b-instruct | openthaigpt | 2024-11-15T04:55:13Z | 1,343 | 13 | transformers | [
"transformers",
"safetensors",
"gguf",
"qwen2",
"text-generation",
"openthaigpt",
"qwen",
"conversational",
"th",
"en",
"arxiv:2309.00071",
"arxiv:2411.07238",
"doi:10.57967/hf/3168",
"license:other",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-09-30T13:32:13Z | ---
license: other
license_name: qwen
language:
- th
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- openthaigpt
- qwen
model-index:
- name: OpenThaiGPT1.5-7b
results:
- task:
type: text-generation
dataset:
name: ThaiExam
type: multiple_choices
metrics:
- name: Thai Exam(Acc)
type: accuracy
value: 52.04
source:
name: 🇹🇭 Thai LLM Leaderboard
url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard
- task:
type: text-generation
dataset:
name: M3Exam
type: multiple_choices
metrics:
- name: M3Exam(Acc)
type: Accuracy
value: 54.01
source:
name: 🇹🇭 Thai LLM Leaderboard
url: https://huggingface.co/spaces/ThaiLLM-Leaderboard/leaderboard
---
# 🇹🇭 OpenThaiGPT 7b 1.5 Instruct
[More Info](https://openthaigpt.aieat.or.th/)
🇹🇭 **OpenThaiGPT 7b Version 1.5** is an advanced 7-billion-parameter Thai language chat model based on Qwen v2.5 released on September 30, 2024. It has been specifically fine-tuned on over 2,000,000 Thai instruction pairs and is capable of answering Thai-specific domain questions.
<a href="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/NoVK86trV6I8LSEduOQ_K.png" target="_blank"><img src="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/NoVK86trV6I8LSEduOQ_K.png" style="width:800px"></a>
## Online Demo:
https://demo72b.aieat.or.th/
## Example code for API Calling
https://github.com/OpenThaiGPT/openthaigpt1.5_api_examples
## Highlights
- **State-of-the-art Thai language LLM**, achieving the highest average scores across various Thai language exams compared to other open-source Thai LLMs.
- **Multi-turn conversation support** for extended dialogues.
- **Retrieval Augmented Generation (RAG) compatibility** for enhanced response generation.
- **Impressive context handling**: Processes up to 131,072 tokens of input and generates up to 8,192 tokens, enabling detailed and complex interactions.
- **Tool calling support**: Enables users to efficiently call various functions through intelligent responses.
## Benchmark on [OpenThaiGPT Eval](https://huggingface.co/datasets/openthaigpt/openthaigpt_eval)
** Please take a look at ``openthaigpt/openthaigpt1.5-7b-instruct`` for this model's evaluation result.
| **Exam names** | **scb10x/llama-3-typhoon-v1.5x-8b-instruct** | **meta-llama/Llama-3.1-7B-Instruct** | **Qwen/Qwen2.5-7B-Instruct_stat** | **openthaigpt/openthaigpt1.5-7b** |
|:------------------------------:|:--------------------------------------------:|:------------------------------------:|:---------------------------------:|:---------------------------------:|
| **01_a_level** | 46.67% | 47.50% | 58.33% | 60.00% |
| **02_tgat** | 32.00% | 36.00% | 32.00% | 36.00% |
| **03_tpat1** | 52.50% | 55.00% | 57.50% | 57.50% |
| **04_investment_consult** | 56.00% | 48.00% | 68.00% | 76.00% |
| **05_facebook_beleble_th_200** | 78.00% | 73.00% | 79.00% | 81.00% |
| **06_xcopa_th_200** | 79.50% | 69.00% | 80.50% | 81.00% |
| **07_xnli2.0_th_200** | 56.50% | 55.00% | 53.00% | 54.50% |
| **08_onet_m3_thai** | 48.00% | 32.00% | 72.00% | 64.00% |
| **09_onet_m3_social** | 75.00% | 50.00% | 90.00% | 80.00% |
| **10_onet_m3_math** | 25.00% | 18.75% | 31.25% | 31.25% |
| **11_onet_m3_science** | 46.15% | 42.31% | 46.15% | 46.15% |
| **12_onet_m3_english** | 70.00% | 76.67% | 86.67% | 83.33% |
| **13_onet_m6_thai** | 47.69% | 29.23% | 46.15% | 53.85% |
| **14_onet_m6_math** | 29.41% | 17.65% | 29.41% | 29.41% |
| **15_onet_m6_social** | 50.91% | 43.64% | 56.36% | 58.18% |
| **16_onet_m6_science** | 42.86% | 32.14% | 57.14% | 57.14% |
| **17_onet_m6_english** | 65.38% | 71.15% | 78.85% | 80.77% |
| **Micro Average** | 60.65% | 55.60% | 64.41% | <b style="color:blue">65.78%</b> |
Thai language multiple choice exams, Test on unseen test set, Zero-shot learning. Benchmark source code and exams information: https://github.com/OpenThaiGPT/openthaigpt_eval
(Updated on: 30 September 2024)
## Benchmark on [scb10x/thai_exam](https://huggingface.co/datasets/scb10x/thai_exam)
| Models | **Thai Exam (Acc)** |
|:----------------------------------------------------------:|:-------------------:|
| **api/claude-3-5-sonnet-20240620** | 69.2 |
| <b style="color:blue">**openthaigpt/openthaigpt1.5-72b-instruct***</b> | <b style="color:blue">64.07</b> |
| **api/gpt-4o-2024-05-13** | 63.89 |
| **hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4** | 63.54 |
| <b style="color:blue">**openthaigpt/openthaigpt1.5-14b-instruct***</b> | <b style="color:blue">59.65</b> |
| **scb10x/llama-3-typhoon-v1.5x-70b-instruct** | 58.76 |
| **Qwen/Qwen2-72B-Instruct** | 58.23 |
| **meta-llama/Meta-Llama-3.1-70B-Instruct** | 58.23 |
| **Qwen/Qwen2.5-14B-Instruct** | 57.35 |
| **api/gpt-4o-mini-2024-07-18** | 54.51 |
| <b style="color:blue">**openthaigpt/openthaigpt1.5-7b-instruct***</b> | <b style="color:blue">52.04</b> |
| **SeaLLMs/SeaLLMs-v3-7B-Chat** | 51.33 |
| **openthaigpt/openthaigpt-1.0.0-70b-chat** | 50.09 |
<b style="color:blue">*</b> Evaluated by OpenThaiGPT team using [scb10x/thai_exam](https://huggingface.co/datasets/scb10x/thai_exam).
(Updated on: 13 October 2024)
## Licenses
* Built with Qwen
* Qwen License: Allow **Research** and
**Commercial uses** but if your user base exceeds 100 million monthly active users, you need to negotiate a separate commercial license. Please see LICENSE file for more information.<br>
## Sponsors
<img src="https://cdn-uploads.huggingface.co/production/uploads/5fcd9c426d942eaf4d1ebd30/3kjN6kuTzXDXQ6o1RFvHX.png" width="600px">
## Supports
- Official website: https://openthaigpt.aieat.or.th
- Facebook page: https://web.facebook.com/groups/openthaigpt
- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
- E-mail: [email protected]
## Prompt Format
Prompt format is based on ChatML.
```
<|im_start|>system\n{sytem_prompt}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n
```
### System prompt:
```
คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์
```
### Examples
#### Single Turn Conversation Example
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\n
```
#### Single Turn Conversation with Context (RAG) Example
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nกรุงเทพมหานคร เป็นเมืองหลวง นครและมหานครที่มีประชากรมากที่สุดของประเทศไทย กรุงเทพมหานครมีพื้นที่ทั้งหมด 1,568.737 ตร.กม. มีประชากรตามทะเบียนราษฎรกว่า 8 ล้านคน\nกรุงเทพมหานครมีพื้นที่เท่าไร่<|im_end|>\n<|im_start|>assistant\n
```
#### Multi Turn Conversation Example
##### First turn
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\n
```
##### Second turn
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\nสวัสดีครับ ยินดีต้อนรับครับ คุณต้องการให้ฉันช่วยอะไรครับ?<|im_end|>\n<|im_start|>user\nกรุงเทพมหานคร ชื่อเต็มยาวๆคืออะไร<|im_end|>\n<|im_start|>assistant\n
```
##### Result
```
<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\nสวัสดีครับ ยินดีต้อนรับครับ คุณต้องการให้ฉันช่วยอะไรครับ?<|im_end|>\n<|im_start|>user\nกรุงเทพมหานคร ชื่อเต็มยาวๆคืออะไร<|im_end|>\n<|im_start|>assistant\nชื่อเต็มของกรุงเทพมหานครคือ \"กรุงเทพมหานคร อมรรัตนโกสินทร์ มหินทรายุธยา มหาดิลกภพ นพรัตนราชธานีบูรีรมย์ อุดมราชนิเวศน์มหาสถาน อมรพิมานอวตารสถิต สักกะทัตติยวิษณุกรรมประสิทธิ์\"
```
## How to use
### Free API Service (hosted by Siam.Ai and Float16.cloud)
#### Siam.AI
```bash
curl https://api.aieat.or.th/v1/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer dummy" \
-d '{
"model": ".",
"prompt": "<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nกรุงเทพมหานครคืออะไร<|im_end|>\n<|im_start|>assistant\n",
"max_tokens": 512,
"temperature": 0.7,
"top_p": 0.8,
"top_k": 40,
"stop": ["<|im_end|>"]
}'
```
#### Float16
```bash
curl -X POST https://api.float16.cloud/dedicate/78y8fJLuzE/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer float16-AG0F8yNce5s1DiXm1ujcNrTaZquEdaikLwhZBRhyZQNeS7Dv0X" \
-d '{
"model": "openthaigpt/openthaigpt1.5-7b-instruct",
"messages": [
{
"role": "system",
"content": "คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์"
},
{
"role": "user",
"content": "สวัสดี"
}
]
}'
```
### OpenAI Client Library (Hosted by VLLM, please see below.)
```python
import openai
# Configure OpenAI client to use vLLM server
openai.api_base = "http://127.0.0.1:8000/v1"
openai.api_key = "dummy" # vLLM doesn't require a real API key
prompt = "<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nกรุงเทพมหานครคืออะไร<|im_end|>\n<|im_start|>assistant\n"
try:
response = openai.Completion.create(
model=".", # Specify the model you're using with vLLM
prompt=prompt,
max_tokens=512,
temperature=0.7,
top_p=0.8,
top_k=40,
stop=["<|im_end|>"]
)
print("Generated Text:", response.choices[0].text)
except Exception as e:
print("Error:", str(e))
```
### Huggingface
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "openthaigpt/openthaigpt1.5-7b-instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "ประเทศไทยคืออะไร"
messages = [
{"role": "system", "content": "คุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์"},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
### vLLM
1. Install VLLM (https://github.com/vllm-project/vllm)
2. Run server
```bash
vllm serve openthaigpt/openthaigpt1.5-7b-instruct --tensor-parallel-size 4
```
* Note, change ``--tensor-parallel-size 4`` to the amount of available GPU cards.
If you wish to enable tool calling feature, add ``--enable-auto-tool-choice --tool-call-parser hermes`` into command. e.g.,
```bash
vllm serve openthaigpt/openthaigpt1.5-7b-instruct --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser hermes
```
3. Run inference (CURL example)
```bash
curl -X POST 'http://127.0.0.1:8000/v1/completions' \
-H 'Content-Type: application/json' \
-d '{
"model": ".",
"prompt": "<|im_start|>system\nคุณคือผู้ช่วยตอบคำถามที่ฉลาดและซื่อสัตย์<|im_end|>\n<|im_start|>user\nสวัสดีครับ<|im_end|>\n<|im_start|>assistant\n",
"max_tokens": 512,
"temperature": 0.7,
"top_p": 0.8,
"top_k": 40,
"stop": ["<|im_end|>"]
}'
```
### Processing Long Texts
The current `config.json` is set for context length up to 32,768 tokens.
To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
For supported frameworks, you could add the following to `config.json` to enable YaRN:
```json
{
...
"rope_scaling": {
"factor": 4.0,
"original_max_position_embeddings": 32768,
"type": "yarn"
}
}
```
### Tool Calling
The Tool Calling feature in OpenThaiGPT 1.5 enables users to efficiently call various functions through intelligent responses. This includes making external API calls to retrieve real-time data, such as current temperature information, or predicting future data simply by submitting a query.
For example, a user can ask OpenThaiGPT, “What is the current temperature in San Francisco?” and the AI will execute a pre-defined function to provide an immediate response without the need for additional coding.
This feature also allows for broader applications with external data sources, including the ability to call APIs for services such as weather updates, stock market information, or data from within the user’s own system.
#### Example:
```python
import openai
def get_temperature(location, date=None, unit="celsius"):
"""Get temperature for a location (current or specific date)."""
if date:
return {"temperature": 25.9, "location": location, "date": date, "unit": unit}
return {"temperature": 26.1, "location": location, "unit": unit}
tools = [
{
"name": "get_temperature",
"description": "Get temperature for a location (current or by date).",
"parameters": {
"location": "string", "date": "string (optional)", "unit": "enum [celsius, fahrenheit]"
},
}
]
messages = [{"role": "user", "content": "อุณหภูมิที่ San Francisco วันนี้ีและพรุ้่งนี้คือเท่าไร่?"}]
# Simulated response flow using OpenThaiGPT Tool Calling
response = openai.ChatCompletion.create(
model=".", messages=messages, tools=tools, temperature=0.7, max_tokens=512
)
print(response)
```
**Full example**: https://github.com/OpenThaiGPT/openthaigpt1.5_api_examples/blob/main/api_tool_calling_powered_by_siamai.py
### GPU Memory Requirements
| **Number of Parameters** | **FP 16 bits** | **8 bits (Quantized)** | **4 bits (Quantized)** | **Example Graphic Card for 4 bits** |
|------------------|----------------|------------------------|------------------------|---------------------------------------------|
| **7b** | 24 GB | 12 GB | 6 GB | Nvidia RTX 4060 8GB |
| **13b** | 48 GB | 24 GB | 12 GB | Nvidia RTX 4070 16GB |
| **72b** | 192 GB | 96 GB | 48 GB | Nvidia RTX 4090 24GB x 2 cards |
### OpenThaiGPT Team
* Sumeth Yuenyong ([email protected])
* Kobkrit Viriyayudhakorn ([email protected])
* Apivadee Piyatumrong ([email protected])
* Jillaphat Jaroenkantasima ([email protected])
* Thaweewat Rugsujarit ([email protected])
* Norapat Buppodom ([email protected])
* Koravich Sangkaew ([email protected])
* Peerawat Rojratchadakorn ([email protected])
* Surapon Nonesung ([email protected])
* Chanon Utupon ([email protected])
* Sadhis Wongprayoon ([email protected])
* Nucharee Thongthungwong ([email protected])
* Chawakorn Phiantham ([email protected])
* Patteera Triamamornwooth ([email protected])
* Nattarika Juntarapaoraya ([email protected])
* Kriangkrai Saetan ([email protected])
* Pitikorn Khlaisamniang ([email protected])
### Citation
If OpenThaiGPT has been beneficial for your work, kindly consider citing it as follows:
#### Bibtex
```bibtex
@misc{yuenyong2024openthaigpt15thaicentricopen,
title={OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model},
author={Sumeth Yuenyong and Kobkrit Viriyayudhakorn and Apivadee Piyatumrong and Jillaphat Jaroenkantasima},
year={2024},
eprint={2411.07238},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2411.07238},
}
```
#### APA Style (for TXT, MS Word)
```
Yuenyong, S., Viriyayudhakorn, K., Piyatumrong, A., & Jaroenkantasima, J. (2024). OpenThaiGPT 1.5: A Thai-Centric Open Source Large Language Model. arXiv [Cs.CL]. Retrieved from http://arxiv.org/abs/2411.07238
```
<i>Disclaimer: Provided responses are not guaranteed.</i> |
mradermacher/hyperion-medium-preview-i1-GGUF | mradermacher | 2024-11-15T04:55:10Z | 52 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Locutusque/hyperion-medium-preview",
"base_model:quantized:Locutusque/hyperion-medium-preview",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix"
] | null | 2024-11-14T23:54:24Z | ---
base_model: Locutusque/hyperion-medium-preview
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Locutusque/hyperion-medium-preview
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/hyperion-medium-preview-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/hyperion-medium-preview-i1-GGUF/resolve/main/hyperion-medium-preview.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
unsloth/Qwen2.5-Coder-3B-Instruct-128K-GGUF | unsloth | 2024-11-15T04:51:35Z | 828 | 6 | transformers | [
"transformers",
"gguf",
"qwen2",
"unsloth",
"code",
"qwen",
"qwen-coder",
"codeqwen",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-3B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-3B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-12T19:00:38Z | ---
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
language:
- en
library_name: transformers
license: apache-2.0
tags:
- unsloth
- transformers
- code
- qwen
- qwen-coder
- codeqwen
---
> [!NOTE]
> Use 4bit quants (Q4_K_M) and above for 3B - lower quants will degrade accuracy
# YaRN 128K. 32K non extended GGUF here: [link](https://huggingface.co/unsloth/Qwen2.5-Coder-3B-Instruct-GGUF)
# Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing).
Also a [Qwen 2.5 conversational style notebook](https://colab.research.google.com/drive/1qN1CEalC70EO1wGKhNxs1go1W9So61R5?usp=sharing).
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.1 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma-2 9b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
# unsloth/Qwen2.5-Coder-3B-Instruct-128K-GGUF
## Introduction
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:
- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.
**This repo contains the 0.5B Qwen2.5-Coder model**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
- Number of Parameters: 0.49B
- Number of Paramaters (Non-Embedding): 0.36B
- Number of Layers: 24
- Number of Attention Heads (GQA): 14 for Q and 2 for KV
- Context Length: Full 32,768 tokens
**We do not recommend using base language models for conversations.** Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., or fill in the middle tasks on this model.
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186).
## Requirements
The code of Qwen2.5-Coder has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.37.0`, you will encounter the following error:
```
KeyError: 'qwen2'
```
## Evaluation & Performance
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{hui2024qwen2,
title={Qwen2. 5-Coder Technical Report},
author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
journal={arXiv preprint arXiv:2409.12186},
year={2024}
}
@article{qwen2,
title={Qwen2 Technical Report},
author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
journal={arXiv preprint arXiv:2407.10671},
year={2024}
}
``` |
unsloth/Qwen2.5-Coder-1.5B-Instruct-128K-GGUF | unsloth | 2024-11-15T04:51:20Z | 636 | 4 | transformers | [
"transformers",
"gguf",
"qwen2",
"unsloth",
"code",
"qwen",
"qwen-coder",
"codeqwen",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-1.5B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-12T19:22:33Z | ---
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
language:
- en
library_name: transformers
license: apache-2.0
tags:
- unsloth
- transformers
- code
- qwen
- qwen-coder
- codeqwen
---
> [!NOTE]
> Use 4bit quants (Q4_K_M) and above for 1.5B - lower quants will degrade accuracy
# YaRN 128K. 32K non extended GGUF here: [link](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct-GGUF)
# Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing).
Also a [Qwen 2.5 conversational style notebook](https://colab.research.google.com/drive/1qN1CEalC70EO1wGKhNxs1go1W9So61R5?usp=sharing).
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.1 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma-2 9b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
# unsloth/Qwen2.5-Coder-1.5B-Instruct-128K-GGUF
## Introduction
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:
- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.
**This repo contains the 0.5B Qwen2.5-Coder model**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
- Number of Parameters: 0.49B
- Number of Paramaters (Non-Embedding): 0.36B
- Number of Layers: 24
- Number of Attention Heads (GQA): 14 for Q and 2 for KV
- Context Length: Full 32,768 tokens
**We do not recommend using base language models for conversations.** Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., or fill in the middle tasks on this model.
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186).
## Requirements
The code of Qwen2.5-Coder has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.37.0`, you will encounter the following error:
```
KeyError: 'qwen2'
```
## Evaluation & Performance
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{hui2024qwen2,
title={Qwen2. 5-Coder Technical Report},
author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
journal={arXiv preprint arXiv:2409.12186},
year={2024}
}
@article{qwen2,
title={Qwen2 Technical Report},
author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
journal={arXiv preprint arXiv:2407.10671},
year={2024}
}
``` |
unsloth/Qwen2.5-Coder-1.5B-Instruct-GGUF | unsloth | 2024-11-15T04:50:33Z | 273 | 1 | transformers | [
"transformers",
"gguf",
"unsloth",
"code",
"qwen",
"qwen-coder",
"codeqwen",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-1.5B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-12T08:50:15Z | ---
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
language:
- en
library_name: transformers
license: apache-2.0
tags:
- unsloth
- transformers
- code
- qwen
- qwen-coder
- codeqwen
---
> [!NOTE]
> Use 4bit quants (Q4_K_M) and above for 1.5B - lower quants will degrade accuracy
>
# Finetune Llama 3.2, Qwen2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing).
Also a [Qwen 2.5 conversational style notebook](https://colab.research.google.com/drive/1qN1CEalC70EO1wGKhNxs1go1W9So61R5?usp=sharing).
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.1 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma-2 9b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
# unsloth/Qwen2.5-Coder-1.5B-Instruct-GGUF
## Introduction
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:
- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.
**This repo contains the 0.5B Qwen2.5-Coder model**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
- Number of Parameters: 0.49B
- Number of Paramaters (Non-Embedding): 0.36B
- Number of Layers: 24
- Number of Attention Heads (GQA): 14 for Q and 2 for KV
- Context Length: Full 32,768 tokens
**We do not recommend using base language models for conversations.** Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., or fill in the middle tasks on this model.
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186).
## Requirements
The code of Qwen2.5-Coder has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.37.0`, you will encounter the following error:
```
KeyError: 'qwen2'
```
## Evaluation & Performance
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{hui2024qwen2,
title={Qwen2. 5-Coder Technical Report},
author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
journal={arXiv preprint arXiv:2409.12186},
year={2024}
}
@article{qwen2,
title={Qwen2 Technical Report},
author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
journal={arXiv preprint arXiv:2407.10671},
year={2024}
}
``` |
unsloth/Qwen2.5-Coder-3B-Instruct-GGUF | unsloth | 2024-11-15T04:50:18Z | 230 | 2 | transformers | [
"transformers",
"gguf",
"unsloth",
"code",
"qwen",
"qwen-coder",
"codeqwen",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-3B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-3B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-12T08:16:26Z | ---
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
language:
- en
library_name: transformers
license: apache-2.0
tags:
- unsloth
- transformers
- code
- qwen
- qwen-coder
- codeqwen
---
> [!NOTE]
> Use 4bit quants (Q4_K_M) and above for 3B - lower quants will degrade accuracy
# Finetune Llama 3.2, Qwen2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
We have a Qwen 2.5 (all model sizes) [free Google Colab Tesla T4 notebook](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing).
Also a [Qwen 2.5 conversational style notebook](https://colab.research.google.com/drive/1qN1CEalC70EO1wGKhNxs1go1W9So61R5?usp=sharing).
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
## ✨ Finetune for Free
All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
| **Llama-3.1 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
| **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
| **Gemma-2 9b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
| **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
| **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
| **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
# unsloth/Qwen2.5-Coder-3B-Instruct-GGUF
## Introduction
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:
- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. Qwen2.5-Coder-32B has become the current state-of-the-art open-source codeLLM, with its coding abilities matching those of GPT-4o.
- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies.
**This repo contains the 0.5B Qwen2.5-Coder model**, which has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
- Number of Parameters: 0.49B
- Number of Paramaters (Non-Embedding): 0.36B
- Number of Layers: 24
- Number of Attention Heads (GQA): 14 for Q and 2 for KV
- Context Length: Full 32,768 tokens
**We do not recommend using base language models for conversations.** Instead, you can apply post-training, e.g., SFT, RLHF, continued pretraining, etc., or fill in the middle tasks on this model.
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186).
## Requirements
The code of Qwen2.5-Coder has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.37.0`, you will encounter the following error:
```
KeyError: 'qwen2'
```
## Evaluation & Performance
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
## Citation
If you find our work helpful, feel free to give us a cite.
```
@article{hui2024qwen2,
title={Qwen2. 5-Coder Technical Report},
author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
journal={arXiv preprint arXiv:2409.12186},
year={2024}
}
@article{qwen2,
title={Qwen2 Technical Report},
author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
journal={arXiv preprint arXiv:2407.10671},
year={2024}
}
``` |
mav23/Qwen2.5-Coder-1.5B-Instruct-abliterated-GGUF | mav23 | 2024-11-15T04:35:38Z | 39 | 0 | transformers | [
"transformers",
"gguf",
"chat",
"abliterated",
"uncensored",
"text-generation",
"en",
"base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-1.5B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-11-15T04:15:37Z | ---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
tags:
- chat
- abliterated
- uncensored
---
# huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated
This is an uncensored version of [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
Qwen2.5-Coder uncensored version has covered six mainstream model sizes,
[0.5](https://huggingface.co/huihui-ai/Qwen2.5-Coder-0.5B-Instruct-abliterated),
[1.5](https://huggingface.co/huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated),
[3](https://huggingface.co/huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated),
[7](https://huggingface.co/huihui-ai/Qwen2.5-Coder-7B-Instruct-abliterated),
[14](https://huggingface.co/huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated),
[32](https://huggingface.co/huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated) billion parameters.
## Usage
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
# Load the model and tokenizer
model_name = "huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Initialize conversation context
initial_messages = [
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}
]
messages = initial_messages.copy() # Copy the initial conversation context
# Enter conversation loop
while True:
# Get user input
user_input = input("User: ").strip() # Strip leading and trailing spaces
# If the user types '/exit', end the conversation
if user_input.lower() == "/exit":
print("Exiting chat.")
break
# If the user types '/clean', reset the conversation context
if user_input.lower() == "/clean":
messages = initial_messages.copy() # Reset conversation context
print("Chat history cleared. Starting a new conversation.")
continue
# If input is empty, prompt the user and continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
# Add user input to the conversation
messages.append({"role": "user", "content": user_input})
# Build the chat template
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
# Tokenize input and prepare it for the model
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# Generate a response from the model
generated_ids = model.generate(
**model_inputs,
max_new_tokens=8192
)
# Extract model output, removing special tokens
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
# Add the model's response to the conversation
messages.append({"role": "assistant", "content": response})
# Print the model's response
print(f"Qwen: {response}")
```
## Evaluations
The following data has been re-evaluated and calculated as the average for each test.
| Benchmark | Qwen2.5-Coder-1.5B-Instruct | Qwen2.5-Coder-1.5B-Instruct-abliterated |
|-------------|-----------------------------|-----------------------------------------|
| IF_Eval | 43.43 | **45.41** |
| MMLU Pro | 21.5 | 20.57 |
| TruthfulQA | 46.07 | 41.9 |
| BBH | 36.67 | 36.09 |
| GPQA | 28.00 | 26.13 |
The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Qwen2.5-Coder-1.5B-Instruct-abliterated/blob/main/eval.sh)
|
AlaaHussien/dinov2-base-finetuned-eye | AlaaHussien | 2024-11-15T04:31:31Z | 170 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"dinov2",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/dinov2-base",
"base_model:finetune:facebook/dinov2-base",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-10-29T20:36:27Z | ---
library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-base
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
model-index:
- name: dinov2-base-finetuned-eye
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.968
- name: F1
type: f1
value: 0.9678344915175675
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# dinov2-base-finetuned-eye
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2262
- Accuracy: 0.968
- F1: 0.9678
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.3853 | 1.0 | 250 | 0.4918 | 0.874 | 0.8729 |
| 0.5345 | 2.0 | 500 | 0.4390 | 0.878 | 0.8771 |
| 0.4693 | 3.0 | 750 | 0.3857 | 0.88 | 0.8796 |
| 0.1933 | 4.0 | 1000 | 0.3444 | 0.894 | 0.8948 |
| 0.3146 | 5.0 | 1250 | 0.2456 | 0.936 | 0.9362 |
| 0.1832 | 6.0 | 1500 | 0.3369 | 0.924 | 0.9229 |
| 0.1407 | 7.0 | 1750 | 0.3425 | 0.946 | 0.9454 |
| 0.1462 | 8.0 | 2000 | 0.2864 | 0.948 | 0.9476 |
| 0.0905 | 9.0 | 2250 | 0.2177 | 0.956 | 0.9560 |
| 0.0859 | 10.0 | 2500 | 0.2262 | 0.968 | 0.9678 |
### Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
|
AlekseyCalvin/Artsy_Lite_Flux_v1_by_jurdn_Diffusers | AlekseyCalvin | 2024-11-15T04:29:13Z | 65 | 0 | diffusers | [
"diffusers",
"safetensors",
"FluxPipeline",
"FLUXv1-schnell",
"image-generation",
"flux-diffusers",
"art",
"realism",
"photography",
"illustration",
"anime",
"full finetune",
"trained",
"finetune",
"trainable",
"full-finetune",
"checkpoint",
"text2image",
"Schnell",
"Flux",
"Artsy",
"ArtsyLite",
"text-to-image",
"base_model:black-forest-labs/FLUX.1-schnell",
"base_model:finetune:black-forest-labs/FLUX.1-schnell",
"license:apache-2.0",
"endpoints_compatible",
"diffusers:FluxPipeline",
"region:us"
] | text-to-image | 2024-11-11T06:28:56Z | ---
license: apache-2.0
base_model:
- black-forest-labs/FLUX.1-schnell
library_name: diffusers
pipeline_tag: text-to-image
emoji: 🌊
tags:
- FluxPipeline
- FLUXv1-schnell
- image-generation
- flux-diffusers
- diffusers
- art
- realism
- photography
- illustration
- anime
- full finetune
- trained
- finetune
- trainable
- full-finetune
- checkpoint
- text2image
- Schnell
- Flux
- Artsy
- ArtsyLite
---
Herein lives a HF/Diffusers port of the Flux-Schnell-based [Artsy Lite](https://civitai.com/models/920261/artsy-lite) model by [jurdn](https://civitai.com/user/jurdn).
Find the safetensors and other versions/variants, plus more info, at the CivitAI link above.
|
suehyunpark/potpourri-8b-inst-fft-induction-bc-optimal-action-max1-per-task | suehyunpark | 2024-11-15T04:26:57Z | 14 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"base_model:barc0/Llama-3.1-ARC-Potpourri-Induction-8B",
"base_model:finetune:barc0/Llama-3.1-ARC-Potpourri-Induction-8B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-11-12T11:55:33Z | ---
base_model: barc0/Llama-3.1-ARC-Potpourri-Induction-8B
library_name: transformers
model_name: potpourri-8b-inst-fft-induction-bc-optimal-action-max1-per-task
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for potpourri-8b-inst-fft-induction-bc-optimal-action-max1-per-task
This model is a fine-tuned version of [barc0/Llama-3.1-ARC-Potpourri-Induction-8B](https://huggingface.co/barc0/Llama-3.1-ARC-Potpourri-Induction-8B).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="suehyunpark/potpourri-8b-inst-fft-induction-bc-optimal-action-max1-per-task", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/suehyun/arc-improve/runs/lkmxtlyv)
This model was trained with SFT.
### Framework versions
- TRL: 0.12.1
- Transformers: 4.46.2
- Pytorch: 2.5.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
v1v1d/Nayana_eval_hindi_lora_32 | v1v1d | 2024-11-15T04:15:05Z | 52 | 0 | transformers | [
"transformers",
"safetensors",
"GOT",
"feature-extraction",
"got",
"vision-language",
"ocr2.0",
"custom_code",
"image-text-to-text",
"multilingual",
"license:apache-2.0",
"region:us"
] | image-text-to-text | 2024-11-15T04:14:02Z | ---
pipeline_tag: image-text-to-text
library_name: transformers
language:
- multilingual
tags:
- got
- vision-language
- ocr2.0
- custom_code
license: apache-2.0
---
Nayana All langangauge 15k checkpoint 87.5 accuracy Base for other finetunes
Lora r = 32 trained on t4 |
asr-africa/mms-1b-all-lg-CV-Fleurs_filtered-100hrs-v1 | asr-africa | 2024-11-15T04:13:44Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:fleurs",
"base_model:facebook/mms-1b-all",
"base_model:finetune:facebook/mms-1b-all",
"license:cc-by-nc-4.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | 2024-11-14T14:00:30Z | ---
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-1b-all
tags:
- generated_from_trainer
datasets:
- fleurs
metrics:
- wer
model-index:
- name: mms-1b-all-lg-CV-Fleurs_filtered-100hrs-v1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: fleurs
config: lg_ug
split: test
args: lg_ug
metrics:
- name: Wer
type: wer
value: 0.4098153547133139
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mms-1b-all-lg-CV-Fleurs_filtered-100hrs-v1
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2897
- Wer: 0.4098
- Cer: 0.0743
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 70
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
| 0.3203 | 1.0 | 7125 | 0.3178 | 0.4156 | 0.0762 |
| 0.2149 | 2.0 | 14250 | 0.3008 | 0.4194 | 0.0759 |
| 0.2093 | 3.0 | 21375 | 0.3015 | 0.4017 | 0.0743 |
| 0.2064 | 4.0 | 28500 | 0.3043 | 0.4114 | 0.0745 |
| 0.2042 | 5.0 | 35625 | 0.2955 | 0.4069 | 0.0753 |
| 0.2022 | 6.0 | 42750 | 0.3009 | 0.4088 | 0.0750 |
| 0.1989 | 7.0 | 49875 | 0.3088 | 0.4092 | 0.0756 |
| 0.1983 | 8.0 | 57000 | 0.2980 | 0.4081 | 0.0754 |
| 0.1969 | 9.0 | 64125 | 0.2951 | 0.4040 | 0.0741 |
| 0.1957 | 10.0 | 71250 | 0.2899 | 0.4039 | 0.0745 |
| 0.1945 | 11.0 | 78375 | 0.2896 | 0.4083 | 0.0744 |
| 0.1936 | 12.0 | 85500 | 0.2931 | 0.4038 | 0.0743 |
| 0.1929 | 13.0 | 92625 | 0.2897 | 0.4098 | 0.0743 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.1.0+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3
|
danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF | danielhanchen | 2024-11-15T04:09:28Z | 9 | 0 | transformers | [
"transformers",
"gguf",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"base_model:Qwen/Qwen2.5-Coder-3B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-3B-Instruct",
"license:other",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-11-15T04:09:13Z | ---
license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/main/LICENSE
language:
- en
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
- code
- codeqwen
- chat
- qwen
- qwen-coder
- llama-cpp
- gguf-my-repo
---
# danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2.5-Coder-3B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF --hf-file qwen2.5-coder-3b-instruct-q2_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF --hf-file qwen2.5-coder-3b-instruct-q2_k.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF --hf-file qwen2.5-coder-3b-instruct-q2_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF --hf-file qwen2.5-coder-3b-instruct-q2_k.gguf -c 2048
```
|
Kelex83/finetuned-detr-resnet-50-dc5-fashionpedia | Kelex83 | 2024-11-15T04:08:17Z | 32 | 0 | transformers | [
"transformers",
"safetensors",
"detr",
"object-detection",
"generated_from_trainer",
"base_model:facebook/detr-resnet-50-dc5",
"base_model:finetune:facebook/detr-resnet-50-dc5",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | object-detection | 2024-11-13T09:23:11Z | ---
library_name: transformers
license: apache-2.0
base_model: facebook/detr-resnet-50-dc5
tags:
- generated_from_trainer
model-index:
- name: finetuned-detr-resnet-50-dc5-fashionpedia
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuned-detr-resnet-50-dc5-fashionpedia
This model is a fine-tuned version of [facebook/detr-resnet-50-dc5](https://huggingface.co/facebook/detr-resnet-50-dc5) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2712
- Map: 0.0137
- Map 50: 0.0256
- Map 75: 0.0131
- Map Small: 0.0064
- Map Medium: 0.0183
- Map Large: 0.0123
- Mar 1: 0.0366
- Mar 10: 0.0653
- Mar 100: 0.0683
- Mar Small: 0.0264
- Mar Medium: 0.0676
- Mar Large: 0.0777
- Map Shirt, blouse: 0.0
- Mar 100 Shirt, blouse: 0.0
- Map Top, t-shirt, sweatshirt: 0.0347
- Mar 100 Top, t-shirt, sweatshirt: 0.3371
- Map Sweater: 0.0
- Mar 100 Sweater: 0.0
- Map Cardigan: 0.0
- Mar 100 Cardigan: 0.0
- Map Jacket: 0.0
- Mar 100 Jacket: 0.0
- Map Vest: 0.0
- Mar 100 Vest: 0.0
- Map Pants: 0.1262
- Mar 100 Pants: 0.6475
- Map Shorts: 0.0
- Mar 100 Shorts: 0.0
- Map Skirt: 0.0
- Mar 100 Skirt: 0.0
- Map Coat: 0.0
- Mar 100 Coat: 0.0
- Map Dress: 0.1141
- Mar 100 Dress: 0.7232
- Map Jumpsuit: 0.0
- Mar 100 Jumpsuit: 0.0
- Map Cape: 0.0
- Mar 100 Cape: 0.0
- Map Glasses: 0.0086
- Mar 100 Glasses: 0.0946
- Map Hat: 0.0
- Mar 100 Hat: 0.0
- Map Headband, head covering, hair accessory: 0.0006
- Mar 100 Headband, head covering, hair accessory: 0.0037
- Map Tie: 0.0
- Mar 100 Tie: 0.0
- Map Glove: 0.0
- Mar 100 Glove: 0.0
- Map Watch: 0.0
- Mar 100 Watch: 0.0
- Map Belt: 0.0
- Mar 100 Belt: 0.0
- Map Leg warmer: 0.0
- Mar 100 Leg warmer: 0.0
- Map Tights, stockings: 0.0
- Mar 100 Tights, stockings: 0.0
- Map Sock: 0.0
- Mar 100 Sock: 0.0
- Map Shoe: 0.2039
- Mar 100 Shoe: 0.5147
- Map Bag, wallet: 0.0134
- Mar 100 Bag, wallet: 0.0173
- Map Scarf: 0.0
- Mar 100 Scarf: 0.0
- Map Umbrella: 0.0
- Mar 100 Umbrella: 0.0
- Map Hood: 0.0
- Mar 100 Hood: 0.0
- Map Collar: 0.0
- Mar 100 Collar: 0.0
- Map Lapel: 0.0079
- Mar 100 Lapel: 0.0059
- Map Epaulette: 0.0
- Mar 100 Epaulette: 0.0
- Map Sleeve: 0.078
- Mar 100 Sleeve: 0.4796
- Map Pocket: 0.0002
- Mar 100 Pocket: 0.0606
- Map Neckline: 0.0417
- Mar 100 Neckline: 0.2583
- Map Buckle: 0.0
- Mar 100 Buckle: 0.0
- Map Zipper: 0.0
- Mar 100 Zipper: 0.0
- Map Applique: 0.0
- Mar 100 Applique: 0.0
- Map Bead: 0.0
- Mar 100 Bead: 0.0
- Map Bow: 0.0
- Mar 100 Bow: 0.0
- Map Flower: 0.0
- Mar 100 Flower: 0.0
- Map Fringe: 0.0
- Mar 100 Fringe: 0.0
- Map Ribbon: 0.0
- Mar 100 Ribbon: 0.0
- Map Rivet: 0.0
- Mar 100 Rivet: 0.0
- Map Ruffle: 0.0
- Mar 100 Ruffle: 0.0
- Map Sequin: 0.0
- Mar 100 Sequin: 0.0
- Map Tassel: 0.0
- Mar 100 Tassel: 0.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 10000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Shirt, blouse | Mar 100 Shirt, blouse | Map Top, t-shirt, sweatshirt | Mar 100 Top, t-shirt, sweatshirt | Map Sweater | Mar 100 Sweater | Map Cardigan | Mar 100 Cardigan | Map Jacket | Mar 100 Jacket | Map Vest | Mar 100 Vest | Map Pants | Mar 100 Pants | Map Shorts | Mar 100 Shorts | Map Skirt | Mar 100 Skirt | Map Coat | Mar 100 Coat | Map Dress | Mar 100 Dress | Map Jumpsuit | Mar 100 Jumpsuit | Map Cape | Mar 100 Cape | Map Glasses | Mar 100 Glasses | Map Hat | Mar 100 Hat | Map Headband, head covering, hair accessory | Mar 100 Headband, head covering, hair accessory | Map Tie | Mar 100 Tie | Map Glove | Mar 100 Glove | Map Watch | Mar 100 Watch | Map Belt | Mar 100 Belt | Map Leg warmer | Mar 100 Leg warmer | Map Tights, stockings | Mar 100 Tights, stockings | Map Sock | Mar 100 Sock | Map Shoe | Mar 100 Shoe | Map Bag, wallet | Mar 100 Bag, wallet | Map Scarf | Mar 100 Scarf | Map Umbrella | Mar 100 Umbrella | Map Hood | Mar 100 Hood | Map Collar | Mar 100 Collar | Map Lapel | Mar 100 Lapel | Map Epaulette | Mar 100 Epaulette | Map Sleeve | Mar 100 Sleeve | Map Pocket | Mar 100 Pocket | Map Neckline | Mar 100 Neckline | Map Buckle | Mar 100 Buckle | Map Zipper | Mar 100 Zipper | Map Applique | Mar 100 Applique | Map Bead | Mar 100 Bead | Map Bow | Mar 100 Bow | Map Flower | Mar 100 Flower | Map Fringe | Mar 100 Fringe | Map Ribbon | Mar 100 Ribbon | Map Rivet | Mar 100 Rivet | Map Ruffle | Mar 100 Ruffle | Map Sequin | Mar 100 Sequin | Map Tassel | Mar 100 Tassel |
|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-----------------:|:---------------------:|:----------------------------:|:--------------------------------:|:-----------:|:---------------:|:------------:|:----------------:|:----------:|:--------------:|:--------:|:------------:|:---------:|:-------------:|:----------:|:--------------:|:---------:|:-------------:|:--------:|:------------:|:---------:|:-------------:|:------------:|:----------------:|:--------:|:------------:|:-----------:|:---------------:|:-------:|:-----------:|:-------------------------------------------:|:-----------------------------------------------:|:-------:|:-----------:|:---------:|:-------------:|:---------:|:-------------:|:--------:|:------------:|:--------------:|:------------------:|:---------------------:|:-------------------------:|:--------:|:------------:|:--------:|:------------:|:---------------:|:-------------------:|:---------:|:-------------:|:------------:|:----------------:|:--------:|:------------:|:----------:|:--------------:|:---------:|:-------------:|:-------------:|:-----------------:|:----------:|:--------------:|:----------:|:--------------:|:------------:|:----------------:|:----------:|:--------------:|:----------:|:--------------:|:------------:|:----------------:|:--------:|:------------:|:-------:|:-----------:|:----------:|:--------------:|:----------:|:--------------:|:----------:|:--------------:|:---------:|:-------------:|:----------:|:--------------:|:----------:|:--------------:|:----------:|:--------------:|
| 7.0493 | 0.0044 | 50 | 6.4615 | 0.0002 | 0.0002 | 0.0002 | 0.0 | 0.0002 | 0.0006 | 0.0004 | 0.0013 | 0.0016 | 0.0006 | 0.0004 | 0.0072 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0167 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0012 | 0.0 | 0.0 | 0.0001 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0193 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.008 | 0.0145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0082 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0118 | 0.0 | 0.0 | 0.0 | 0.0 |
| 5.3509 | 0.0088 | 100 | 5.6823 | 0.0003 | 0.0003 | 0.0003 | 0.0 | 0.0002 | 0.0012 | 0.0006 | 0.001 | 0.0017 | 0.0007 | 0.0021 | 0.0053 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0004 | 0.0087 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0193 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0119 | 0.0192 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0091 | 0.0 | 0.0 | 0.0 | 0.0057 | 0.0 | 0.0 | 0.0 | 0.0144 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 5.3659 | 0.0132 | 150 | 5.1351 | 0.0003 | 0.0005 | 0.0003 | 0.0 | 0.0001 | 0.0012 | 0.0009 | 0.0021 | 0.0037 | 0.001 | 0.0034 | 0.0146 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0167 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0006 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0019 | 0.0283 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0157 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0111 | 0.0178 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0004 | 0.0688 | 0.0 | 0.0 | 0.0 | 0.0078 | 0.0 | 0.0 | 0.0 | 0.0119 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0026 | 0.0 | 0.0 | 0.0 | 0.0 |
| 4.5562 | 0.0175 | 200 | 4.6970 | 0.0002 | 0.0004 | 0.0001 | 0.0 | 0.0002 | 0.0003 | 0.0003 | 0.0007 | 0.0034 | 0.0011 | 0.0044 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0004 | 0.0063 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0016 | 0.0054 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0007 | 0.1231 | 0.0 | 0.0 | 0.0005 | 0.0107 | 0.0 | 0.0 | 0.0 | 0.0119 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 5.181 | 0.0219 | 250 | 4.3474 | 0.0001 | 0.0003 | 0.0001 | 0.0 | 0.0002 | 0.0001 | 0.0002 | 0.0005 | 0.0035 | 0.0013 | 0.0045 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0016 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0068 | 0.0046 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.1353 | 0.0 | 0.0 | 0.0001 | 0.0124 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.9616 | 0.0263 | 300 | 3.9479 | 0.0 | 0.0001 | 0.0 | 0.0 | 0.0001 | 0.0001 | 0.0001 | 0.0008 | 0.0042 | 0.0022 | 0.0051 | 0.0129 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0249 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.001 | 0.1518 | 0.0 | 0.0 | 0.0002 | 0.0156 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.7922 | 0.0307 | 350 | 3.7664 | 0.0001 | 0.0002 | 0.0 | 0.0 | 0.0001 | 0.0001 | 0.0002 | 0.0009 | 0.0049 | 0.0017 | 0.0059 | 0.0182 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0243 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0013 | 0.1908 | 0.0 | 0.0 | 0.0008 | 0.0122 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4752 | 0.0351 | 400 | 3.9790 | 0.0001 | 0.0004 | 0.0 | 0.0001 | 0.0002 | 0.0003 | 0.0004 | 0.0019 | 0.0075 | 0.0041 | 0.01 | 0.015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0025 | 0.1017 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0018 | 0.2403 | 0.0 | 0.0 | 0.0006 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.9056 | 0.0395 | 450 | 3.7476 | 0.0001 | 0.0003 | 0.0 | 0.0001 | 0.0001 | 0.0001 | 0.0004 | 0.0014 | 0.0065 | 0.0036 | 0.0078 | 0.0129 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0024 | 0.0568 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0019 | 0.2417 | 0.0 | 0.0 | 0.0001 | 0.0002 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 4.0423 | 0.0438 | 500 | 3.5736 | 0.0001 | 0.0005 | 0.0 | 0.0001 | 0.0001 | 0.0001 | 0.0004 | 0.0018 | 0.0073 | 0.0043 | 0.0086 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0025 | 0.0584 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0028 | 0.2763 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.3564 | 0.0482 | 550 | 3.4520 | 0.0003 | 0.0011 | 0.0001 | 0.0004 | 0.0004 | 0.0001 | 0.0007 | 0.0044 | 0.0116 | 0.0083 | 0.0139 | 0.0147 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0101 | 0.1876 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0039 | 0.3426 | 0.0 | 0.0 | 0.0007 | 0.0015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.1953 | 0.0526 | 600 | 3.3816 | 0.0005 | 0.0016 | 0.0002 | 0.0006 | 0.0007 | 0.0001 | 0.001 | 0.0067 | 0.0145 | 0.0102 | 0.0185 | 0.0151 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0198 | 0.328 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0038 | 0.3381 | 0.0 | 0.0 | 0.0002 | 0.0004 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5103 | 0.0570 | 650 | 3.3732 | 0.0007 | 0.0024 | 0.0003 | 0.0007 | 0.001 | 0.0001 | 0.0013 | 0.0073 | 0.0146 | 0.0104 | 0.0193 | 0.0198 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0291 | 0.378 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0035 | 0.2907 | 0.0 | 0.0 | 0.0005 | 0.0035 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0506 | 0.0614 | 700 | 3.3284 | 0.0007 | 0.0024 | 0.0003 | 0.0008 | 0.001 | 0.0001 | 0.0013 | 0.0081 | 0.0161 | 0.0111 | 0.0209 | 0.0164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0281 | 0.3659 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0053 | 0.3703 | 0.0 | 0.0 | 0.001 | 0.0038 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2105 | 0.0658 | 750 | 3.3047 | 0.0008 | 0.0027 | 0.0003 | 0.0008 | 0.0011 | 0.0001 | 0.0014 | 0.0082 | 0.0156 | 0.011 | 0.02 | 0.0169 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0311 | 0.3509 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0049 | 0.3603 | 0.0 | 0.0 | 0.0007 | 0.0066 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6299 | 0.0701 | 800 | 3.2656 | 0.0011 | 0.0037 | 0.0004 | 0.0011 | 0.0015 | 0.0001 | 0.002 | 0.0091 | 0.0158 | 0.0102 | 0.0211 | 0.0262 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0447 | 0.3593 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.006 | 0.3602 | 0.0 | 0.0 | 0.0011 | 0.0085 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0512 | 0.0745 | 850 | 3.2161 | 0.0012 | 0.0037 | 0.0005 | 0.0011 | 0.0016 | 0.0002 | 0.0021 | 0.0105 | 0.0176 | 0.0134 | 0.023 | 0.0298 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.043 | 0.3998 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0073 | 0.3646 | 0.0 | 0.0 | 0.0034 | 0.0451 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4365 | 0.0789 | 900 | 3.1872 | 0.0013 | 0.0043 | 0.0006 | 0.0013 | 0.0018 | 0.0002 | 0.002 | 0.0108 | 0.018 | 0.0136 | 0.0234 | 0.0287 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0504 | 0.3998 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.008 | 0.3953 | 0.0 | 0.0 | 0.0035 | 0.0324 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4587 | 0.0833 | 950 | 3.1776 | 0.0016 | 0.0049 | 0.0007 | 0.0013 | 0.0025 | 0.0002 | 0.0024 | 0.0111 | 0.0181 | 0.0129 | 0.0241 | 0.0283 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0556 | 0.3766 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0088 | 0.4052 | 0.0 | 0.0 | 0.008 | 0.052 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.7678 | 0.0877 | 1000 | 3.1366 | 0.0017 | 0.005 | 0.0008 | 0.0013 | 0.0026 | 0.0005 | 0.0026 | 0.0124 | 0.0199 | 0.0156 | 0.0255 | 0.0334 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0016 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0553 | 0.4129 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0103 | 0.4162 | 0.0 | 0.0 | 0.0066 | 0.084 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9833 | 0.0921 | 1050 | 3.1290 | 0.002 | 0.0056 | 0.001 | 0.0016 | 0.0026 | 0.0005 | 0.003 | 0.0129 | 0.0197 | 0.0145 | 0.0265 | 0.0296 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0016 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0676 | 0.4114 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0101 | 0.4164 | 0.0 | 0.0 | 0.006 | 0.0781 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4028 | 0.0964 | 1100 | 3.0953 | 0.0019 | 0.0055 | 0.0008 | 0.0015 | 0.003 | 0.0005 | 0.0029 | 0.0135 | 0.0207 | 0.0158 | 0.0269 | 0.0338 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0051 | 0.0049 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0638 | 0.4308 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0112 | 0.424 | 0.0 | 0.0 | 0.0079 | 0.094 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9266 | 0.1008 | 1150 | 3.1042 | 0.0016 | 0.0046 | 0.0009 | 0.0012 | 0.0029 | 0.0006 | 0.0026 | 0.0128 | 0.0209 | 0.0163 | 0.0268 | 0.0316 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0056 | 0.0069 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0487 | 0.4455 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0119 | 0.4135 | 0.0 | 0.0 | 0.0082 | 0.0968 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.82 | 0.1052 | 1200 | 3.0522 | 0.002 | 0.0059 | 0.0009 | 0.0015 | 0.0029 | 0.0006 | 0.0031 | 0.0142 | 0.0209 | 0.0152 | 0.0277 | 0.0343 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0082 | 0.0094 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0618 | 0.4117 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0131 | 0.4271 | 0.0 | 0.0 | 0.0089 | 0.112 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2205 | 0.1096 | 1250 | 3.0567 | 0.002 | 0.0059 | 0.0011 | 0.0014 | 0.003 | 0.0008 | 0.0037 | 0.0161 | 0.022 | 0.0157 | 0.0286 | 0.0336 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0115 | 0.028 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0538 | 0.4408 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0191 | 0.3985 | 0.0 | 0.0 | 0.0097 | 0.1429 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.127 | 0.1140 | 1300 | 3.1491 | 0.0021 | 0.0059 | 0.0011 | 0.0018 | 0.0027 | 0.0007 | 0.004 | 0.0147 | 0.02 | 0.0127 | 0.0268 | 0.0367 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.005 | 0.0201 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0583 | 0.4457 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0183 | 0.3663 | 0.0 | 0.0 | 0.0131 | 0.0899 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.3857 | 0.1184 | 1350 | 3.0887 | 0.0022 | 0.0059 | 0.0013 | 0.0016 | 0.0032 | 0.0006 | 0.0041 | 0.0157 | 0.021 | 0.0147 | 0.0276 | 0.032 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0075 | 0.0222 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0591 | 0.4646 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0178 | 0.3663 | 0.0 | 0.0 | 0.015 | 0.112 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4188 | 0.1227 | 1400 | 3.0303 | 0.0022 | 0.006 | 0.0011 | 0.0014 | 0.0031 | 0.001 | 0.0039 | 0.016 | 0.0214 | 0.0154 | 0.0283 | 0.0313 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0157 | 0.0268 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0533 | 0.4352 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0178 | 0.3834 | 0.0 | 0.0 | 0.013 | 0.1371 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8893 | 0.1271 | 1450 | 2.9888 | 0.0025 | 0.0069 | 0.0014 | 0.002 | 0.0036 | 0.0008 | 0.0049 | 0.0178 | 0.0228 | 0.0172 | 0.0297 | 0.0353 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0058 | 0.0291 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0751 | 0.4528 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0205 | 0.406 | 0.0 | 0.0 | 0.0137 | 0.1628 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0498 | 0.1315 | 1500 | 2.9922 | 0.0026 | 0.0071 | 0.0014 | 0.002 | 0.0039 | 0.0007 | 0.005 | 0.0177 | 0.023 | 0.0163 | 0.0297 | 0.0364 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0087 | 0.0443 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0776 | 0.4105 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0204 | 0.4382 | 0.0 | 0.0 | 0.0151 | 0.1627 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.335 | 0.1359 | 1550 | 2.9809 | 0.0027 | 0.0073 | 0.0014 | 0.002 | 0.0038 | 0.001 | 0.0058 | 0.0189 | 0.0243 | 0.0174 | 0.03 | 0.0373 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0123 | 0.086 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0778 | 0.4315 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0185 | 0.423 | 0.0 | 0.0 | 0.0137 | 0.1765 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.1299 | 0.1403 | 1600 | 2.9605 | 0.0029 | 0.0079 | 0.0015 | 0.0022 | 0.0039 | 0.001 | 0.0065 | 0.0193 | 0.0245 | 0.0167 | 0.0297 | 0.0334 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0151 | 0.1219 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.087 | 0.4205 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0161 | 0.4142 | 0.0 | 0.0 | 0.0146 | 0.1696 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.189 | 0.1447 | 1650 | 2.9775 | 0.0023 | 0.007 | 0.0011 | 0.0015 | 0.003 | 0.0013 | 0.0065 | 0.0188 | 0.0241 | 0.0156 | 0.028 | 0.0343 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0201 | 0.1593 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0558 | 0.3799 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0157 | 0.4 | 0.0 | 0.0 | 0.0149 | 0.171 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2569 | 0.1490 | 1700 | 2.9462 | 0.0028 | 0.0077 | 0.0015 | 0.002 | 0.0035 | 0.0012 | 0.0066 | 0.0191 | 0.0243 | 0.0166 | 0.029 | 0.0335 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0229 | 0.1343 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0714 | 0.4231 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0149 | 0.3978 | 0.0001 | 0.0002 | 0.0207 | 0.1629 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2697 | 0.1534 | 1750 | 2.9275 | 0.0027 | 0.0075 | 0.0015 | 0.0019 | 0.0036 | 0.0014 | 0.0074 | 0.02 | 0.0255 | 0.0164 | 0.029 | 0.0387 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0023 | 0.0022 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0206 | 0.1738 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0635 | 0.4292 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0195 | 0.4244 | 0.0 | 0.0 | 0.0195 | 0.1447 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.8347 | 0.1578 | 1800 | 2.8975 | 0.0029 | 0.0077 | 0.0018 | 0.0021 | 0.0037 | 0.0017 | 0.0073 | 0.0208 | 0.027 | 0.0185 | 0.0303 | 0.0395 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0017 | 0.0038 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0252 | 0.1866 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.069 | 0.4611 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0163 | 0.423 | 0.0 | 0.0 | 0.0223 | 0.1674 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.336 | 0.1622 | 1850 | 2.8781 | 0.0031 | 0.0081 | 0.002 | 0.0021 | 0.0036 | 0.002 | 0.0084 | 0.0219 | 0.0279 | 0.0184 | 0.0311 | 0.0406 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0017 | 0.0061 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0313 | 0.2075 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0731 | 0.4601 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0203 | 0.4414 | 0.0001 | 0.0006 | 0.0181 | 0.1698 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.1503 | 0.1666 | 1900 | 2.8516 | 0.0036 | 0.0091 | 0.0023 | 0.0023 | 0.0046 | 0.0022 | 0.0087 | 0.0234 | 0.0287 | 0.0186 | 0.03 | 0.0404 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.015 | 0.0194 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0293 | 0.2441 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0799 | 0.4445 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0191 | 0.4294 | 0.0 | 0.0015 | 0.0213 | 0.1803 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9179 | 0.1710 | 1950 | 2.8664 | 0.0032 | 0.0089 | 0.0018 | 0.0019 | 0.0037 | 0.0022 | 0.009 | 0.0229 | 0.0275 | 0.0154 | 0.0298 | 0.0416 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0104 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0279 | 0.2498 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0678 | 0.3701 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0242 | 0.4278 | 0.0001 | 0.0017 | 0.0188 | 0.2 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9207 | 0.1753 | 2000 | 2.8651 | 0.0037 | 0.0096 | 0.0023 | 0.0026 | 0.0042 | 0.0021 | 0.0094 | 0.0237 | 0.0293 | 0.018 | 0.0304 | 0.0415 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0025 | 0.0083 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0334 | 0.287 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1 | 0.4208 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0201 | 0.4315 | 0.0 | 0.0 | 0.0149 | 0.2005 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7564 | 0.1797 | 2050 | 2.8356 | 0.0042 | 0.0103 | 0.0027 | 0.003 | 0.005 | 0.0027 | 0.0108 | 0.0254 | 0.0308 | 0.0169 | 0.0317 | 0.0429 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0114 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0412 | 0.3581 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1012 | 0.4047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0202 | 0.4474 | 0.004 | 0.0017 | 0.015 | 0.1903 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9197 | 0.1841 | 2100 | 2.8097 | 0.0041 | 0.0096 | 0.0028 | 0.0026 | 0.0046 | 0.0027 | 0.0105 | 0.0261 | 0.0319 | 0.0182 | 0.0328 | 0.0439 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0132 | 0.0204 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0452 | 0.3589 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0952 | 0.4425 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0179 | 0.4531 | 0.0001 | 0.0039 | 0.0164 | 0.1865 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4666 | 0.1885 | 2150 | 2.8181 | 0.0043 | 0.0099 | 0.003 | 0.0025 | 0.0044 | 0.0033 | 0.0108 | 0.0269 | 0.0323 | 0.0184 | 0.0314 | 0.0491 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0238 | 0.0404 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0377 | 0.364 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0985 | 0.4392 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0203 | 0.4459 | 0.0001 | 0.0022 | 0.0156 | 0.1941 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8845 | 0.1929 | 2200 | 2.8454 | 0.0038 | 0.0091 | 0.0026 | 0.0023 | 0.0044 | 0.0025 | 0.0109 | 0.0269 | 0.0319 | 0.0162 | 0.0316 | 0.0465 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0165 | 0.0414 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0358 | 0.4014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0869 | 0.4242 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0217 | 0.4278 | 0.0 | 0.0035 | 0.0148 | 0.1681 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.562 | 0.1973 | 2250 | 2.8099 | 0.0038 | 0.0094 | 0.0024 | 0.0022 | 0.0049 | 0.0026 | 0.0109 | 0.0269 | 0.032 | 0.0187 | 0.0309 | 0.0428 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0135 | 0.05 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0371 | 0.3659 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.079 | 0.4258 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0244 | 0.4242 | 0.0 | 0.0043 | 0.0189 | 0.2002 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4295 | 0.2016 | 2300 | 2.8019 | 0.0043 | 0.0097 | 0.0033 | 0.0024 | 0.0047 | 0.0032 | 0.0116 | 0.0275 | 0.0326 | 0.0171 | 0.0329 | 0.0377 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0268 | 0.0771 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0432 | 0.3626 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0876 | 0.4517 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0223 | 0.4267 | 0.0 | 0.0045 | 0.0188 | 0.1776 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6915 | 0.2060 | 2350 | 2.7792 | 0.0044 | 0.0103 | 0.003 | 0.0024 | 0.0043 | 0.0036 | 0.0134 | 0.029 | 0.0341 | 0.0167 | 0.0331 | 0.0467 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0312 | 0.0952 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0452 | 0.4108 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0829 | 0.4292 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0227 | 0.4323 | 0.0001 | 0.0046 | 0.0189 | 0.1954 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5396 | 0.2104 | 2400 | 2.7852 | 0.0046 | 0.0106 | 0.0033 | 0.0025 | 0.0048 | 0.0036 | 0.0138 | 0.0313 | 0.0359 | 0.0168 | 0.0326 | 0.0478 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0426 | 0.1583 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0423 | 0.4492 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0904 | 0.4539 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0202 | 0.407 | 0.0001 | 0.0069 | 0.018 | 0.1763 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9112 | 0.2148 | 2450 | 2.7817 | 0.0046 | 0.0113 | 0.0031 | 0.0024 | 0.0046 | 0.0035 | 0.0145 | 0.032 | 0.0364 | 0.0162 | 0.0321 | 0.0491 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0413 | 0.1809 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.044 | 0.4746 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0798 | 0.4075 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0233 | 0.4133 | 0.0 | 0.0061 | 0.022 | 0.1929 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1891 | 0.2192 | 2500 | 2.7650 | 0.005 | 0.0117 | 0.0035 | 0.0029 | 0.0053 | 0.0035 | 0.0156 | 0.0354 | 0.0398 | 0.0175 | 0.0336 | 0.0556 | 0.0 | 0.0 | 0.0014 | 0.0021 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0411 | 0.2449 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0379 | 0.5041 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1031 | 0.4429 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.022 | 0.4199 | 0.0001 | 0.0106 | 0.0225 | 0.2053 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2978 | 0.2236 | 2550 | 2.7209 | 0.0053 | 0.0122 | 0.0039 | 0.0029 | 0.0052 | 0.0042 | 0.0161 | 0.0355 | 0.0408 | 0.0197 | 0.0336 | 0.0553 | 0.0 | 0.0 | 0.0017 | 0.0038 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0428 | 0.2185 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0498 | 0.5516 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1044 | 0.4366 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0214 | 0.4527 | 0.0001 | 0.0093 | 0.0215 | 0.2057 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0312 | 0.2280 | 2600 | 2.7076 | 0.0053 | 0.0123 | 0.0037 | 0.003 | 0.0053 | 0.0042 | 0.0168 | 0.0362 | 0.0409 | 0.019 | 0.0343 | 0.0552 | 0.0 | 0.0 | 0.001 | 0.0025 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.044 | 0.2137 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0487 | 0.564 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1034 | 0.4483 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.024 | 0.4313 | 0.0 | 0.0058 | 0.0226 | 0.2176 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9525 | 0.2323 | 2650 | 2.7448 | 0.005 | 0.0116 | 0.0038 | 0.0029 | 0.0049 | 0.0039 | 0.0161 | 0.0362 | 0.0406 | 0.0178 | 0.0336 | 0.0594 | 0.0 | 0.0 | 0.0043 | 0.0072 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0422 | 0.2379 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0401 | 0.5549 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1004 | 0.4586 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0236 | 0.3983 | 0.0001 | 0.0095 | 0.0217 | 0.2002 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3726 | 0.2367 | 2700 | 2.7169 | 0.0051 | 0.0115 | 0.0039 | 0.0024 | 0.0049 | 0.0047 | 0.0171 | 0.0366 | 0.041 | 0.0172 | 0.0335 | 0.0597 | 0.0 | 0.0 | 0.0014 | 0.0034 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0552 | 0.2497 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0461 | 0.573 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0879 | 0.4284 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0264 | 0.4167 | 0.0 | 0.0059 | 0.0197 | 0.2066 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4374 | 0.2411 | 2750 | 2.7227 | 0.0049 | 0.0115 | 0.0037 | 0.0024 | 0.0061 | 0.0043 | 0.017 | 0.0372 | 0.0416 | 0.0176 | 0.035 | 0.0594 | 0.0 | 0.0 | 0.0006 | 0.0015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0434 | 0.2532 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0517 | 0.5896 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0834 | 0.4256 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0246 | 0.4171 | 0.0001 | 0.0063 | 0.0236 | 0.221 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3248 | 0.2455 | 2800 | 2.6968 | 0.0053 | 0.0119 | 0.0039 | 0.0027 | 0.0053 | 0.0045 | 0.0182 | 0.0388 | 0.0434 | 0.0178 | 0.035 | 0.0611 | 0.0 | 0.0 | 0.001 | 0.0036 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0455 | 0.2981 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0568 | 0.6079 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0934 | 0.4559 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0231 | 0.4169 | 0.0001 | 0.0078 | 0.0222 | 0.204 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9627 | 0.2499 | 2850 | 2.6914 | 0.0055 | 0.0122 | 0.0043 | 0.0027 | 0.005 | 0.0051 | 0.0179 | 0.0393 | 0.0439 | 0.0178 | 0.036 | 0.0545 | 0.0 | 0.0 | 0.009 | 0.0078 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0531 | 0.3029 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0543 | 0.6128 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0939 | 0.4689 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.025 | 0.4234 | 0.0 | 0.0086 | 0.0199 | 0.1929 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.5196 | 0.2543 | 2900 | 2.6557 | 0.0058 | 0.0128 | 0.0046 | 0.0028 | 0.006 | 0.0049 | 0.0189 | 0.04 | 0.0449 | 0.0199 | 0.0382 | 0.0508 | 0.0 | 0.0 | 0.0037 | 0.0101 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0492 | 0.3175 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0619 | 0.5872 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1075 | 0.479 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0262 | 0.4453 | 0.0001 | 0.0138 | 0.0195 | 0.2128 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6884 | 0.2586 | 2950 | 2.6729 | 0.0058 | 0.0129 | 0.0045 | 0.0029 | 0.0055 | 0.005 | 0.0186 | 0.0389 | 0.0434 | 0.019 | 0.0372 | 0.0468 | 0.0 | 0.0 | 0.0026 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0476 | 0.3408 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0682 | 0.5547 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0998 | 0.4673 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0226 | 0.4141 | 0.0001 | 0.0154 | 0.0259 | 0.198 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5318 | 0.2630 | 3000 | 2.6668 | 0.006 | 0.0132 | 0.0048 | 0.0031 | 0.0059 | 0.0051 | 0.02 | 0.0415 | 0.0461 | 0.0189 | 0.0391 | 0.0548 | 0.0 | 0.0 | 0.0055 | 0.0141 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0542 | 0.3959 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0593 | 0.5821 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1066 | 0.4709 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0226 | 0.4293 | 0.0001 | 0.0162 | 0.029 | 0.2122 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6744 | 0.2674 | 3050 | 2.6491 | 0.0063 | 0.0139 | 0.0051 | 0.0031 | 0.0062 | 0.0055 | 0.0203 | 0.042 | 0.0461 | 0.0195 | 0.0387 | 0.0503 | 0.0 | 0.0 | 0.0041 | 0.0234 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0644 | 0.3847 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0596 | 0.5778 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1075 | 0.4797 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0262 | 0.4178 | 0.0 | 0.0143 | 0.0295 | 0.2225 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0012 | 0.2718 | 3100 | 2.6299 | 0.0064 | 0.0135 | 0.0051 | 0.0029 | 0.006 | 0.0058 | 0.0206 | 0.0425 | 0.047 | 0.02 | 0.0394 | 0.0553 | 0.0 | 0.0 | 0.0054 | 0.0286 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0699 | 0.4 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0625 | 0.5797 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1038 | 0.4871 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0259 | 0.4347 | 0.0 | 0.0147 | 0.0268 | 0.2162 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.1837 | 0.2762 | 3150 | 2.6213 | 0.0067 | 0.0142 | 0.0058 | 0.003 | 0.0066 | 0.0062 | 0.0209 | 0.0435 | 0.0482 | 0.0215 | 0.0399 | 0.0624 | 0.0 | 0.0 | 0.0071 | 0.0356 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0712 | 0.3904 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0686 | 0.6138 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1119 | 0.4918 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0265 | 0.4374 | 0.0001 | 0.0162 | 0.025 | 0.2329 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9647 | 0.2806 | 3200 | 2.6316 | 0.0061 | 0.0134 | 0.0047 | 0.0028 | 0.0062 | 0.0056 | 0.0206 | 0.0424 | 0.0467 | 0.0182 | 0.0387 | 0.0545 | 0.0 | 0.0 | 0.0046 | 0.0337 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0657 | 0.4207 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0621 | 0.5986 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0975 | 0.4579 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0249 | 0.4268 | 0.0 | 0.0121 | 0.0241 | 0.1992 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6275 | 0.2849 | 3250 | 2.6175 | 0.0064 | 0.0135 | 0.0053 | 0.0028 | 0.0069 | 0.0059 | 0.0219 | 0.0448 | 0.0493 | 0.0205 | 0.0412 | 0.0563 | 0.0 | 0.0 | 0.0051 | 0.0366 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0643 | 0.4411 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0707 | 0.6293 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1009 | 0.4827 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0262 | 0.4342 | 0.0 | 0.0154 | 0.0262 | 0.2288 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2604 | 0.2893 | 3300 | 2.6128 | 0.0069 | 0.0142 | 0.006 | 0.0031 | 0.0081 | 0.0063 | 0.022 | 0.0453 | 0.0499 | 0.0202 | 0.0424 | 0.0657 | 0.0 | 0.0 | 0.0097 | 0.0627 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0732 | 0.4268 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0696 | 0.6398 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1104 | 0.488 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0246 | 0.4383 | 0.0001 | 0.0158 | 0.0293 | 0.2249 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0361 | 0.2937 | 3350 | 2.5990 | 0.0074 | 0.0154 | 0.0065 | 0.003 | 0.0066 | 0.0073 | 0.0235 | 0.0452 | 0.0503 | 0.0208 | 0.0429 | 0.0564 | 0.0 | 0.0 | 0.0135 | 0.0827 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0882 | 0.4382 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0817 | 0.6301 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1099 | 0.4832 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0226 | 0.4304 | 0.0001 | 0.0184 | 0.0262 | 0.2296 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4672 | 0.2981 | 3400 | 2.6148 | 0.0064 | 0.0137 | 0.0052 | 0.0029 | 0.0087 | 0.0055 | 0.0211 | 0.0458 | 0.05 | 0.0197 | 0.0432 | 0.0563 | 0.0 | 0.0 | 0.0108 | 0.0914 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.069 | 0.4232 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0519 | 0.6415 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1124 | 0.481 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0276 | 0.425 | 0.0001 | 0.0171 | 0.0205 | 0.221 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0081 | 0.3025 | 3450 | 2.6040 | 0.0065 | 0.0136 | 0.0055 | 0.0027 | 0.0081 | 0.0061 | 0.021 | 0.0465 | 0.0515 | 0.0213 | 0.0453 | 0.0581 | 0.0 | 0.0 | 0.0122 | 0.0869 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0688 | 0.4048 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0642 | 0.6809 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1034 | 0.4948 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0267 | 0.4558 | 0.0001 | 0.0171 | 0.0233 | 0.2309 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0952 | 0.3069 | 3500 | 2.5743 | 0.0068 | 0.0141 | 0.0058 | 0.0029 | 0.0085 | 0.0061 | 0.0233 | 0.0488 | 0.0537 | 0.0215 | 0.0473 | 0.0641 | 0.0 | 0.0 | 0.0149 | 0.0945 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0668 | 0.4742 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0682 | 0.6809 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1063 | 0.4974 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0284 | 0.4596 | 0.0001 | 0.018 | 0.0273 | 0.2457 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5016 | 0.3112 | 3550 | 2.5812 | 0.0069 | 0.0142 | 0.0059 | 0.0033 | 0.0078 | 0.0062 | 0.0242 | 0.049 | 0.0536 | 0.0205 | 0.0462 | 0.0707 | 0.0 | 0.0 | 0.0131 | 0.0848 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0719 | 0.4822 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0643 | 0.685 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1127 | 0.4992 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0315 | 0.4626 | 0.0001 | 0.0182 | 0.0261 | 0.235 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4596 | 0.3156 | 3600 | 2.5700 | 0.0073 | 0.0148 | 0.0064 | 0.003 | 0.0071 | 0.0069 | 0.0241 | 0.0492 | 0.0541 | 0.0209 | 0.0465 | 0.0706 | 0.0 | 0.0 | 0.0179 | 0.0884 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0731 | 0.4662 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.073 | 0.701 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1111 | 0.5056 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.031 | 0.4626 | 0.0001 | 0.0216 | 0.0276 | 0.2429 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2083 | 0.3200 | 3650 | 2.5575 | 0.0075 | 0.015 | 0.0066 | 0.0033 | 0.0083 | 0.0072 | 0.0253 | 0.0499 | 0.0551 | 0.0212 | 0.047 | 0.0725 | 0.0 | 0.0 | 0.014 | 0.0893 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0844 | 0.4841 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0726 | 0.7067 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1144 | 0.5068 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0304 | 0.4744 | 0.0001 | 0.0216 | 0.028 | 0.254 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2074 | 0.3244 | 3700 | 2.5718 | 0.0075 | 0.0151 | 0.0065 | 0.0035 | 0.0084 | 0.0065 | 0.0248 | 0.0503 | 0.055 | 0.0208 | 0.0482 | 0.07 | 0.0 | 0.0 | 0.0133 | 0.1141 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0727 | 0.5016 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0718 | 0.6882 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.129 | 0.4864 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0309 | 0.4681 | 0.0001 | 0.0195 | 0.027 | 0.2543 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8081 | 0.3288 | 3750 | 2.5592 | 0.0082 | 0.0165 | 0.0072 | 0.0039 | 0.0078 | 0.0076 | 0.025 | 0.0492 | 0.0539 | 0.0216 | 0.0472 | 0.0676 | 0.0 | 0.0 | 0.0163 | 0.1221 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0855 | 0.4443 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0809 | 0.686 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1291 | 0.4884 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0356 | 0.4576 | 0.0001 | 0.0214 | 0.028 | 0.2599 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4224 | 0.3332 | 3800 | 2.5625 | 0.0078 | 0.0159 | 0.0066 | 0.0033 | 0.0076 | 0.007 | 0.0251 | 0.0504 | 0.055 | 0.0215 | 0.0498 | 0.0692 | 0.0 | 0.0 | 0.0136 | 0.1162 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0854 | 0.4876 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.077 | 0.6866 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1173 | 0.5093 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0371 | 0.4568 | 0.0001 | 0.0247 | 0.0278 | 0.2466 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6959 | 0.3375 | 3850 | 2.5409 | 0.0077 | 0.0154 | 0.0068 | 0.0028 | 0.0077 | 0.0074 | 0.025 | 0.0506 | 0.0553 | 0.0221 | 0.0491 | 0.0658 | 0.0 | 0.0 | 0.0219 | 0.1128 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0855 | 0.5099 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0776 | 0.6819 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.113 | 0.5157 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0354 | 0.4585 | 0.0001 | 0.0219 | 0.0211 | 0.2426 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7602 | 0.3419 | 3900 | 2.5424 | 0.008 | 0.016 | 0.007 | 0.0034 | 0.0085 | 0.0072 | 0.0257 | 0.051 | 0.0555 | 0.0219 | 0.0494 | 0.0668 | 0.0 | 0.0 | 0.0225 | 0.1257 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0772 | 0.5121 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0761 | 0.6799 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1232 | 0.5036 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0325 | 0.4465 | 0.0001 | 0.0243 | 0.0259 | 0.255 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2808 | 0.3463 | 3950 | 2.5410 | 0.0077 | 0.0151 | 0.0069 | 0.003 | 0.0078 | 0.0072 | 0.0254 | 0.0507 | 0.0555 | 0.0212 | 0.05 | 0.0671 | 0.0 | 0.0 | 0.0228 | 0.1208 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0766 | 0.5201 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0783 | 0.6799 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1105 | 0.5064 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0311 | 0.4609 | 0.0001 | 0.0232 | 0.025 | 0.2375 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8816 | 0.3507 | 4000 | 2.5517 | 0.0074 | 0.0148 | 0.0069 | 0.0033 | 0.0079 | 0.0067 | 0.0245 | 0.0505 | 0.0552 | 0.0203 | 0.0498 | 0.0694 | 0.0 | 0.0 | 0.0148 | 0.1112 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0745 | 0.5178 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0774 | 0.6839 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1097 | 0.4925 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0313 | 0.4563 | 0.0001 | 0.0247 | 0.0262 | 0.2496 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6022 | 0.3551 | 4050 | 2.5470 | 0.0078 | 0.0153 | 0.0071 | 0.0034 | 0.0085 | 0.0069 | 0.024 | 0.0506 | 0.0556 | 0.0216 | 0.0491 | 0.0646 | 0.0 | 0.0 | 0.015 | 0.14 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0805 | 0.5 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.076 | 0.6766 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1187 | 0.4984 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.027 | 0.4652 | 0.0001 | 0.0216 | 0.0322 | 0.2511 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0763 | 0.3595 | 4100 | 2.5482 | 0.0073 | 0.0151 | 0.0063 | 0.003 | 0.0075 | 0.0066 | 0.0229 | 0.0484 | 0.0533 | 0.0204 | 0.0482 | 0.0619 | 0.0 | 0.0 | 0.0155 | 0.1528 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0714 | 0.4787 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0765 | 0.6362 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1124 | 0.4671 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0268 | 0.4432 | 0.0001 | 0.0281 | 0.0253 | 0.24 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9504 | 0.3638 | 4150 | 2.5168 | 0.0083 | 0.0167 | 0.0074 | 0.0036 | 0.0081 | 0.0077 | 0.0254 | 0.0504 | 0.0553 | 0.0222 | 0.0481 | 0.0642 | 0.0 | 0.0 | 0.0169 | 0.1608 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0912 | 0.4745 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.08 | 0.6713 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1244 | 0.4818 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0324 | 0.4685 | 0.0001 | 0.0262 | 0.0282 | 0.2578 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9656 | 0.3682 | 4200 | 2.5238 | 0.0076 | 0.0155 | 0.0065 | 0.0032 | 0.0082 | 0.0069 | 0.0251 | 0.0505 | 0.0555 | 0.0216 | 0.0509 | 0.0632 | 0.0 | 0.0 | 0.018 | 0.1501 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.074 | 0.4997 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0743 | 0.6638 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1124 | 0.4966 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0323 | 0.4676 | 0.0001 | 0.0247 | 0.0295 | 0.2448 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8733 | 0.3726 | 4250 | 2.5311 | 0.008 | 0.0159 | 0.0072 | 0.0033 | 0.0085 | 0.0072 | 0.0249 | 0.0495 | 0.0544 | 0.0225 | 0.0479 | 0.0615 | 0.0 | 0.0 | 0.0172 | 0.1459 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0809 | 0.4873 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0813 | 0.6553 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1168 | 0.4999 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.03 | 0.4475 | 0.0001 | 0.0255 | 0.0326 | 0.2351 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8777 | 0.3770 | 4300 | 2.5353 | 0.0074 | 0.0154 | 0.0062 | 0.0031 | 0.0082 | 0.007 | 0.0233 | 0.0482 | 0.0525 | 0.0208 | 0.0455 | 0.0605 | 0.0 | 0.0 | 0.0186 | 0.1493 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0714 | 0.4605 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0813 | 0.6384 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1126 | 0.4838 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0285 | 0.4292 | 0.0001 | 0.0266 | 0.0282 | 0.2271 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.312 | 0.3814 | 4350 | 2.5155 | 0.0075 | 0.0155 | 0.0064 | 0.0034 | 0.0092 | 0.0067 | 0.024 | 0.0509 | 0.0551 | 0.0215 | 0.0495 | 0.0635 | 0.0 | 0.0 | 0.0207 | 0.1495 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0694 | 0.5089 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0682 | 0.6717 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.116 | 0.491 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0377 | 0.448 | 0.0001 | 0.0234 | 0.0325 | 0.2426 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3045 | 0.3858 | 4400 | 2.5102 | 0.008 | 0.0161 | 0.0071 | 0.0035 | 0.0096 | 0.0072 | 0.0252 | 0.0518 | 0.0563 | 0.022 | 0.0501 | 0.0649 | 0.0 | 0.0 | 0.0215 | 0.1539 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0772 | 0.522 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0715 | 0.6789 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1178 | 0.5043 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0472 | 0.4614 | 0.0001 | 0.0296 | 0.0306 | 0.2376 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.6469 | 0.3901 | 4450 | 2.4944 | 0.0084 | 0.0167 | 0.0078 | 0.0031 | 0.0101 | 0.0078 | 0.0254 | 0.0525 | 0.057 | 0.0219 | 0.0506 | 0.0663 | 0.0 | 0.0 | 0.0193 | 0.164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0853 | 0.5226 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0826 | 0.69 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1219 | 0.5092 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0423 | 0.4549 | 0.0001 | 0.027 | 0.0257 | 0.2493 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1084 | 0.3945 | 4500 | 2.4853 | 0.0085 | 0.017 | 0.0075 | 0.0034 | 0.0101 | 0.0076 | 0.0259 | 0.0531 | 0.0578 | 0.0235 | 0.0518 | 0.0661 | 0.0 | 0.0 | 0.0199 | 0.1867 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0837 | 0.5131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0832 | 0.6923 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1273 | 0.5 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0391 | 0.4699 | 0.0001 | 0.0275 | 0.0294 | 0.2668 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.34 | 0.3989 | 4550 | 2.4771 | 0.0082 | 0.0167 | 0.0072 | 0.0032 | 0.0102 | 0.0072 | 0.0253 | 0.0529 | 0.0576 | 0.0224 | 0.0529 | 0.0665 | 0.0 | 0.0 | 0.0214 | 0.2069 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0734 | 0.5172 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.081 | 0.674 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1245 | 0.4932 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0407 | 0.4679 | 0.0001 | 0.032 | 0.0294 | 0.2525 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4942 | 0.4033 | 4600 | 2.4845 | 0.0085 | 0.0171 | 0.0076 | 0.0037 | 0.0095 | 0.0072 | 0.0254 | 0.0517 | 0.056 | 0.0219 | 0.0505 | 0.0645 | 0.0 | 0.0 | 0.0264 | 0.2067 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0754 | 0.5064 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0797 | 0.6435 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1355 | 0.4935 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0377 | 0.4451 | 0.0001 | 0.0322 | 0.0289 | 0.2425 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4839 | 0.4077 | 4650 | 2.4877 | 0.0088 | 0.0176 | 0.0081 | 0.0039 | 0.0103 | 0.0074 | 0.0256 | 0.0525 | 0.0569 | 0.0217 | 0.0532 | 0.0638 | 0.0 | 0.0 | 0.026 | 0.2137 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0826 | 0.514 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0792 | 0.6553 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1392 | 0.4893 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0384 | 0.4602 | 0.0001 | 0.0322 | 0.0316 | 0.2468 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5089 | 0.4121 | 4700 | 2.4807 | 0.0084 | 0.0172 | 0.0073 | 0.0034 | 0.0109 | 0.0073 | 0.0267 | 0.0531 | 0.057 | 0.0198 | 0.0528 | 0.066 | 0.0 | 0.0 | 0.0209 | 0.2181 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0797 | 0.5341 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0796 | 0.6705 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1231 | 0.4721 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0448 | 0.449 | 0.0001 | 0.0333 | 0.0299 | 0.2403 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9228 | 0.4164 | 4750 | 2.4644 | 0.0088 | 0.0177 | 0.0079 | 0.0037 | 0.0113 | 0.0077 | 0.0272 | 0.0548 | 0.0588 | 0.0218 | 0.0539 | 0.0746 | 0.0 | 0.0 | 0.0242 | 0.2067 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0821 | 0.5576 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0819 | 0.685 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1319 | 0.5031 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0397 | 0.4564 | 0.0001 | 0.0286 | 0.0354 | 0.2616 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.5246 | 0.4208 | 4800 | 2.4674 | 0.0088 | 0.0174 | 0.0079 | 0.0037 | 0.0105 | 0.0078 | 0.0271 | 0.0536 | 0.0574 | 0.0215 | 0.0524 | 0.066 | 0.0 | 0.0 | 0.0198 | 0.1825 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0838 | 0.5465 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.081 | 0.6722 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1314 | 0.507 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0479 | 0.4478 | 0.0001 | 0.0273 | 0.0306 | 0.2546 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6292 | 0.4252 | 4850 | 2.4685 | 0.0087 | 0.0171 | 0.0079 | 0.0039 | 0.0104 | 0.0078 | 0.0269 | 0.0545 | 0.0584 | 0.0217 | 0.0539 | 0.0682 | 0.0 | 0.0 | 0.0192 | 0.1945 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0795 | 0.55 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0814 | 0.6805 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1303 | 0.5147 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0487 | 0.4563 | 0.0001 | 0.0362 | 0.0329 | 0.2485 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0016 | 0.4296 | 4900 | 2.4470 | 0.0089 | 0.0175 | 0.0082 | 0.0037 | 0.0109 | 0.008 | 0.028 | 0.0553 | 0.0593 | 0.0223 | 0.0544 | 0.0685 | 0.0 | 0.0 | 0.0196 | 0.2017 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0875 | 0.5752 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0826 | 0.6736 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1323 | 0.511 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.047 | 0.4662 | 0.0001 | 0.0375 | 0.0327 | 0.2576 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2245 | 0.4340 | 4950 | 2.4507 | 0.0093 | 0.0178 | 0.0084 | 0.0035 | 0.0104 | 0.0089 | 0.0289 | 0.0566 | 0.0606 | 0.0225 | 0.0557 | 0.0716 | 0.0 | 0.0 | 0.0212 | 0.2175 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1037 | 0.5949 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0823 | 0.6874 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1295 | 0.4978 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0511 | 0.471 | 0.0001 | 0.0403 | 0.0304 | 0.273 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5848 | 0.4384 | 5000 | 2.4488 | 0.0092 | 0.0179 | 0.0085 | 0.0037 | 0.0101 | 0.0083 | 0.0284 | 0.056 | 0.0598 | 0.0224 | 0.0544 | 0.0688 | 0.0 | 0.0 | 0.0196 | 0.2164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0985 | 0.5818 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0841 | 0.6795 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1333 | 0.514 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0466 | 0.459 | 0.0001 | 0.0403 | 0.0325 | 0.2565 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7955 | 0.4427 | 5050 | 2.4566 | 0.0087 | 0.0169 | 0.0079 | 0.0037 | 0.0108 | 0.0078 | 0.0276 | 0.0558 | 0.0594 | 0.0218 | 0.0539 | 0.069 | 0.0 | 0.0 | 0.0207 | 0.2152 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0872 | 0.5828 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0749 | 0.6713 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.127 | 0.5104 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0519 | 0.4549 | 0.0001 | 0.0422 | 0.0289 | 0.2535 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6832 | 0.4471 | 5100 | 2.4586 | 0.0089 | 0.0172 | 0.0081 | 0.0037 | 0.0112 | 0.0081 | 0.0276 | 0.0558 | 0.0598 | 0.0226 | 0.0552 | 0.0698 | 0.0 | 0.0 | 0.0204 | 0.2101 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0949 | 0.5834 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0754 | 0.6785 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1296 | 0.5118 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0493 | 0.4639 | 0.0002 | 0.0454 | 0.0289 | 0.2556 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5706 | 0.4515 | 5150 | 2.4522 | 0.0094 | 0.0179 | 0.0088 | 0.0038 | 0.0115 | 0.0086 | 0.0283 | 0.0566 | 0.0605 | 0.0228 | 0.0557 | 0.0705 | 0.0 | 0.0 | 0.023 | 0.2189 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1035 | 0.5901 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0814 | 0.6825 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1318 | 0.5198 | 0.0089 | 0.0065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0527 | 0.4626 | 0.0001 | 0.0416 | 0.0295 | 0.2599 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2534 | 0.4559 | 5200 | 2.4336 | 0.0097 | 0.0182 | 0.0092 | 0.0038 | 0.0113 | 0.0088 | 0.0288 | 0.0562 | 0.06 | 0.0223 | 0.0561 | 0.0716 | 0.0 | 0.0 | 0.0225 | 0.2137 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1032 | 0.5844 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0912 | 0.6803 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1417 | 0.518 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0487 | 0.4608 | 0.0002 | 0.0422 | 0.0285 | 0.2577 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4737 | 0.4603 | 5250 | 2.4330 | 0.0097 | 0.0187 | 0.009 | 0.0039 | 0.0107 | 0.009 | 0.0288 | 0.0555 | 0.0595 | 0.0225 | 0.055 | 0.0727 | 0.0 | 0.0 | 0.0234 | 0.2162 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1033 | 0.5729 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0893 | 0.6709 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1418 | 0.5063 | 0.0099 | 0.0047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0422 | 0.4538 | 0.0002 | 0.0433 | 0.0347 | 0.2709 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2841 | 0.4647 | 5300 | 2.4288 | 0.0101 | 0.0192 | 0.0095 | 0.0041 | 0.0117 | 0.0095 | 0.0298 | 0.0559 | 0.06 | 0.0229 | 0.055 | 0.0729 | 0.0 | 0.0 | 0.0253 | 0.2265 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1083 | 0.5637 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0966 | 0.6864 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1479 | 0.5068 | 0.0084 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0435 | 0.4686 | 0.0002 | 0.0485 | 0.0327 | 0.2566 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3675 | 0.4691 | 5350 | 2.4358 | 0.0098 | 0.0185 | 0.0094 | 0.0042 | 0.0115 | 0.009 | 0.0292 | 0.0567 | 0.0607 | 0.0223 | 0.0562 | 0.076 | 0.0 | 0.0 | 0.0218 | 0.2288 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1008 | 0.5844 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0841 | 0.6789 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1538 | 0.5101 | 0.0113 | 0.0084 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0466 | 0.4699 | 0.0002 | 0.047 | 0.0316 | 0.2642 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7819 | 0.4734 | 5400 | 2.4224 | 0.0103 | 0.0193 | 0.0098 | 0.0041 | 0.0128 | 0.0099 | 0.0303 | 0.0574 | 0.0619 | 0.0231 | 0.0576 | 0.0757 | 0.0 | 0.0 | 0.0285 | 0.2621 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1086 | 0.5787 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0972 | 0.6943 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1524 | 0.499 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.045 | 0.4793 | 0.0002 | 0.0485 | 0.033 | 0.2824 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9625 | 0.4778 | 5450 | 2.4276 | 0.0102 | 0.0196 | 0.0094 | 0.0041 | 0.0119 | 0.0097 | 0.0299 | 0.0561 | 0.0604 | 0.0234 | 0.0557 | 0.0711 | 0.0 | 0.0 | 0.0284 | 0.2457 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1086 | 0.5455 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0971 | 0.6874 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1503 | 0.4889 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0438 | 0.4737 | 0.0002 | 0.05 | 0.0341 | 0.2814 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8536 | 0.4822 | 5500 | 2.4273 | 0.01 | 0.0193 | 0.0093 | 0.0041 | 0.0124 | 0.0092 | 0.03 | 0.0559 | 0.0599 | 0.0222 | 0.0566 | 0.0709 | 0.0 | 0.0 | 0.0276 | 0.2387 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1008 | 0.5592 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.095 | 0.6839 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1487 | 0.4946 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.046 | 0.459 | 0.0002 | 0.0463 | 0.0316 | 0.2682 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2057 | 0.4866 | 5550 | 2.4177 | 0.0103 | 0.0191 | 0.01 | 0.0042 | 0.013 | 0.0098 | 0.0312 | 0.0584 | 0.0628 | 0.0244 | 0.0584 | 0.0757 | 0.0 | 0.0 | 0.0274 | 0.2501 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1034 | 0.5777 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0948 | 0.7199 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1573 | 0.5148 | 0.0092 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0478 | 0.4795 | 0.0002 | 0.0452 | 0.0335 | 0.2963 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8074 | 0.4910 | 5600 | 2.4264 | 0.01 | 0.0192 | 0.0092 | 0.0042 | 0.0133 | 0.0096 | 0.0308 | 0.0576 | 0.0619 | 0.0221 | 0.0588 | 0.0846 | 0.0 | 0.0 | 0.0275 | 0.2528 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0989 | 0.5873 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0942 | 0.7171 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1493 | 0.4939 | 0.0089 | 0.0047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0471 | 0.4634 | 0.0002 | 0.0487 | 0.0338 | 0.2793 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8717 | 0.4954 | 5650 | 2.4182 | 0.0102 | 0.0193 | 0.0095 | 0.0043 | 0.0124 | 0.0095 | 0.0311 | 0.0579 | 0.062 | 0.0226 | 0.0592 | 0.0771 | 0.0 | 0.0 | 0.0307 | 0.2699 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0963 | 0.5844 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0976 | 0.7016 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1553 | 0.4987 | 0.0089 | 0.0042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0448 | 0.4681 | 0.0002 | 0.052 | 0.0335 | 0.2716 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8318 | 0.4997 | 5700 | 2.4191 | 0.0101 | 0.0193 | 0.0096 | 0.0043 | 0.0133 | 0.0094 | 0.0303 | 0.0583 | 0.0623 | 0.0222 | 0.0582 | 0.0774 | 0.0 | 0.0 | 0.0257 | 0.2587 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1103 | 0.6006 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0847 | 0.7077 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1554 | 0.5077 | 0.0089 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0492 | 0.4665 | 0.0002 | 0.0474 | 0.0292 | 0.2723 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4833 | 0.5041 | 5750 | 2.4234 | 0.0102 | 0.0193 | 0.0098 | 0.0042 | 0.0133 | 0.0094 | 0.0297 | 0.0584 | 0.0624 | 0.0223 | 0.0574 | 0.0786 | 0.0 | 0.0 | 0.029 | 0.2773 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1111 | 0.6 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0854 | 0.7004 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1599 | 0.5187 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0457 | 0.4569 | 0.0002 | 0.0472 | 0.0318 | 0.2658 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1686 | 0.5085 | 5800 | 2.4080 | 0.0105 | 0.0197 | 0.0098 | 0.0043 | 0.0137 | 0.0101 | 0.0306 | 0.0585 | 0.0628 | 0.0233 | 0.0587 | 0.0786 | 0.0 | 0.0 | 0.0306 | 0.2749 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1115 | 0.6061 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0886 | 0.703 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1575 | 0.5115 | 0.0089 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0497 | 0.474 | 0.0001 | 0.0455 | 0.0343 | 0.27 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1837 | 0.5129 | 5850 | 2.4086 | 0.0105 | 0.0199 | 0.01 | 0.0044 | 0.0127 | 0.0102 | 0.0301 | 0.058 | 0.062 | 0.0233 | 0.0573 | 0.0791 | 0.0 | 0.0 | 0.0288 | 0.2752 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1071 | 0.585 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0924 | 0.6957 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.162 | 0.5129 | 0.0089 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0501 | 0.4553 | 0.0002 | 0.0506 | 0.0322 | 0.2709 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1888 | 0.5173 | 5900 | 2.4098 | 0.0108 | 0.0205 | 0.0103 | 0.0044 | 0.0138 | 0.0105 | 0.0306 | 0.0579 | 0.0619 | 0.0223 | 0.0588 | 0.0796 | 0.0 | 0.0 | 0.0319 | 0.2771 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1139 | 0.5946 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0952 | 0.6996 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1652 | 0.4996 | 0.0092 | 0.0056 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0527 | 0.4529 | 0.0002 | 0.0526 | 0.0284 | 0.2638 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7038 | 0.5217 | 5950 | 2.4142 | 0.0105 | 0.02 | 0.0096 | 0.0045 | 0.0144 | 0.0097 | 0.03 | 0.0576 | 0.0611 | 0.0223 | 0.0578 | 0.0756 | 0.0 | 0.0 | 0.0289 | 0.2651 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1075 | 0.6134 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0855 | 0.6756 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0023 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1667 | 0.5049 | 0.0079 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0549 | 0.4403 | 0.0001 | 0.0489 | 0.0295 | 0.255 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0488 | 0.5260 | 6000 | 2.4054 | 0.0107 | 0.0205 | 0.01 | 0.0044 | 0.0137 | 0.0102 | 0.0311 | 0.0581 | 0.0616 | 0.0216 | 0.0576 | 0.0753 | 0.0 | 0.0 | 0.0303 | 0.2912 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1147 | 0.6166 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0861 | 0.6803 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1702 | 0.491 | 0.0091 | 0.0084 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0538 | 0.442 | 0.0001 | 0.0459 | 0.0295 | 0.2585 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.342 | 0.5304 | 6050 | 2.4073 | 0.011 | 0.0207 | 0.0106 | 0.005 | 0.0143 | 0.0106 | 0.0311 | 0.0589 | 0.0628 | 0.0228 | 0.0595 | 0.0818 | 0.0 | 0.0 | 0.0284 | 0.2771 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1212 | 0.621 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0913 | 0.7031 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1746 | 0.4893 | 0.0046 | 0.0079 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0534 | 0.4766 | 0.0001 | 0.0413 | 0.0322 | 0.2735 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9017 | 0.5348 | 6100 | 2.4063 | 0.0112 | 0.0211 | 0.0107 | 0.005 | 0.0134 | 0.0106 | 0.032 | 0.0584 | 0.0623 | 0.0228 | 0.0589 | 0.0857 | 0.0 | 0.0 | 0.0292 | 0.2771 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1198 | 0.6108 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0979 | 0.6978 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1751 | 0.4938 | 0.0088 | 0.0089 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0511 | 0.4642 | 0.0002 | 0.0478 | 0.0311 | 0.2644 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.968 | 0.5392 | 6150 | 2.4001 | 0.0109 | 0.0207 | 0.0104 | 0.0048 | 0.0132 | 0.0106 | 0.031 | 0.0579 | 0.0618 | 0.0219 | 0.0602 | 0.08 | 0.0 | 0.0 | 0.0293 | 0.2739 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1123 | 0.6102 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0989 | 0.6907 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.17 | 0.4812 | 0.0079 | 0.0047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0547 | 0.4659 | 0.0002 | 0.0481 | 0.0277 | 0.2672 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0871 | 0.5436 | 6200 | 2.3993 | 0.0108 | 0.0206 | 0.0102 | 0.0046 | 0.0133 | 0.0103 | 0.031 | 0.0577 | 0.0617 | 0.0221 | 0.0603 | 0.0775 | 0.0 | 0.0 | 0.0316 | 0.2832 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1095 | 0.6022 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1011 | 0.6904 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1674 | 0.4871 | 0.0082 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0484 | 0.4592 | 0.0002 | 0.0489 | 0.0283 | 0.2571 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4298 | 0.5480 | 6250 | 2.4031 | 0.0104 | 0.0202 | 0.0097 | 0.0047 | 0.0125 | 0.0095 | 0.0302 | 0.0573 | 0.0614 | 0.0216 | 0.0583 | 0.0745 | 0.0 | 0.0 | 0.0306 | 0.2893 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1027 | 0.615 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0916 | 0.6671 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0018 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1691 | 0.479 | 0.0079 | 0.0047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0455 | 0.4697 | 0.0002 | 0.0496 | 0.0317 | 0.2469 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4915 | 0.5523 | 6300 | 2.3843 | 0.0107 | 0.0204 | 0.0103 | 0.005 | 0.0144 | 0.0095 | 0.0306 | 0.0592 | 0.0631 | 0.023 | 0.0603 | 0.076 | 0.0 | 0.0 | 0.0295 | 0.2901 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1022 | 0.6194 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0881 | 0.6793 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0005 | 0.0028 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1782 | 0.5013 | 0.0097 | 0.0084 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0489 | 0.4735 | 0.0002 | 0.0563 | 0.0359 | 0.2722 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0322 | 0.5567 | 6350 | 2.3705 | 0.0109 | 0.0209 | 0.0101 | 0.0048 | 0.0129 | 0.0106 | 0.0318 | 0.0599 | 0.0636 | 0.023 | 0.0614 | 0.0773 | 0.0 | 0.0 | 0.0292 | 0.2962 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1066 | 0.6223 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0987 | 0.699 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1685 | 0.5029 | 0.0083 | 0.0075 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0528 | 0.4662 | 0.0002 | 0.0539 | 0.0366 | 0.2768 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.1661 | 0.5611 | 6400 | 2.3671 | 0.0114 | 0.0212 | 0.0109 | 0.0048 | 0.014 | 0.0115 | 0.0327 | 0.0604 | 0.0643 | 0.024 | 0.0609 | 0.077 | 0.0 | 0.0 | 0.0314 | 0.2897 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.114 | 0.6213 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1083 | 0.7175 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0023 | 0.0 | 0.0 | 0.0003 | 0.0028 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1712 | 0.5178 | 0.0082 | 0.0047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0553 | 0.4702 | 0.0002 | 0.0539 | 0.0352 | 0.2764 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6323 | 0.5655 | 6450 | 2.3834 | 0.0111 | 0.0209 | 0.0103 | 0.0047 | 0.014 | 0.0113 | 0.0324 | 0.0604 | 0.0642 | 0.0238 | 0.0599 | 0.0792 | 0.0 | 0.0 | 0.0285 | 0.2836 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1109 | 0.6299 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.101 | 0.7234 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0015 | 0.0 | 0.0 | 0.0004 | 0.0028 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.167 | 0.5123 | 0.0083 | 0.0051 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0592 | 0.4676 | 0.0002 | 0.053 | 0.0339 | 0.275 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9815 | 0.5699 | 6500 | 2.3698 | 0.0109 | 0.0205 | 0.0104 | 0.0047 | 0.0146 | 0.0107 | 0.0324 | 0.0606 | 0.0644 | 0.0237 | 0.0599 | 0.0759 | 0.0 | 0.0 | 0.0324 | 0.2907 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0967 | 0.6312 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1025 | 0.7187 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0004 | 0.0028 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1661 | 0.5286 | 0.0112 | 0.0117 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0546 | 0.4619 | 0.0001 | 0.048 | 0.0378 | 0.2698 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.7586 | 0.5743 | 6550 | 2.3746 | 0.0107 | 0.0203 | 0.0102 | 0.0046 | 0.0149 | 0.0108 | 0.0318 | 0.0604 | 0.0641 | 0.0234 | 0.0606 | 0.078 | 0.0 | 0.0 | 0.0322 | 0.2813 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1013 | 0.6153 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1007 | 0.7301 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0001 | 0.0062 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1589 | 0.5249 | 0.0082 | 0.0075 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.055 | 0.4655 | 0.0002 | 0.0474 | 0.0376 | 0.2721 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9074 | 0.5786 | 6600 | 2.3659 | 0.0111 | 0.0207 | 0.0107 | 0.0048 | 0.0135 | 0.0103 | 0.0324 | 0.0606 | 0.0645 | 0.0239 | 0.0597 | 0.0757 | 0.0 | 0.0 | 0.0315 | 0.2996 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1031 | 0.629 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1022 | 0.7142 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1686 | 0.5279 | 0.0079 | 0.0047 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.057 | 0.465 | 0.0001 | 0.0455 | 0.0383 | 0.2814 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9045 | 0.5830 | 6650 | 2.3662 | 0.011 | 0.0204 | 0.0104 | 0.0049 | 0.0147 | 0.01 | 0.0321 | 0.061 | 0.0651 | 0.0236 | 0.0618 | 0.0768 | 0.0 | 0.0 | 0.0292 | 0.2981 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1008 | 0.6274 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0986 | 0.7293 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0085 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1723 | 0.5241 | 0.0098 | 0.0093 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0571 | 0.4753 | 0.0002 | 0.048 | 0.0381 | 0.2743 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2403 | 0.5874 | 6700 | 2.3604 | 0.0105 | 0.02 | 0.0098 | 0.0048 | 0.0143 | 0.0098 | 0.0314 | 0.0603 | 0.064 | 0.0227 | 0.0618 | 0.0755 | 0.0 | 0.0 | 0.0288 | 0.2907 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0908 | 0.6299 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0948 | 0.7012 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0069 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1677 | 0.5225 | 0.009 | 0.0089 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0587 | 0.464 | 0.0001 | 0.0489 | 0.0352 | 0.2708 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7937 | 0.5918 | 6750 | 2.3725 | 0.0101 | 0.0193 | 0.0091 | 0.0046 | 0.0144 | 0.0096 | 0.0295 | 0.0595 | 0.0633 | 0.0223 | 0.0609 | 0.0752 | 0.0 | 0.0 | 0.0273 | 0.2855 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0869 | 0.6306 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0866 | 0.6937 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1628 | 0.5151 | 0.0092 | 0.0084 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0554 | 0.459 | 0.0002 | 0.0511 | 0.0341 | 0.266 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6128 | 0.5962 | 6800 | 2.3598 | 0.0104 | 0.02 | 0.0097 | 0.0045 | 0.0136 | 0.0104 | 0.0309 | 0.0593 | 0.0631 | 0.0215 | 0.0596 | 0.0764 | 0.0 | 0.0 | 0.0291 | 0.2884 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0984 | 0.6299 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0921 | 0.7069 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0001 | 0.0023 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1603 | 0.5021 | 0.0101 | 0.0098 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0575 | 0.4578 | 0.0001 | 0.0485 | 0.032 | 0.2586 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3714 | 0.6006 | 6850 | 2.3492 | 0.0111 | 0.0208 | 0.0104 | 0.0046 | 0.0138 | 0.0113 | 0.0327 | 0.0613 | 0.0653 | 0.0235 | 0.0619 | 0.0782 | 0.0 | 0.0 | 0.031 | 0.2964 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1056 | 0.6363 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.098 | 0.7415 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1645 | 0.514 | 0.0093 | 0.0098 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0643 | 0.4733 | 0.0002 | 0.0533 | 0.0384 | 0.2773 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.3155 | 0.6049 | 6900 | 2.3474 | 0.0109 | 0.0207 | 0.0103 | 0.0047 | 0.0155 | 0.0107 | 0.0324 | 0.0611 | 0.0648 | 0.0232 | 0.0633 | 0.0765 | 0.0 | 0.0 | 0.0307 | 0.2971 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0967 | 0.6226 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0991 | 0.7384 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0015 | 0.0 | 0.0 | 0.0002 | 0.0018 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1647 | 0.5181 | 0.0094 | 0.0098 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0634 | 0.4636 | 0.0002 | 0.0554 | 0.0392 | 0.2703 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6329 | 0.6093 | 6950 | 2.3509 | 0.0113 | 0.0211 | 0.0109 | 0.0046 | 0.0152 | 0.0106 | 0.0325 | 0.0613 | 0.065 | 0.0231 | 0.064 | 0.0766 | 0.0 | 0.0 | 0.0305 | 0.2966 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1022 | 0.6226 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1019 | 0.7427 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0038 | 0.0 | 0.0 | 0.0003 | 0.0018 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1647 | 0.5178 | 0.0182 | 0.0182 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0609 | 0.4721 | 0.0002 | 0.0528 | 0.0419 | 0.262 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9196 | 0.6137 | 7000 | 2.3432 | 0.0115 | 0.0212 | 0.0112 | 0.0046 | 0.0147 | 0.0109 | 0.0334 | 0.0618 | 0.0654 | 0.0243 | 0.063 | 0.0769 | 0.0 | 0.0 | 0.0312 | 0.2916 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1062 | 0.6166 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1046 | 0.7339 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0001 | 0.0085 | 0.0 | 0.0 | 0.0004 | 0.0028 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1681 | 0.5256 | 0.0182 | 0.021 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0595 | 0.4781 | 0.0002 | 0.0574 | 0.0388 | 0.2711 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8484 | 0.6181 | 7050 | 2.3584 | 0.0111 | 0.021 | 0.0107 | 0.0044 | 0.0144 | 0.0104 | 0.0321 | 0.0597 | 0.0632 | 0.0217 | 0.062 | 0.0753 | 0.0 | 0.0 | 0.0345 | 0.2956 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1051 | 0.622 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1044 | 0.7159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0062 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1599 | 0.5017 | 0.0143 | 0.0145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0586 | 0.4592 | 0.0002 | 0.0526 | 0.0335 | 0.2399 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1078 | 0.6225 | 7100 | 2.3503 | 0.0111 | 0.0208 | 0.0107 | 0.0046 | 0.0139 | 0.0101 | 0.0319 | 0.0601 | 0.0637 | 0.0225 | 0.0618 | 0.075 | 0.0 | 0.0 | 0.0296 | 0.2924 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1037 | 0.6242 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1014 | 0.7132 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.01 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1644 | 0.5138 | 0.0152 | 0.0154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0614 | 0.4627 | 0.0002 | 0.0524 | 0.0352 | 0.2442 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1935 | 0.6269 | 7150 | 2.3596 | 0.0111 | 0.0207 | 0.0103 | 0.0047 | 0.0135 | 0.0104 | 0.0315 | 0.0591 | 0.0625 | 0.0232 | 0.0606 | 0.0779 | 0.0 | 0.0 | 0.029 | 0.2771 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0988 | 0.628 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1013 | 0.6858 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0108 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1622 | 0.513 | 0.0152 | 0.0154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0617 | 0.4551 | 0.0002 | 0.0532 | 0.04 | 0.2386 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.1469 | 0.6312 | 7200 | 2.3577 | 0.011 | 0.0207 | 0.0107 | 0.0049 | 0.0139 | 0.0097 | 0.0309 | 0.0588 | 0.0621 | 0.0219 | 0.0599 | 0.077 | 0.0 | 0.0 | 0.0269 | 0.2718 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0965 | 0.6366 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0977 | 0.6898 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0085 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1684 | 0.5091 | 0.0132 | 0.0126 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0603 | 0.4416 | 0.0002 | 0.0515 | 0.0403 | 0.2342 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.8813 | 0.6356 | 7250 | 2.3379 | 0.0115 | 0.0216 | 0.0109 | 0.0048 | 0.0143 | 0.0108 | 0.0326 | 0.0613 | 0.0645 | 0.0224 | 0.0616 | 0.0791 | 0.0 | 0.0 | 0.0306 | 0.2979 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1043 | 0.6449 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0988 | 0.7238 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0077 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1728 | 0.504 | 0.0178 | 0.0192 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0648 | 0.464 | 0.0001 | 0.0483 | 0.0374 | 0.259 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1135 | 0.6400 | 7300 | 2.3347 | 0.0119 | 0.0223 | 0.0115 | 0.0049 | 0.0151 | 0.0112 | 0.0332 | 0.0616 | 0.065 | 0.0232 | 0.0636 | 0.0787 | 0.0 | 0.0 | 0.036 | 0.3029 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1128 | 0.6357 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1008 | 0.7278 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0062 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1783 | 0.5154 | 0.0159 | 0.0178 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0642 | 0.4727 | 0.0002 | 0.0498 | 0.041 | 0.262 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1482 | 0.6444 | 7350 | 2.3241 | 0.0121 | 0.0225 | 0.0117 | 0.005 | 0.0159 | 0.0117 | 0.0335 | 0.0618 | 0.0655 | 0.0241 | 0.0645 | 0.0783 | 0.0 | 0.0 | 0.0334 | 0.2958 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1216 | 0.6296 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1059 | 0.7396 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0108 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1821 | 0.5192 | 0.0126 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0625 | 0.4755 | 0.0002 | 0.0546 | 0.0394 | 0.2698 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8763 | 0.6488 | 7400 | 2.3245 | 0.012 | 0.0227 | 0.0115 | 0.0048 | 0.0153 | 0.0117 | 0.0337 | 0.0611 | 0.0646 | 0.0234 | 0.0628 | 0.0762 | 0.0 | 0.0 | 0.0339 | 0.2899 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1217 | 0.6156 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1059 | 0.7425 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.178 | 0.5158 | 0.0087 | 0.0098 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0681 | 0.4732 | 0.0002 | 0.0545 | 0.0339 | 0.2575 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.6302 | 0.6532 | 7450 | 2.3228 | 0.0121 | 0.0225 | 0.0116 | 0.0051 | 0.0153 | 0.0117 | 0.0335 | 0.0612 | 0.0643 | 0.023 | 0.0615 | 0.077 | 0.0 | 0.0 | 0.0337 | 0.2956 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1221 | 0.6287 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1054 | 0.7331 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0012 | 0.0192 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1803 | 0.5185 | 0.0089 | 0.0093 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0688 | 0.4658 | 0.0001 | 0.0478 | 0.035 | 0.2395 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6397 | 0.6575 | 7500 | 2.3219 | 0.0122 | 0.0226 | 0.0117 | 0.005 | 0.0155 | 0.0123 | 0.0338 | 0.0616 | 0.0649 | 0.0236 | 0.0615 | 0.0783 | 0.0 | 0.0 | 0.0336 | 0.2971 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.117 | 0.6293 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1107 | 0.7348 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0009 | 0.0185 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1803 | 0.5214 | 0.0109 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0704 | 0.4719 | 0.0001 | 0.0498 | 0.0387 | 0.2516 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0553 | 0.6619 | 7550 | 2.3254 | 0.0123 | 0.0229 | 0.0119 | 0.0051 | 0.0153 | 0.0121 | 0.0341 | 0.0614 | 0.0648 | 0.0235 | 0.0633 | 0.0782 | 0.0 | 0.0 | 0.0339 | 0.3166 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1139 | 0.6261 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1117 | 0.7152 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0006 | 0.0177 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.185 | 0.5185 | 0.0135 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0676 | 0.4705 | 0.0002 | 0.0515 | 0.0392 | 0.2497 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5076 | 0.6663 | 7600 | 2.3156 | 0.012 | 0.0225 | 0.0116 | 0.005 | 0.0151 | 0.0114 | 0.034 | 0.0615 | 0.0647 | 0.0234 | 0.0616 | 0.0783 | 0.0 | 0.0 | 0.0296 | 0.3042 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1175 | 0.6366 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1059 | 0.7222 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0138 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1781 | 0.5192 | 0.0085 | 0.0154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0725 | 0.4644 | 0.0001 | 0.0504 | 0.0405 | 0.2517 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2284 | 0.6707 | 7650 | 2.3124 | 0.0121 | 0.0229 | 0.0114 | 0.005 | 0.0157 | 0.0115 | 0.0343 | 0.0618 | 0.065 | 0.0234 | 0.0629 | 0.0779 | 0.0 | 0.0 | 0.03 | 0.3133 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1154 | 0.6328 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1061 | 0.7201 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0002 | 0.0169 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.18 | 0.5262 | 0.0121 | 0.0168 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0737 | 0.4635 | 0.0002 | 0.0487 | 0.0372 | 0.2535 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9091 | 0.6751 | 7700 | 2.3099 | 0.0124 | 0.0231 | 0.012 | 0.0051 | 0.0168 | 0.0118 | 0.0348 | 0.0627 | 0.0661 | 0.0238 | 0.0652 | 0.0819 | 0.0 | 0.0 | 0.0366 | 0.3234 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1194 | 0.6401 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.108 | 0.7333 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0003 | 0.0177 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1826 | 0.5278 | 0.0106 | 0.0145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0743 | 0.4674 | 0.0002 | 0.0517 | 0.0407 | 0.2642 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.77 | 0.6795 | 7750 | 2.3025 | 0.0125 | 0.0232 | 0.012 | 0.0052 | 0.017 | 0.0118 | 0.0351 | 0.063 | 0.0663 | 0.024 | 0.0661 | 0.0802 | 0.0 | 0.0 | 0.037 | 0.3263 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.118 | 0.6401 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1105 | 0.7321 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0008 | 0.0185 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1837 | 0.5304 | 0.0104 | 0.0126 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0727 | 0.469 | 0.0002 | 0.0558 | 0.0399 | 0.2638 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.6237 | 0.6839 | 7800 | 2.3045 | 0.0124 | 0.0232 | 0.0118 | 0.0051 | 0.0165 | 0.0118 | 0.0347 | 0.0632 | 0.0667 | 0.0244 | 0.0658 | 0.078 | 0.0 | 0.0 | 0.0358 | 0.3276 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.122 | 0.6411 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1085 | 0.7431 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0011 | 0.01 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1812 | 0.5303 | 0.0121 | 0.0126 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0696 | 0.4714 | 0.0002 | 0.0571 | 0.0404 | 0.2753 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7165 | 0.6882 | 7850 | 2.3041 | 0.0125 | 0.0232 | 0.012 | 0.0051 | 0.0167 | 0.0121 | 0.035 | 0.063 | 0.0665 | 0.0249 | 0.0644 | 0.0773 | 0.0 | 0.0 | 0.0333 | 0.3244 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1243 | 0.6395 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1121 | 0.735 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0005 | 0.0138 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1805 | 0.5256 | 0.0104 | 0.0126 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0705 | 0.4737 | 0.0002 | 0.0548 | 0.0422 | 0.281 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4805 | 0.6926 | 7900 | 2.2965 | 0.0126 | 0.0234 | 0.0121 | 0.0052 | 0.0163 | 0.0122 | 0.0351 | 0.0631 | 0.0664 | 0.0247 | 0.0646 | 0.0775 | 0.0 | 0.0 | 0.0327 | 0.3248 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1233 | 0.6382 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.114 | 0.7348 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0014 | 0.02 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1843 | 0.5245 | 0.0124 | 0.0117 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0711 | 0.4696 | 0.0002 | 0.0556 | 0.0403 | 0.2751 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3697 | 0.6970 | 7950 | 2.3020 | 0.0125 | 0.0232 | 0.012 | 0.0053 | 0.0158 | 0.0118 | 0.0347 | 0.0625 | 0.0658 | 0.024 | 0.0641 | 0.0772 | 0.0 | 0.0 | 0.0363 | 0.3223 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1176 | 0.6325 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1118 | 0.7207 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0024 | 0.0277 | 0.0 | 0.0 | 0.0001 | 0.0009 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.186 | 0.5233 | 0.0136 | 0.015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0671 | 0.4705 | 0.0002 | 0.0541 | 0.038 | 0.258 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4367 | 0.7014 | 8000 | 2.2973 | 0.0123 | 0.0237 | 0.0113 | 0.0055 | 0.0167 | 0.0117 | 0.0345 | 0.0624 | 0.0656 | 0.0241 | 0.0636 | 0.0776 | 0.0 | 0.0 | 0.0362 | 0.3267 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1119 | 0.6341 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1093 | 0.7138 | 0.0 | 0.0 | 0.0 | 0.0 | 0.004 | 0.0292 | 0.0 | 0.0 | 0.0001 | 0.0009 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1838 | 0.5123 | 0.0124 | 0.014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0702 | 0.4667 | 0.0002 | 0.0558 | 0.0398 | 0.2661 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8973 | 0.7058 | 8050 | 2.2975 | 0.012 | 0.0233 | 0.0111 | 0.0055 | 0.0172 | 0.0108 | 0.0342 | 0.0629 | 0.0662 | 0.0239 | 0.0661 | 0.078 | 0.0 | 0.0 | 0.0309 | 0.3366 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1076 | 0.6449 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.103 | 0.7138 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0039 | 0.0223 | 0.0 | 0.0 | 0.0001 | 0.0018 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.183 | 0.5104 | 0.0118 | 0.0154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.072 | 0.4738 | 0.0002 | 0.0584 | 0.0392 | 0.2674 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.3595 | 0.7102 | 8100 | 2.2966 | 0.0123 | 0.0233 | 0.0118 | 0.0056 | 0.0178 | 0.0111 | 0.0346 | 0.0635 | 0.0668 | 0.0242 | 0.0665 | 0.0806 | 0.0 | 0.0 | 0.0316 | 0.3385 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1091 | 0.6567 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1056 | 0.7089 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0045 | 0.0338 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1904 | 0.5164 | 0.0135 | 0.0154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0069 | 0.0052 | 0.0 | 0.0 | 0.0675 | 0.4757 | 0.0002 | 0.0597 | 0.0387 | 0.2618 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9927 | 0.7145 | 8150 | 2.2890 | 0.0127 | 0.0237 | 0.0121 | 0.006 | 0.0159 | 0.012 | 0.0354 | 0.0639 | 0.0673 | 0.0253 | 0.0659 | 0.0797 | 0.0 | 0.0 | 0.0341 | 0.3314 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1176 | 0.6436 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1097 | 0.7295 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0043 | 0.0385 | 0.0 | 0.0 | 0.0005 | 0.0064 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1955 | 0.5171 | 0.0129 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0695 | 0.4793 | 0.0002 | 0.0615 | 0.0408 | 0.2768 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0569 | 0.7189 | 8200 | 2.2972 | 0.0123 | 0.0236 | 0.0116 | 0.0057 | 0.0163 | 0.0113 | 0.0345 | 0.063 | 0.0664 | 0.0242 | 0.066 | 0.0784 | 0.0 | 0.0 | 0.0329 | 0.3324 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1116 | 0.6462 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1102 | 0.7191 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0033 | 0.0331 | 0.0 | 0.0 | 0.0003 | 0.0055 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1863 | 0.5059 | 0.0119 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0697 | 0.4714 | 0.0002 | 0.0597 | 0.0388 | 0.2665 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.3867 | 0.7233 | 8250 | 2.2923 | 0.0127 | 0.0239 | 0.0119 | 0.006 | 0.0166 | 0.0117 | 0.0345 | 0.0637 | 0.067 | 0.0246 | 0.067 | 0.0793 | 0.0 | 0.0 | 0.0333 | 0.3364 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.118 | 0.6529 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1095 | 0.7163 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0033 | 0.0331 | 0.0 | 0.0 | 0.0003 | 0.0055 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1926 | 0.5158 | 0.0123 | 0.0136 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.073 | 0.4783 | 0.0002 | 0.063 | 0.0406 | 0.2666 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6549 | 0.7277 | 8300 | 2.2972 | 0.0126 | 0.0238 | 0.0119 | 0.0059 | 0.0164 | 0.0116 | 0.034 | 0.0626 | 0.0657 | 0.0237 | 0.0652 | 0.0773 | 0.0 | 0.0 | 0.0337 | 0.3301 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1155 | 0.6398 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1106 | 0.7063 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0029 | 0.03 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1912 | 0.5175 | 0.0128 | 0.0131 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0746 | 0.4685 | 0.0002 | 0.0595 | 0.0393 | 0.2574 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2556 | 0.7321 | 8350 | 2.2949 | 0.0127 | 0.024 | 0.012 | 0.0061 | 0.0168 | 0.0113 | 0.0342 | 0.063 | 0.0662 | 0.0246 | 0.0656 | 0.078 | 0.0 | 0.0 | 0.0336 | 0.3375 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1142 | 0.6411 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1079 | 0.6998 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0041 | 0.03 | 0.0 | 0.0 | 0.0004 | 0.0055 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1971 | 0.5209 | 0.0146 | 0.0164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0713 | 0.473 | 0.0002 | 0.0599 | 0.0396 | 0.2615 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.4421 | 0.7365 | 8400 | 2.2933 | 0.0126 | 0.0238 | 0.0119 | 0.0059 | 0.0172 | 0.0115 | 0.0342 | 0.0633 | 0.0664 | 0.0246 | 0.066 | 0.0775 | 0.0 | 0.0 | 0.0323 | 0.3385 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1161 | 0.6484 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1073 | 0.7016 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0042 | 0.0331 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1957 | 0.5213 | 0.013 | 0.0136 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0719 | 0.4724 | 0.0002 | 0.0593 | 0.0401 | 0.2672 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2309 | 0.7408 | 8450 | 2.2843 | 0.0128 | 0.024 | 0.012 | 0.0058 | 0.0173 | 0.012 | 0.0342 | 0.064 | 0.0672 | 0.0249 | 0.0659 | 0.0797 | 0.0 | 0.0 | 0.0334 | 0.3417 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1228 | 0.6522 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1071 | 0.7167 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0041 | 0.0331 | 0.0 | 0.0 | 0.0001 | 0.0009 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1941 | 0.5219 | 0.0115 | 0.014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0753 | 0.4758 | 0.0002 | 0.0599 | 0.0409 | 0.2731 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2695 | 0.7452 | 8500 | 2.2861 | 0.0128 | 0.0243 | 0.0122 | 0.006 | 0.0169 | 0.012 | 0.0348 | 0.0639 | 0.067 | 0.0243 | 0.0665 | 0.0794 | 0.0 | 0.0 | 0.0333 | 0.3427 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1201 | 0.6548 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.109 | 0.7161 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0048 | 0.0362 | 0.0 | 0.0 | 0.0003 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1929 | 0.5121 | 0.0142 | 0.0173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0741 | 0.4731 | 0.0002 | 0.0602 | 0.0409 | 0.267 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1015 | 0.7496 | 8550 | 2.2875 | 0.013 | 0.0245 | 0.0126 | 0.006 | 0.0168 | 0.0119 | 0.0353 | 0.0641 | 0.0671 | 0.0247 | 0.0669 | 0.0782 | 0.0 | 0.0 | 0.0353 | 0.3417 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1253 | 0.6551 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1105 | 0.7096 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0048 | 0.05 | 0.0 | 0.0 | 0.0004 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1967 | 0.5134 | 0.0137 | 0.0164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0722 | 0.4744 | 0.0002 | 0.0589 | 0.0397 | 0.2628 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8313 | 0.7540 | 8600 | 2.2866 | 0.013 | 0.0243 | 0.0124 | 0.0061 | 0.017 | 0.0119 | 0.0348 | 0.0639 | 0.0671 | 0.0246 | 0.0668 | 0.0802 | 0.0 | 0.0 | 0.0341 | 0.3438 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1243 | 0.657 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1087 | 0.7033 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0051 | 0.0531 | 0.0 | 0.0 | 0.0004 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1985 | 0.5121 | 0.0143 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0723 | 0.4736 | 0.0002 | 0.0593 | 0.0389 | 0.2635 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6549 | 0.7584 | 8650 | 2.2904 | 0.0128 | 0.024 | 0.0122 | 0.006 | 0.0167 | 0.0115 | 0.0342 | 0.063 | 0.066 | 0.024 | 0.0658 | 0.077 | 0.0 | 0.0 | 0.0347 | 0.3331 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1184 | 0.6468 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1089 | 0.6992 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0042 | 0.0515 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1945 | 0.5083 | 0.0137 | 0.015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0708 | 0.465 | 0.0002 | 0.0548 | 0.0415 | 0.257 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1444 | 0.7628 | 8700 | 2.2815 | 0.0133 | 0.0248 | 0.0129 | 0.0063 | 0.0181 | 0.0119 | 0.0361 | 0.0648 | 0.0678 | 0.0252 | 0.0681 | 0.0786 | 0.0 | 0.0 | 0.0344 | 0.3436 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.126 | 0.6551 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1155 | 0.7191 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0061 | 0.0623 | 0.0 | 0.0 | 0.0006 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1968 | 0.5119 | 0.0128 | 0.0168 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0731 | 0.4747 | 0.0002 | 0.061 | 0.0407 | 0.2655 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2141 | 0.7671 | 8750 | 2.2809 | 0.0134 | 0.0249 | 0.0129 | 0.0061 | 0.0178 | 0.0122 | 0.0358 | 0.0642 | 0.0672 | 0.0248 | 0.0675 | 0.0786 | 0.0 | 0.0 | 0.034 | 0.3406 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1275 | 0.65 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1184 | 0.7161 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0055 | 0.0531 | 0.0 | 0.0 | 0.0007 | 0.0055 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1945 | 0.5073 | 0.0126 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0739 | 0.474 | 0.0002 | 0.0569 | 0.0416 | 0.266 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.544 | 0.7715 | 8800 | 2.2786 | 0.0135 | 0.0255 | 0.0128 | 0.0061 | 0.0181 | 0.0123 | 0.036 | 0.0648 | 0.0678 | 0.0254 | 0.0675 | 0.0773 | 0.0 | 0.0 | 0.0357 | 0.3417 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1278 | 0.6516 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1173 | 0.7209 | 0.0 | 0.0 | 0.0 | 0.0 | 0.007 | 0.0692 | 0.0 | 0.0 | 0.001 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1967 | 0.5086 | 0.0134 | 0.0164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0743 | 0.4749 | 0.0001 | 0.0552 | 0.039 | 0.2677 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5715 | 0.7759 | 8850 | 2.2770 | 0.0135 | 0.0251 | 0.0127 | 0.0061 | 0.0182 | 0.0123 | 0.0366 | 0.0651 | 0.0682 | 0.0259 | 0.0683 | 0.0782 | 0.0 | 0.0 | 0.035 | 0.344 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.128 | 0.6513 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1163 | 0.7222 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0074 | 0.0738 | 0.0 | 0.0 | 0.0007 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1976 | 0.5111 | 0.0126 | 0.0159 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0742 | 0.4798 | 0.0002 | 0.0576 | 0.039 | 0.2699 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.2387 | 0.7803 | 8900 | 2.2790 | 0.0135 | 0.0255 | 0.0126 | 0.0062 | 0.0181 | 0.0125 | 0.0365 | 0.0649 | 0.068 | 0.0261 | 0.0678 | 0.0798 | 0.0 | 0.0 | 0.0359 | 0.34 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1287 | 0.6471 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1152 | 0.7248 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0074 | 0.0815 | 0.0 | 0.0 | 0.0008 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1965 | 0.5105 | 0.0123 | 0.015 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0005 | 0.0099 | 0.0074 | 0.0 | 0.0 | 0.0728 | 0.4758 | 0.0002 | 0.0599 | 0.0396 | 0.2624 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5896 | 0.7847 | 8950 | 2.2772 | 0.0136 | 0.0256 | 0.013 | 0.0063 | 0.0175 | 0.0129 | 0.0368 | 0.0651 | 0.0683 | 0.0264 | 0.0686 | 0.078 | 0.0 | 0.0 | 0.0372 | 0.3373 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1335 | 0.6417 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1158 | 0.7313 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0077 | 0.0862 | 0.0 | 0.0 | 0.0008 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1972 | 0.5111 | 0.0121 | 0.0145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0743 | 0.4814 | 0.0002 | 0.0595 | 0.0385 | 0.2677 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0685 | 0.7891 | 9000 | 2.2833 | 0.0135 | 0.0254 | 0.0127 | 0.0059 | 0.0173 | 0.0131 | 0.037 | 0.0646 | 0.0678 | 0.026 | 0.0685 | 0.077 | 0.0 | 0.0 | 0.0368 | 0.3326 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1378 | 0.6414 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.118 | 0.7201 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0067 | 0.0877 | 0.0 | 0.0 | 0.0008 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1925 | 0.5052 | 0.0118 | 0.014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.07 | 0.4761 | 0.0002 | 0.0597 | 0.0397 | 0.2693 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.298 | 0.7934 | 9050 | 2.2835 | 0.0137 | 0.0255 | 0.0128 | 0.0061 | 0.017 | 0.013 | 0.037 | 0.0643 | 0.0674 | 0.0261 | 0.0672 | 0.0789 | 0.0 | 0.0 | 0.0375 | 0.3307 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1328 | 0.6331 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1187 | 0.714 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0075 | 0.0923 | 0.0 | 0.0 | 0.0008 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1948 | 0.5076 | 0.0127 | 0.014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0714 | 0.4758 | 0.0001 | 0.0586 | 0.0443 | 0.2648 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3469 | 0.7978 | 9100 | 2.2834 | 0.0137 | 0.0257 | 0.0132 | 0.0062 | 0.0173 | 0.0128 | 0.0368 | 0.0645 | 0.0675 | 0.0259 | 0.0672 | 0.0767 | 0.0 | 0.0 | 0.0373 | 0.3276 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1327 | 0.6427 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1169 | 0.7156 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0074 | 0.0923 | 0.0 | 0.0 | 0.001 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1982 | 0.5096 | 0.0133 | 0.0145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0741 | 0.4725 | 0.0001 | 0.0554 | 0.0421 | 0.2622 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.1837 | 0.8022 | 9150 | 2.2845 | 0.0137 | 0.0259 | 0.0129 | 0.0063 | 0.018 | 0.0127 | 0.0365 | 0.0644 | 0.0674 | 0.0254 | 0.0668 | 0.0772 | 0.0 | 0.0 | 0.0374 | 0.3339 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1332 | 0.643 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1163 | 0.7211 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0087 | 0.09 | 0.0 | 0.0 | 0.0012 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.196 | 0.5033 | 0.0124 | 0.014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0753 | 0.4694 | 0.0001 | 0.058 | 0.0406 | 0.257 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8285 | 0.8066 | 9200 | 2.2777 | 0.0139 | 0.026 | 0.0131 | 0.0064 | 0.0182 | 0.013 | 0.0368 | 0.0647 | 0.0679 | 0.0263 | 0.0675 | 0.0771 | 0.0 | 0.0 | 0.037 | 0.3297 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1355 | 0.6408 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1174 | 0.7222 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0087 | 0.0931 | 0.0 | 0.0 | 0.001 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2 | 0.5107 | 0.0112 | 0.014 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0775 | 0.4758 | 0.0002 | 0.0599 | 0.041 | 0.2656 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0853 | 0.8110 | 9250 | 2.2759 | 0.0138 | 0.026 | 0.0132 | 0.0062 | 0.0181 | 0.013 | 0.0367 | 0.0649 | 0.0679 | 0.026 | 0.0677 | 0.0775 | 0.0 | 0.0 | 0.0382 | 0.3333 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.133 | 0.6452 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1177 | 0.7232 | 0.0 | 0.0 | 0.0 | 0.0 | 0.008 | 0.0885 | 0.0 | 0.0 | 0.001 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1994 | 0.5061 | 0.011 | 0.0117 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0782 | 0.4826 | 0.0002 | 0.0599 | 0.0407 | 0.2641 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.2712 | 0.8154 | 9300 | 2.2727 | 0.0139 | 0.026 | 0.0134 | 0.0064 | 0.0187 | 0.013 | 0.037 | 0.0651 | 0.0681 | 0.0261 | 0.0675 | 0.0781 | 0.0 | 0.0 | 0.0385 | 0.3413 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1312 | 0.6439 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1169 | 0.7242 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0074 | 0.0831 | 0.0 | 0.0 | 0.001 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2032 | 0.5132 | 0.0113 | 0.0145 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0806 | 0.4826 | 0.0002 | 0.0578 | 0.0406 | 0.2611 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.4336 | 0.8197 | 9350 | 2.2726 | 0.0138 | 0.0257 | 0.0132 | 0.0064 | 0.0181 | 0.0126 | 0.0367 | 0.0651 | 0.0681 | 0.0263 | 0.0674 | 0.0777 | 0.0 | 0.0 | 0.0364 | 0.336 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1293 | 0.6439 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1156 | 0.7264 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0083 | 0.0869 | 0.0 | 0.0 | 0.0007 | 0.0046 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2038 | 0.5137 | 0.0108 | 0.0121 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0807 | 0.4827 | 0.0002 | 0.0612 | 0.0402 | 0.2603 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.9569 | 0.8241 | 9400 | 2.2735 | 0.0136 | 0.0255 | 0.0129 | 0.0063 | 0.018 | 0.0124 | 0.0364 | 0.0652 | 0.0682 | 0.0261 | 0.0664 | 0.078 | 0.0 | 0.0 | 0.0355 | 0.3394 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1253 | 0.6465 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1149 | 0.7313 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0072 | 0.0831 | 0.0 | 0.0 | 0.0007 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2042 | 0.5148 | 0.0115 | 0.0154 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0789 | 0.4807 | 0.0001 | 0.0563 | 0.0396 | 0.259 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5639 | 0.8285 | 9450 | 2.2715 | 0.0137 | 0.0255 | 0.0132 | 0.0064 | 0.0178 | 0.0124 | 0.0366 | 0.0654 | 0.0684 | 0.0264 | 0.0668 | 0.078 | 0.0 | 0.0 | 0.0365 | 0.3448 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1252 | 0.6475 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1142 | 0.7248 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0078 | 0.0869 | 0.0 | 0.0 | 0.0008 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2051 | 0.5168 | 0.011 | 0.0136 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0778 | 0.4824 | 0.0002 | 0.0595 | 0.0404 | 0.2595 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.3379 | 0.8329 | 9500 | 2.2704 | 0.0136 | 0.0254 | 0.0131 | 0.0064 | 0.0176 | 0.0123 | 0.0366 | 0.0653 | 0.0684 | 0.0265 | 0.0673 | 0.0776 | 0.0 | 0.0 | 0.0358 | 0.3392 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1259 | 0.6484 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1143 | 0.7274 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0075 | 0.0877 | 0.0 | 0.0 | 0.0005 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2065 | 0.5167 | 0.0104 | 0.0126 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0774 | 0.4822 | 0.0002 | 0.0623 | 0.0402 | 0.2609 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.8189 | 0.8373 | 9550 | 2.2692 | 0.0136 | 0.0254 | 0.0131 | 0.0064 | 0.0178 | 0.0122 | 0.0368 | 0.0655 | 0.0685 | 0.0264 | 0.0672 | 0.0778 | 0.0 | 0.0 | 0.0349 | 0.3385 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1256 | 0.6506 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1131 | 0.726 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0077 | 0.0869 | 0.0 | 0.0 | 0.0005 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2054 | 0.5178 | 0.0118 | 0.0164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0782 | 0.4844 | 0.0002 | 0.0606 | 0.0415 | 0.2602 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 3.0404 | 0.8417 | 9600 | 2.2710 | 0.0137 | 0.0255 | 0.0131 | 0.0063 | 0.018 | 0.0121 | 0.0367 | 0.0655 | 0.0685 | 0.0263 | 0.0671 | 0.0777 | 0.0 | 0.0 | 0.0347 | 0.3402 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1273 | 0.651 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1132 | 0.7278 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0082 | 0.0854 | 0.0 | 0.0 | 0.0005 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2049 | 0.5168 | 0.0128 | 0.0173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0783 | 0.4819 | 0.0002 | 0.06 | 0.04 | 0.26 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.9754 | 0.8460 | 9650 | 2.2730 | 0.0136 | 0.0253 | 0.013 | 0.0063 | 0.018 | 0.0121 | 0.0366 | 0.0653 | 0.0682 | 0.0261 | 0.0668 | 0.0779 | 0.0 | 0.0 | 0.0348 | 0.3415 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1261 | 0.6478 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1139 | 0.7236 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0074 | 0.0869 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2046 | 0.514 | 0.0123 | 0.0164 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0771 | 0.4787 | 0.0002 | 0.0612 | 0.0399 | 0.2588 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.088 | 0.8504 | 9700 | 2.2728 | 0.0137 | 0.0254 | 0.013 | 0.0064 | 0.0182 | 0.0121 | 0.0368 | 0.0653 | 0.0683 | 0.0264 | 0.0675 | 0.0779 | 0.0 | 0.0 | 0.0352 | 0.3419 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1271 | 0.6433 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1131 | 0.7246 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0082 | 0.0946 | 0.0 | 0.0 | 0.0005 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2047 | 0.5145 | 0.0126 | 0.0168 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0089 | 0.0067 | 0.0 | 0.0 | 0.0773 | 0.479 | 0.0002 | 0.0602 | 0.041 | 0.258 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.0154 | 0.8548 | 9750 | 2.2726 | 0.0136 | 0.0255 | 0.013 | 0.0064 | 0.0182 | 0.0122 | 0.0367 | 0.0654 | 0.0684 | 0.0263 | 0.0674 | 0.0778 | 0.0 | 0.0 | 0.0348 | 0.3383 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1259 | 0.6471 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1139 | 0.725 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0084 | 0.0946 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2044 | 0.5151 | 0.013 | 0.0178 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0772 | 0.4791 | 0.0002 | 0.06 | 0.0401 | 0.2577 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.8461 | 0.8592 | 9800 | 2.2720 | 0.0136 | 0.0254 | 0.0131 | 0.0063 | 0.0182 | 0.0121 | 0.0367 | 0.0653 | 0.0683 | 0.0264 | 0.0677 | 0.0777 | 0.0 | 0.0 | 0.0349 | 0.3379 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1262 | 0.6503 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1136 | 0.7217 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0084 | 0.0938 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2046 | 0.515 | 0.0129 | 0.0168 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0776 | 0.4799 | 0.0002 | 0.0608 | 0.04 | 0.2562 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.6359 | 0.8636 | 9850 | 2.2715 | 0.0137 | 0.0255 | 0.0131 | 0.0064 | 0.0183 | 0.0122 | 0.0366 | 0.0653 | 0.0683 | 0.0263 | 0.0674 | 0.0777 | 0.0 | 0.0 | 0.0348 | 0.3389 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1254 | 0.6455 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1144 | 0.723 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0085 | 0.0938 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2046 | 0.5153 | 0.0132 | 0.0173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0778 | 0.4799 | 0.0002 | 0.0604 | 0.0413 | 0.2569 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5484 | 0.8680 | 9900 | 2.2710 | 0.0137 | 0.0255 | 0.0131 | 0.0063 | 0.0184 | 0.0122 | 0.0366 | 0.0654 | 0.0684 | 0.0265 | 0.0677 | 0.0777 | 0.0 | 0.0 | 0.0351 | 0.3387 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.125 | 0.6484 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.114 | 0.7228 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0085 | 0.0938 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2046 | 0.5154 | 0.0132 | 0.0173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0779 | 0.4798 | 0.0002 | 0.0612 | 0.0413 | 0.258 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.5602 | 0.8723 | 9950 | 2.2719 | 0.0137 | 0.0255 | 0.0131 | 0.0063 | 0.0183 | 0.0122 | 0.0366 | 0.0653 | 0.0683 | 0.0264 | 0.0675 | 0.0776 | 0.0 | 0.0 | 0.0347 | 0.3373 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1259 | 0.6475 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1139 | 0.7228 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0085 | 0.0946 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2036 | 0.5148 | 0.0133 | 0.0173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.0779 | 0.4792 | 0.0002 | 0.0604 | 0.0417 | 0.2585 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.7095 | 0.8767 | 10000 | 2.2712 | 0.0137 | 0.0256 | 0.0131 | 0.0064 | 0.0183 | 0.0123 | 0.0366 | 0.0653 | 0.0683 | 0.0264 | 0.0676 | 0.0777 | 0.0 | 0.0 | 0.0347 | 0.3371 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1262 | 0.6475 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.1141 | 0.7232 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0086 | 0.0946 | 0.0 | 0.0 | 0.0006 | 0.0037 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2039 | 0.5147 | 0.0134 | 0.0173 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0079 | 0.0059 | 0.0 | 0.0 | 0.078 | 0.4796 | 0.0002 | 0.0606 | 0.0417 | 0.2583 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
### Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
|
huwhitememes/rfkjr-lora | huwhitememes | 2024-11-15T04:07:53Z | 5 | 1 | diffusers | [
"diffusers",
"text-to-image",
"flux",
"lora",
"template:sd-lora",
"fluxgym",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | 2024-11-15T04:06:33Z | ---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- fluxgym
widget:
- output:
url: sample/rfkjr-lora_005120_00_20241114215914.png
text: A photo of RFK Jr., RFK Jr., Robert F. Kennedy Jr.,
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: A photo of RFK Jr., RFK Jr., Robert F. Kennedy Jr.,
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# rfkjr-lora
A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)
<Gallery />
## Trigger words
You should use `A photo of RFK Jr., RFK Jr., Robert F. Kennedy Jr.,` to trigger the image generation.
## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
Weights for this model are available in Safetensors format.
|
chrysoliteop/NoName | chrysoliteop | 2024-11-15T04:07:13Z | 10 | 0 | diffusers | [
"diffusers",
"stable-diffusion",
"lora",
"text-to-image",
"en",
"base_model:stabilityai/stable-diffusion-3.5-large",
"base_model:adapter:stabilityai/stable-diffusion-3.5-large",
"region:us"
] | text-to-image | 2024-11-11T07:25:09Z | ---
language: en
pipeline_tag: text-to-image
tags:
- stable-diffusion
- diffusers
- lora
inference: true
base_model:
- stabilityai/stable-diffusion-3.5-large
trigger: Sims
instance_prompt: Sims
---
## Trigger words
You should use `Sims` to trigger the image generation.
## License
Please adhere to the licensing terms as described [here](https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md). |
gyu121791/Llama3-Dsr-Ko-3-8B | gyu121791 | 2024-11-15T04:06:22Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-11-15T04:03:44Z | ---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF | mradermacher | 2024-11-15T04:05:11Z | 54 | 1 | transformers | [
"transformers",
"gguf",
"instruct",
"finetune",
"chatml",
"axolotl",
"roleplay",
"en",
"base_model:Gryphe/Pantheon-RP-1.6.1-12b-Nemo",
"base_model:quantized:Gryphe/Pantheon-RP-1.6.1-12b-Nemo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T01:51:52Z | ---
base_model: Gryphe/Pantheon-RP-1.6.1-12b-Nemo
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- instruct
- finetune
- chatml
- axolotl
- roleplay
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Gryphe/Pantheon-RP-1.6.1-12b-Nemo
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF | mradermacher | 2024-11-15T04:05:11Z | 22 | 1 | transformers | [
"transformers",
"gguf",
"instruct",
"finetune",
"chatml",
"axolotl",
"roleplay",
"en",
"base_model:Gryphe/Pantheon-RP-1.6.1-12b-Nemo",
"base_model:quantized:Gryphe/Pantheon-RP-1.6.1-12b-Nemo",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-13T00:00:20Z | ---
base_model: Gryphe/Pantheon-RP-1.6.1-12b-Nemo
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- instruct
- finetune
- chatml
- axolotl
- roleplay
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Gryphe/Pantheon-RP-1.6.1-12b-Nemo
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q2_K.gguf) | Q2_K | 4.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q3_K_S.gguf) | Q3_K_S | 5.6 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q3_K_L.gguf) | Q3_K_L | 6.7 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.IQ4_XS.gguf) | IQ4_XS | 6.9 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q4_0_4_4.gguf) | Q4_0_4_4 | 7.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q5_K_S.gguf) | Q5_K_S | 8.6 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q5_K_M.gguf) | Q5_K_M | 8.8 | |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q6_K.gguf) | Q6_K | 10.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Pantheon-RP-1.6.1-12b-Nemo-GGUF/resolve/main/Pantheon-RP-1.6.1-12b-Nemo.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Youremi/sila555 | Youremi | 2024-11-15T03:56:47Z | 87 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | 2024-11-15T03:35:59Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: sila555
---
# Sila555
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `sila555` to trigger the image generation.
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Youremi/sila555', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
blowsnow/rare-puppers | blowsnow | 2024-11-15T03:48:39Z | 5 | 0 | null | [
"tensorboard",
"safetensors",
"vit",
"image-classification",
"pytorch",
"huggingpics",
"model-index",
"region:us"
] | image-classification | 2024-11-15T03:48:29Z | ---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: rare-puppers
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.9253731369972229
---
# rare-puppers
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### corgi
#### samoyed
#### shiba inu
 |
feizhengcong/mochi-1-preview-diffusers | feizhengcong | 2024-11-15T03:39:35Z | 10 | 5 | diffusers | [
"diffusers",
"safetensors",
"license:apache-2.0",
"diffusers:MochiPipeline",
"region:us"
] | null | 2024-10-29T10:22:36Z | ---
license: apache-2.0
---
Diffusers formation for mochi-1-preview model.
It was create by scripts: https://github.com/huggingface/diffusers/blob/main/scripts/convert_mochi_to_diffusers.py
The model can be directly load from pretrained with mochi branch: https://github.com/huggingface/diffusers/tree/mochi-t2v
You can directly use the zipped file branch in: https://huggingface.co/feizhengcong/mochi-1-preview-diffusers/blob/main/diffusers-mochi.zip
```bash
from diffusers import MochiPipeline
from diffusers.utils import export_to_video
pipe = MochiPipeline.from_pretrained(model_path, torch_dtype=torch.bfloat16)
pipe.to("cuda")
prompt = "Close-up of a chameleon's eye, with its scaly skin changing color. Ultra high resolution 4k."
frames = pipe(prompt,
num_inference_steps=50,
guidance_scale=4.5,
num_frames=61,
generator=torch.Generator(device="cuda").manual_seed(42),
).frames[0]
export_to_video(frames, "mochi.mp4")
```
Some generated results:
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/Cm3I6kidy2YP5nu3un7XP.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/bVNem7sGTvBEjxQG7MHw_.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/0YWv2KJwH_UB2WkWjO_bP.mp4"></video>
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/TOLKdMx-kFLCNXD6nIVHm.mp4"></video>
Pretty thanks for the discussion in https://github.com/huggingface/diffusers/pull/9769
11.04 updation for vae encoder releasing.
---
license: apache-2.0
--- |
bushra1dajam/AraBART | bushra1dajam | 2024-11-15T03:33:17Z | 110 | 0 | transformers | [
"transformers",
"safetensors",
"mbart",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-11-13T10:56:03Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
TheRains/llama3-8b-cpt-sahabatai-v1-instruct-Q4_K_M-GGUF | TheRains | 2024-11-15T03:03:56Z | 7 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"en",
"id",
"jv",
"su",
"base_model:GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct",
"base_model:quantized:GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-11-15T03:03:31Z | ---
base_model: GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
language:
- en
- id
- jv
- su
license: llama3
tags:
- llama-cpp
- gguf-my-repo
---
# TheRains/llama3-8b-cpt-sahabatai-v1-instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct`](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo TheRains/llama3-8b-cpt-sahabatai-v1-instruct-Q4_K_M-GGUF --hf-file llama3-8b-cpt-sahabatai-v1-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo TheRains/llama3-8b-cpt-sahabatai-v1-instruct-Q4_K_M-GGUF --hf-file llama3-8b-cpt-sahabatai-v1-instruct-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo TheRains/llama3-8b-cpt-sahabatai-v1-instruct-Q4_K_M-GGUF --hf-file llama3-8b-cpt-sahabatai-v1-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo TheRains/llama3-8b-cpt-sahabatai-v1-instruct-Q4_K_M-GGUF --hf-file llama3-8b-cpt-sahabatai-v1-instruct-q4_k_m.gguf -c 2048
```
|
mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF | mradermacher | 2024-11-15T02:59:13Z | 44 | 0 | transformers | [
"transformers",
"gguf",
"code",
"mistral",
"en",
"base_model:Nondzu/Mistral-7B-codealpaca-lora",
"base_model:quantized:Nondzu/Mistral-7B-codealpaca-lora",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2024-11-15T01:33:52Z | ---
base_model: Nondzu/Mistral-7B-codealpaca-lora
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- code
- mistral
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.2 | fast on arm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.2 | fast on arm+i8mm, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.2 | fast on arm+sve, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-codealpaca-lora-i1-GGUF/resolve/main/Mistral-7B-codealpaca-lora.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
Subsets and Splits