modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-07-16 00:42:46
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 522
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-07-16 00:42:16
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
tim-kang/dreambooth-tetraneo-tetrashapebreakwater | tim-kang | 2023-11-17T02:22:26Z | 2 | 0 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
]
| text-to-image | 2023-11-17T01:19:53Z |
---
license: openrail++
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a photo of tera shape sks breakwater
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - tim-kang/dreambooth-tetraneo-tetrashapebreakwater
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on a photo of tera shape sks breakwater using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
|
DContrerasF/a2c-PandaPickAndPlace-v3 | DContrerasF | 2023-11-17T02:19:50Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaPickAndPlace-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-17T02:14:24Z | ---
library_name: stable-baselines3
tags:
- PandaPickAndPlace-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaPickAndPlace-v3
type: PandaPickAndPlace-v3
metrics:
- type: mean_reward
value: -50.00 +/- 0.00
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaPickAndPlace-v3**
This is a trained model of a **A2C** agent playing **PandaPickAndPlace-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
crumb/qrstudy-410m-64-1 | crumb | 2023-11-17T02:12:50Z | 0 | 0 | peft | [
"peft",
"arxiv:1910.09700",
"base_model:EleutherAI/pythia-410m",
"base_model:adapter:EleutherAI/pythia-410m",
"region:us"
]
| null | 2023-11-17T02:11:55Z | ---
library_name: peft
base_model: EleutherAI/pythia-410m
---
# 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]
- **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 Data 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 Data 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.0.dev0
|
nota-ai/coreml-bk-sdm | nota-ai | 2023-11-17T02:11:20Z | 0 | 6 | null | [
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"core-ml",
"arxiv:2305.15798",
"license:creativeml-openrail-m",
"region:us"
]
| text-to-image | 2023-08-23T09:05:43Z | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- core-ml
pipeline_tag: text-to-image
extra_gated_prompt: >-
This model is open access and available to all, with a CreativeML OpenRAIL-M
license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or
harmful outputs or content
2. The authors claim no rights on the outputs you generate, you are free to
use them and are accountable for their use which must not go against the
provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as
a service. If you do, please be aware you have to include the same use
restrictions as the ones in the license and share a copy of the CreativeML
OpenRAIL-M to all your users (please read the license entirely and carefully)
Please read the full license carefully here:
https://huggingface.co/spaces/CompVis/stable-diffusion-license
extra_gated_heading: Please read the LICENSE to access this model
---
# Palettized Core ML Weights for BK-SDMs
For deployment on iOS 17 or macOS 14, this model card introduces **palettized Core ML weights** of BK-SDM-{[Base-2M](https://huggingface.co/nota-ai/bk-sdm-base-2m), [Small-2M](https://huggingface.co/nota-ai/bk-sdm-small-2m) and [Tiny-2M](https://huggingface.co/nota-ai/bk-sdm-tiny-2m)}. These weights were generated using [Apple’s repository](https://github.com/apple/ml-stable-diffusion) which has [ASCL](https://github.com/apple/ml-stable-diffusion/blob/main/LICENSE.md).
- Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) and (ii) distillation pretraining. Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge.
- More information about BK-SDMs: [Paper](https://arxiv.org/abs/2305.15798), [GitHub](https://github.com/Nota-NetsPresso/BK-SDM), [Demo]( https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion).
A demo to use Core ML Stable Diffusion weights can be found [here](https://github.com/huggingface/swift-coreml-diffusers).
## Deployment Results
| Base Model Name | Pipeline Size | Quantization Type | Attention Implementation |
|----------------------|---------------|-----------------------------------------------------------------------------------|--------------------------|
| [BK-SDM-Base-2M](https://huggingface.co/nota-ai/bk-sdm-base-2m) (Ours) | 1.48GB | [Palettized](https://coremltools.readme.io/docs/palettization-overview) | split_einsum_v2 |
| [BK-SDM-Small-2M](https://huggingface.co/nota-ai/bk-sdm-small-2m) (Ours) | 1.44GB | [Palettized](https://coremltools.readme.io/docs/palettization-overview) | split_einsum_v2 |
| [BK-SDM-Tiny-2M](https://huggingface.co/nota-ai/bk-sdm-tiny-2m) (Ours) | 1.43GB | [Palettized](https://coremltools.readme.io/docs/palettization-overview) | split_einsum_v2 |
| [OFA-Sys' Small Stable Diffusion v0](https://huggingface.co/pcuenq/coreml-small-stable-diffusion-v0) | 3.28GB | None | split_einsum |
| [Apple's Stable Diffusion v1.4, Palettized](https://huggingface.co/apple/coreml-stable-diffusion-1-4-palettized) | 1.57GB | [Palettized](https://coremltools.readme.io/docs/palettization-overview) | split_einsum_v2 |
<img src="https://huggingface.co/nota-ai/coreml-bk-sdm/resolve/main/assets/speed_comparison.gif">
## Compression Method
### U-Net Architecture
Certain residual and attention blocks were eliminated from the U-Net of SDM-v1.4:
- 1.04B-param [SDM-v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) (0.86B-param U-Net): the original source model.
- 0.76B-param [**BK-SDM-Base**](https://huggingface.co/nota-ai/bk-sdm-base) (0.58B-param U-Net): obtained with ① fewer blocks in outer stages.
- 0.66B-param [**BK-SDM-Small**](https://huggingface.co/nota-ai/bk-sdm-small) (0.49B-param U-Net): obtained with ① and ② mid-stage removal.
- 0.50B-param [**BK-SDM-Tiny**](https://huggingface.co/nota-ai/bk-sdm-tiny) (0.33B-param U-Net): obtained with ①, ②, and ③ further inner-stage removal.
<center>
<img alt="U-Net architectures" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_arch.png" width="100%">
</center>
### Distillation Pretraining
The compact U-Net was trained to mimic the behavior of the original U-Net. We leveraged feature-level and output-level distillation, along with the denoising task loss.
<center>
<img alt="KD-based pretraining" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_kd_bksdm.png" width="100%">
</center>
<br/>
# Uses
_Note: This section is taken from the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4) (which was based on the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini)) and applies in the same way to BK-SDMs_.
## Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material and is not fit for product use without additional safety mechanisms and considerations.
- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
### Safety Module
The intended use of this model is with the [Safety Checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) in Diffusers. This checker works by checking model outputs against known hard-coded NSFW concepts. The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter. Specifically, the checker compares the class probability of harmful concepts in the embedding space of the `CLIPTextModel` *after generation* of the images. The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
# Acknowledgments
- We express our gratitude to [Microsoft for Startups Founders Hub](https://www.microsoft.com/en-us/startups) for generously providing the Azure credits used during pretraining.
- We deeply appreciate the pioneering research on Latent/Stable Diffusion conducted by [CompVis](https://github.com/CompVis/latent-diffusion), [Runway](https://runwayml.com/), and [Stability AI](https://stability.ai/).
- We also appreciate the effort from [Apple](https://www.apple.com) for the [Core ML Stable Diffusion](https://github.com/apple/ml-stable-diffusion) library.
- Special thanks to the contributors to [LAION](https://laion.ai/), [Diffusers](https://github.com/huggingface/diffusers), and [Gradio](https://www.gradio.app/) for their valuable support.
# Citation
```bibtex
@article{kim2023architectural,
title={BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={arXiv preprint arXiv:2305.15798},
year={2023},
url={https://arxiv.org/abs/2305.15798}
}
```
```bibtex
@article{kim2023bksdm,
title={BK-SDM: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo)},
year={2023},
url={https://openreview.net/forum?id=bOVydU0XKC}
}
```
*This model card was written by Thibault Castells and is based on the [bk-sdm-base model card](https://huggingface.co/nota-ai/bk-sdm-base) and the [coreml-stable-diffusion-1-4-palettized model card](https://huggingface.co/apple/coreml-stable-diffusion-1-4-palettized).* |
hkivancoral/hushem_5x_deit_tiny_adamax_001_fold4 | hkivancoral | 2023-11-17T02:09:47Z | 13 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-tiny-patch16-224",
"base_model:finetune:facebook/deit-tiny-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-17T02:03:45Z | ---
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_tiny_adamax_001_fold4
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7857142857142857
---
<!-- 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. -->
# hushem_5x_deit_tiny_adamax_001_fold4
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7375
- Accuracy: 0.7857
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4656 | 1.0 | 28 | 1.3873 | 0.3095 |
| 1.2586 | 2.0 | 56 | 1.2764 | 0.5 |
| 1.1469 | 3.0 | 84 | 0.9328 | 0.5 |
| 1.0441 | 4.0 | 112 | 0.8472 | 0.5952 |
| 0.811 | 5.0 | 140 | 0.7157 | 0.6667 |
| 0.9304 | 6.0 | 168 | 1.0112 | 0.5476 |
| 0.6688 | 7.0 | 196 | 1.1025 | 0.6429 |
| 0.7046 | 8.0 | 224 | 0.9337 | 0.7143 |
| 0.6117 | 9.0 | 252 | 0.8164 | 0.7143 |
| 0.4458 | 10.0 | 280 | 0.9534 | 0.7381 |
| 0.3231 | 11.0 | 308 | 0.8226 | 0.7381 |
| 0.2594 | 12.0 | 336 | 1.4042 | 0.6905 |
| 0.3579 | 13.0 | 364 | 1.0151 | 0.6905 |
| 0.3051 | 14.0 | 392 | 1.1256 | 0.7619 |
| 0.212 | 15.0 | 420 | 1.4604 | 0.6905 |
| 0.1011 | 16.0 | 448 | 1.4776 | 0.7381 |
| 0.0658 | 17.0 | 476 | 1.5151 | 0.7143 |
| 0.0916 | 18.0 | 504 | 2.0212 | 0.6667 |
| 0.12 | 19.0 | 532 | 1.3757 | 0.7143 |
| 0.1417 | 20.0 | 560 | 1.9592 | 0.6905 |
| 0.1037 | 21.0 | 588 | 1.5184 | 0.7143 |
| 0.0812 | 22.0 | 616 | 1.5083 | 0.7381 |
| 0.0404 | 23.0 | 644 | 1.7932 | 0.7381 |
| 0.0758 | 24.0 | 672 | 1.5450 | 0.7143 |
| 0.0384 | 25.0 | 700 | 2.0953 | 0.6667 |
| 0.0277 | 26.0 | 728 | 1.9894 | 0.6667 |
| 0.0016 | 27.0 | 756 | 1.8938 | 0.7143 |
| 0.0008 | 28.0 | 784 | 1.7999 | 0.7619 |
| 0.0118 | 29.0 | 812 | 1.7512 | 0.7619 |
| 0.0001 | 30.0 | 840 | 1.8297 | 0.7619 |
| 0.0002 | 31.0 | 868 | 1.7978 | 0.7381 |
| 0.0105 | 32.0 | 896 | 1.6941 | 0.7857 |
| 0.0001 | 33.0 | 924 | 1.6973 | 0.7619 |
| 0.0 | 34.0 | 952 | 1.6981 | 0.7381 |
| 0.0 | 35.0 | 980 | 1.7026 | 0.7381 |
| 0.0 | 36.0 | 1008 | 1.7088 | 0.7619 |
| 0.0 | 37.0 | 1036 | 1.7123 | 0.7619 |
| 0.0 | 38.0 | 1064 | 1.7165 | 0.7619 |
| 0.0 | 39.0 | 1092 | 1.7201 | 0.7619 |
| 0.0 | 40.0 | 1120 | 1.7234 | 0.7619 |
| 0.0 | 41.0 | 1148 | 1.7263 | 0.7619 |
| 0.0 | 42.0 | 1176 | 1.7294 | 0.7619 |
| 0.0 | 43.0 | 1204 | 1.7316 | 0.7619 |
| 0.0 | 44.0 | 1232 | 1.7334 | 0.7857 |
| 0.0 | 45.0 | 1260 | 1.7350 | 0.7857 |
| 0.0 | 46.0 | 1288 | 1.7363 | 0.7857 |
| 0.0 | 47.0 | 1316 | 1.7371 | 0.7857 |
| 0.0 | 48.0 | 1344 | 1.7375 | 0.7857 |
| 0.0 | 49.0 | 1372 | 1.7375 | 0.7857 |
| 0.0 | 50.0 | 1400 | 1.7375 | 0.7857 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
nota-ai/bk-sdm-small | nota-ai | 2023-11-17T02:04:25Z | 793 | 30 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dataset:ChristophSchuhmann/improved_aesthetics_6.5plus",
"arxiv:2305.15798",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-11T05:02:39Z | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
datasets:
- ChristophSchuhmann/improved_aesthetics_6.5plus
library_name: diffusers
pipeline_tag: text-to-image
extra_gated_prompt: >-
This model is open access and available to all, with a CreativeML OpenRAIL-M
license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or
harmful outputs or content
2. The authors claim no rights on the outputs you generate, you are free to
use them and are accountable for their use which must not go against the
provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as
a service. If you do, please be aware you have to include the same use
restrictions as the ones in the license and share a copy of the CreativeML
OpenRAIL-M to all your users (please read the license entirely and carefully)
Please read the full license carefully here:
https://huggingface.co/spaces/CompVis/stable-diffusion-license
extra_gated_heading: Please read the LICENSE to access this model
---
# BK-SDM Model Card
Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient general-purpose text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge.
- **Resources for more information**: [Paper](https://arxiv.org/abs/2305.15798), [GitHub](https://github.com/Nota-NetsPresso/BK-SDM), [Demo]( https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion).
## Examples with 🤗[Diffusers library](https://github.com/huggingface/diffusers).
An inference code with the default PNDM scheduler and 50 denoising steps is as follows.
```python
import torch
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("nota-ai/bk-sdm-small", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a tropical bird sitting on a branch of a tree"
image = pipe(prompt).images[0]
image.save("example.png")
```
The following code is also runnable, because we compressed the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) while keeping the other parts (i.e., Text Encoder and Image Decoder) unchanged:
```python
import torch
from diffusers import StableDiffusionPipeline, UNet2DConditionModel
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipe.unet = UNet2DConditionModel.from_pretrained("nota-ai/bk-sdm-small", subfolder="unet", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a tropical bird sitting on a branch of a tree"
image = pipe(prompt).images[0]
image.save("example.png")
```
## Compression Method
### U-Net Architecture
Certain residual and attention blocks were eliminated from the U-Net of SDM-v1.4:
- 1.04B-param [SDM-v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) (0.86B-param U-Net): the original source model.
- 0.76B-param [**BK-SDM-Base**](https://huggingface.co/nota-ai/bk-sdm-base) (0.58B-param U-Net): obtained with ① fewer blocks in outer stages.
- 0.66B-param [**BK-SDM-Small**](https://huggingface.co/nota-ai/bk-sdm-small) (0.49B-param U-Net): obtained with ① and ② mid-stage removal.
- 0.50B-param [**BK-SDM-Tiny**](https://huggingface.co/nota-ai/bk-sdm-tiny) (0.33B-param U-Net): obtained with ①, ②, and ③ further inner-stage removal.
<center>
<img alt="U-Net architectures" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_arch.png" width="100%">
</center>
### Distillation Pretraining
The compact U-Net was trained to mimic the behavior of the original U-Net. We leveraged feature-level and output-level distillation, along with the denoising task loss.
<center>
<img alt="KD-based pretraining" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_kd_bksdm.png" width="100%">
</center>
<br/>
- **Training Data**: 212,776 image-text pairs (i.e., 0.22M pairs) from [LAION-Aesthetics V2 6.5+](https://laion.ai/blog/laion-aesthetics/).
- **Hardware:** A single NVIDIA A100 80GB GPU
- **Gradient Accumulations**: 4
- **Batch:** 256 (=4×64)
- **Optimizer:** AdamW
- **Learning Rate:** a constant learning rate of 5e-5 for 50K-iteration pretraining
## Experimental Results
The following table shows the zero-shot results on 30K samples from the MS-COCO validation split. After generating 512×512 images with the PNDM scheduler and 25 denoising steps, we downsampled them to 256×256 for evaluating generation scores. Our models were drawn at the 50K-th training iteration.
| Model | FID↓ | IS↑ | CLIP Score↑<br>(ViT-g/14) | # Params,<br>U-Net | # Params,<br>Whole SDM |
|---|:---:|:---:|:---:|:---:|:---:|
| [Stable Diffusion v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) | 13.05 | 36.76 | 0.2958 | 0.86B | 1.04B |
| [BK-SDM-Base](https://huggingface.co/nota-ai/bk-sdm-base) (Ours) | 15.76 | 33.79 | 0.2878 | 0.58B | 0.76B |
| [BK-SDM-Small](https://huggingface.co/nota-ai/bk-sdm-small) (Ours) | 16.98 | 31.68 | 0.2677 | 0.49B | 0.66B |
| [BK-SDM-Tiny](https://huggingface.co/nota-ai/bk-sdm-tiny) (Ours) | 17.12 | 30.09 | 0.2653 | 0.33B | 0.50B |
<br/>
The following figure depicts synthesized images with some MS-COCO captions.
<center>
<img alt="Visual results" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_results.png" width="100%">
</center>
<br/>
# Uses
_Note: This section is taken from the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4) (which was based on the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini)) and applies in the same way to BK-SDMs_.
## Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material and is not fit for product use without additional safety mechanisms and considerations.
- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
### Safety Module
The intended use of this model is with the [Safety Checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) in Diffusers. This checker works by checking model outputs against known hard-coded NSFW concepts. The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter. Specifically, the checker compares the class probability of harmful concepts in the embedding space of the `CLIPTextModel` *after generation* of the images. The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
# Acknowledgments
- We express our gratitude to [Microsoft for Startups Founders Hub](https://www.microsoft.com/en-us/startups) for generously providing the Azure credits used during pretraining.
- We deeply appreciate the pioneering research on Latent/Stable Diffusion conducted by [CompVis](https://github.com/CompVis/latent-diffusion), [Runway](https://runwayml.com/), and [Stability AI](https://stability.ai/).
- Special thanks to the contributors to [LAION](https://laion.ai/), [Diffusers](https://github.com/huggingface/diffusers), and [Gradio](https://www.gradio.app/) for their valuable support.
# Citation
```bibtex
@article{kim2023architectural,
title={BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={arXiv preprint arXiv:2305.15798},
year={2023},
url={https://arxiv.org/abs/2305.15798}
}
```
```bibtex
@article{kim2023bksdm,
title={BK-SDM: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo)},
year={2023},
url={https://openreview.net/forum?id=bOVydU0XKC}
}
```
*This model card was written by Bo-Kyeong Kim and is based on the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4).* |
nota-ai/bk-sdm-base | nota-ai | 2023-11-17T02:03:55Z | 261 | 19 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dataset:ChristophSchuhmann/improved_aesthetics_6.5plus",
"arxiv:2305.15798",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
]
| text-to-image | 2023-07-10T06:50:32Z | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
datasets:
- ChristophSchuhmann/improved_aesthetics_6.5plus
library_name: diffusers
pipeline_tag: text-to-image
extra_gated_prompt: >-
This model is open access and available to all, with a CreativeML OpenRAIL-M
license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or
harmful outputs or content
2. The authors claim no rights on the outputs you generate, you are free to
use them and are accountable for their use which must not go against the
provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as
a service. If you do, please be aware you have to include the same use
restrictions as the ones in the license and share a copy of the CreativeML
OpenRAIL-M to all your users (please read the license entirely and carefully)
Please read the full license carefully here:
https://huggingface.co/spaces/CompVis/stable-diffusion-license
extra_gated_heading: Please read the LICENSE to access this model
---
# BK-SDM Model Card
Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient general-purpose text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge.
- **Resources for more information**: [Paper](https://arxiv.org/abs/2305.15798), [GitHub](https://github.com/Nota-NetsPresso/BK-SDM), [Demo]( https://huggingface.co/spaces/nota-ai/compressed-stable-diffusion).
## Examples with 🤗[Diffusers library](https://github.com/huggingface/diffusers).
An inference code with the default PNDM scheduler and 50 denoising steps is as follows.
```python
import torch
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("nota-ai/bk-sdm-base", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a tropical bird sitting on a branch of a tree"
image = pipe(prompt).images[0]
image.save("example.png")
```
The following code is also runnable, because we compressed the U-Net of [Stable Diffusion v1.4]( https://huggingface.co/CompVis/stable-diffusion-v1-4) while keeping the other parts (i.e., Text Encoder and Image Decoder) unchanged:
```python
import torch
from diffusers import StableDiffusionPipeline, UNet2DConditionModel
pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipe.unet = UNet2DConditionModel.from_pretrained("nota-ai/bk-sdm-base", subfolder="unet", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a tropical bird sitting on a branch of a tree"
image = pipe(prompt).images[0]
image.save("example.png")
```
## Compression Method
### U-Net Architecture
Certain residual and attention blocks were eliminated from the U-Net of SDM-v1.4:
- 1.04B-param [SDM-v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) (0.86B-param U-Net): the original source model.
- 0.76B-param [**BK-SDM-Base**](https://huggingface.co/nota-ai/bk-sdm-base) (0.58B-param U-Net): obtained with ① fewer blocks in outer stages.
- 0.66B-param [**BK-SDM-Small**](https://huggingface.co/nota-ai/bk-sdm-small) (0.49B-param U-Net): obtained with ① and ② mid-stage removal.
- 0.50B-param [**BK-SDM-Tiny**](https://huggingface.co/nota-ai/bk-sdm-tiny) (0.33B-param U-Net): obtained with ①, ②, and ③ further inner-stage removal.
<center>
<img alt="U-Net architectures" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_arch.png" width="100%">
</center>
### Distillation Pretraining
The compact U-Net was trained to mimic the behavior of the original U-Net. We leveraged feature-level and output-level distillation, along with the denoising task loss.
<center>
<img alt="KD-based pretraining" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_kd_bksdm.png" width="100%">
</center>
<br/>
- **Training Data**: 212,776 image-text pairs (i.e., 0.22M pairs) from [LAION-Aesthetics V2 6.5+](https://laion.ai/blog/laion-aesthetics/).
- **Hardware:** A single NVIDIA A100 80GB GPU
- **Gradient Accumulations**: 4
- **Batch:** 256 (=4×64)
- **Optimizer:** AdamW
- **Learning Rate:** a constant learning rate of 5e-5 for 50K-iteration pretraining
## Experimental Results
The following table shows the zero-shot results on 30K samples from the MS-COCO validation split. After generating 512×512 images with the PNDM scheduler and 25 denoising steps, we downsampled them to 256×256 for evaluating generation scores. Our models were drawn at the 50K-th training iteration.
| Model | FID↓ | IS↑ | CLIP Score↑<br>(ViT-g/14) | # Params,<br>U-Net | # Params,<br>Whole SDM |
|---|:---:|:---:|:---:|:---:|:---:|
| [Stable Diffusion v1.4](https://huggingface.co/CompVis/stable-diffusion-v1-4) | 13.05 | 36.76 | 0.2958 | 0.86B | 1.04B |
| [BK-SDM-Base](https://huggingface.co/nota-ai/bk-sdm-base) (Ours) | 15.76 | 33.79 | 0.2878 | 0.58B | 0.76B |
| [BK-SDM-Small](https://huggingface.co/nota-ai/bk-sdm-small) (Ours) | 16.98 | 31.68 | 0.2677 | 0.49B | 0.66B |
| [BK-SDM-Tiny](https://huggingface.co/nota-ai/bk-sdm-tiny) (Ours) | 17.12 | 30.09 | 0.2653 | 0.33B | 0.50B |
<br/>
The following figure depicts synthesized images with some MS-COCO captions.
<center>
<img alt="Visual results" img src="https://netspresso-research-code-release.s3.us-east-2.amazonaws.com/assets-bk-sdm/fig_results.png" width="100%">
</center>
<br/>
# Uses
_Note: This section is taken from the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4) (which was based on the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini)) and applies in the same way to BK-SDMs_.
## Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a large-scale dataset [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material and is not fit for product use without additional safety mechanisms and considerations.
- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
### Safety Module
The intended use of this model is with the [Safety Checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) in Diffusers. This checker works by checking model outputs against known hard-coded NSFW concepts. The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter. Specifically, the checker compares the class probability of harmful concepts in the embedding space of the `CLIPTextModel` *after generation* of the images. The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
# Acknowledgments
- We express our gratitude to [Microsoft for Startups Founders Hub](https://www.microsoft.com/en-us/startups) for generously providing the Azure credits used during pretraining.
- We deeply appreciate the pioneering research on Latent/Stable Diffusion conducted by [CompVis](https://github.com/CompVis/latent-diffusion), [Runway](https://runwayml.com/), and [Stability AI](https://stability.ai/).
- Special thanks to the contributors to [LAION](https://laion.ai/), [Diffusers](https://github.com/huggingface/diffusers), and [Gradio](https://www.gradio.app/) for their valuable support.
# Citation
```bibtex
@article{kim2023architectural,
title={BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={arXiv preprint arXiv:2305.15798},
year={2023},
url={https://arxiv.org/abs/2305.15798}
}
```
```bibtex
@article{kim2023bksdm,
title={BK-SDM: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation},
author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
journal={ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo)},
year={2023},
url={https://openreview.net/forum?id=bOVydU0XKC}
}
```
*This model card was written by Bo-Kyeong Kim and is based on the [Stable Diffusion v1 model card]( https://huggingface.co/CompVis/stable-diffusion-v1-4).* |
Gxl/sda | Gxl | 2023-11-17T01:58:01Z | 0 | 0 | null | [
"generated_from_trainer",
"en",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"arxiv:2305.18290",
"arxiv:2310.16944",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:finetune:mistralai/Mistral-7B-v0.1",
"license:mit",
"region:us"
]
| null | 2022-09-07T12:43:03Z | ---
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-beta
results: []
license: mit
datasets:
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
base_model: mistralai/Mistral-7B-v0.1
---
<!-- 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. -->
<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# Model Card for Zephyr 7B β
Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so and should only be used for educational and research purposes. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
## Model description
- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily English
- **License:** MIT
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/huggingface/alignment-handbook
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
- **Chatbot Arena:** Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org
## Performance
At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks:
| Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
|-------------|-----|----|---------------|--------------|
| StableLM-Tuned-α | 7B| dSFT |2.75| -|
| MPT-Chat | 7B |dSFT |5.42| -|
| Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
| Mistral-Instructv0.1 | 7B| - | 6.84 |-|
| Zephyr-7b-α |7B| dDPO| 6.88| -|
| **Zephyr-7b-β** 🪁 | **7B** | **dDPO** | **7.34** | **90.60** |
| Falcon-Instruct | 40B |dSFT |5.17 |45.71|
| Guanaco | 65B | SFT |6.41| 71.80|
| Llama2-Chat | 70B |RLHF |6.86| 92.66|
| Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
| WizardLM v1.0 | 70B |dSFT |7.71 |-|
| Xwin-LM v0.1 | 70B |dPPO |- |95.57|
| GPT-3.5-turbo | - |RLHF |7.94 |89.37|
| Claude 2 | - |RLHF |8.06| 91.36|
| GPT-4 | -| RLHF |8.99| 95.28| |
hkivancoral/hushem_5x_deit_tiny_adamax_001_fold2 | hkivancoral | 2023-11-17T01:57:13Z | 13 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-tiny-patch16-224",
"base_model:finetune:facebook/deit-tiny-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-17T01:51:18Z | ---
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_tiny_adamax_001_fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.4666666666666667
---
<!-- 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. -->
# hushem_5x_deit_tiny_adamax_001_fold2
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 5.5945
- Accuracy: 0.4667
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3843 | 1.0 | 27 | 1.6047 | 0.2667 |
| 1.3126 | 2.0 | 54 | 1.5540 | 0.2889 |
| 1.242 | 3.0 | 81 | 1.7659 | 0.2889 |
| 1.2292 | 4.0 | 108 | 1.5553 | 0.2667 |
| 1.1861 | 5.0 | 135 | 1.3959 | 0.2889 |
| 0.9837 | 6.0 | 162 | 1.3509 | 0.4889 |
| 0.9151 | 7.0 | 189 | 1.3189 | 0.3778 |
| 0.8428 | 8.0 | 216 | 1.2233 | 0.4444 |
| 0.6366 | 9.0 | 243 | 1.6296 | 0.5556 |
| 0.6056 | 10.0 | 270 | 2.1707 | 0.5333 |
| 0.6193 | 11.0 | 297 | 2.2637 | 0.5333 |
| 0.419 | 12.0 | 324 | 2.6815 | 0.4444 |
| 0.4931 | 13.0 | 351 | 1.6615 | 0.4444 |
| 0.4945 | 14.0 | 378 | 2.3385 | 0.4444 |
| 0.4035 | 15.0 | 405 | 2.2795 | 0.4889 |
| 0.2803 | 16.0 | 432 | 2.9683 | 0.5556 |
| 0.3104 | 17.0 | 459 | 3.6455 | 0.4222 |
| 0.2085 | 18.0 | 486 | 3.8509 | 0.5778 |
| 0.3092 | 19.0 | 513 | 2.7832 | 0.5333 |
| 0.2911 | 20.0 | 540 | 3.5970 | 0.4667 |
| 0.1508 | 21.0 | 567 | 2.8494 | 0.4 |
| 0.1872 | 22.0 | 594 | 3.4606 | 0.5111 |
| 0.1634 | 23.0 | 621 | 3.9940 | 0.5778 |
| 0.0282 | 24.0 | 648 | 4.2310 | 0.4667 |
| 0.0886 | 25.0 | 675 | 3.4801 | 0.4889 |
| 0.1057 | 26.0 | 702 | 3.6632 | 0.4222 |
| 0.0893 | 27.0 | 729 | 3.7806 | 0.5556 |
| 0.0108 | 28.0 | 756 | 4.5566 | 0.5556 |
| 0.1095 | 29.0 | 783 | 4.2488 | 0.5556 |
| 0.0164 | 30.0 | 810 | 4.4510 | 0.5556 |
| 0.0017 | 31.0 | 837 | 4.8182 | 0.5333 |
| 0.0006 | 32.0 | 864 | 5.4595 | 0.5333 |
| 0.0034 | 33.0 | 891 | 5.3273 | 0.5556 |
| 0.0036 | 34.0 | 918 | 4.8258 | 0.4889 |
| 0.0002 | 35.0 | 945 | 5.5297 | 0.5111 |
| 0.0007 | 36.0 | 972 | 5.4553 | 0.4667 |
| 0.0081 | 37.0 | 999 | 5.5834 | 0.5333 |
| 0.0001 | 38.0 | 1026 | 5.4059 | 0.5333 |
| 0.0001 | 39.0 | 1053 | 5.7543 | 0.4667 |
| 0.0 | 40.0 | 1080 | 5.5912 | 0.4667 |
| 0.0 | 41.0 | 1107 | 5.5774 | 0.4667 |
| 0.0 | 42.0 | 1134 | 5.5838 | 0.4667 |
| 0.0 | 43.0 | 1161 | 5.5882 | 0.4667 |
| 0.0 | 44.0 | 1188 | 5.5908 | 0.4667 |
| 0.0 | 45.0 | 1215 | 5.5928 | 0.4667 |
| 0.0 | 46.0 | 1242 | 5.5933 | 0.4667 |
| 0.0 | 47.0 | 1269 | 5.5942 | 0.4667 |
| 0.0 | 48.0 | 1296 | 5.5945 | 0.4667 |
| 0.0 | 49.0 | 1323 | 5.5945 | 0.4667 |
| 0.0 | 50.0 | 1350 | 5.5945 | 0.4667 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
PCYP/dqn-SpaceInvadersNoFrameskip-v4 | PCYP | 2023-11-17T01:55:07Z | 1 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-15T01:01:32Z | ---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 732.00 +/- 245.19
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga PCYP -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga PCYP -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga PCYP
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 5000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
MayIBorn/rte_qlora-llama7b_initialize_dW_A | MayIBorn | 2023-11-17T01:51:37Z | 2 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:huggyllama/llama-7b",
"base_model:adapter:huggyllama/llama-7b",
"region:us"
]
| null | 2023-11-17T01:51:32Z | ---
library_name: peft
base_model: huggyllama/llama-7b
---
# 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]
- **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 Data 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 Data 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.7.0.dev0
|
hkivancoral/hushem_5x_deit_tiny_adamax_001_fold1 | hkivancoral | 2023-11-17T01:51:02Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-tiny-patch16-224",
"base_model:finetune:facebook/deit-tiny-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-17T01:45:07Z | ---
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_tiny_adamax_001_fold1
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.4222222222222222
---
<!-- 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. -->
# hushem_5x_deit_tiny_adamax_001_fold1
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 5.8123
- Accuracy: 0.4222
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3956 | 1.0 | 27 | 1.9737 | 0.3111 |
| 0.888 | 2.0 | 54 | 1.5910 | 0.3556 |
| 1.1183 | 3.0 | 81 | 1.4091 | 0.3778 |
| 0.7709 | 4.0 | 108 | 1.4706 | 0.3778 |
| 0.9892 | 5.0 | 135 | 1.4916 | 0.4222 |
| 0.5847 | 6.0 | 162 | 2.0869 | 0.3778 |
| 0.6569 | 7.0 | 189 | 1.9470 | 0.3556 |
| 0.5263 | 8.0 | 216 | 1.6436 | 0.4 |
| 0.46 | 9.0 | 243 | 2.3342 | 0.3556 |
| 0.4825 | 10.0 | 270 | 1.8564 | 0.4222 |
| 0.3607 | 11.0 | 297 | 2.1004 | 0.4222 |
| 0.2444 | 12.0 | 324 | 2.4392 | 0.4222 |
| 0.3872 | 13.0 | 351 | 1.8032 | 0.4444 |
| 0.3209 | 14.0 | 378 | 2.9763 | 0.4 |
| 0.1884 | 15.0 | 405 | 2.8695 | 0.4667 |
| 0.1329 | 16.0 | 432 | 3.4787 | 0.4 |
| 0.2021 | 17.0 | 459 | 2.9858 | 0.4 |
| 0.1653 | 18.0 | 486 | 3.6825 | 0.4667 |
| 0.0813 | 19.0 | 513 | 3.2825 | 0.4444 |
| 0.1467 | 20.0 | 540 | 3.0809 | 0.4889 |
| 0.0538 | 21.0 | 567 | 3.9816 | 0.4222 |
| 0.1511 | 22.0 | 594 | 3.9404 | 0.4444 |
| 0.0505 | 23.0 | 621 | 4.4773 | 0.4667 |
| 0.0602 | 24.0 | 648 | 3.6484 | 0.4222 |
| 0.0403 | 25.0 | 675 | 4.0392 | 0.4444 |
| 0.005 | 26.0 | 702 | 3.8791 | 0.5556 |
| 0.0725 | 27.0 | 729 | 5.2091 | 0.4222 |
| 0.0084 | 28.0 | 756 | 4.7587 | 0.4222 |
| 0.0002 | 29.0 | 783 | 5.6091 | 0.3778 |
| 0.0001 | 30.0 | 810 | 5.5834 | 0.4222 |
| 0.0004 | 31.0 | 837 | 5.1075 | 0.4 |
| 0.0002 | 32.0 | 864 | 5.0938 | 0.4667 |
| 0.0014 | 33.0 | 891 | 5.4645 | 0.4667 |
| 0.0 | 34.0 | 918 | 5.9402 | 0.4222 |
| 0.0 | 35.0 | 945 | 5.8799 | 0.4222 |
| 0.0 | 36.0 | 972 | 5.8415 | 0.4222 |
| 0.0 | 37.0 | 999 | 5.8263 | 0.4222 |
| 0.0 | 38.0 | 1026 | 5.8129 | 0.4222 |
| 0.0 | 39.0 | 1053 | 5.8088 | 0.4222 |
| 0.0 | 40.0 | 1080 | 5.8085 | 0.4222 |
| 0.0 | 41.0 | 1107 | 5.8075 | 0.4222 |
| 0.0 | 42.0 | 1134 | 5.8084 | 0.4222 |
| 0.0 | 43.0 | 1161 | 5.8094 | 0.4222 |
| 0.0 | 44.0 | 1188 | 5.8109 | 0.4222 |
| 0.0 | 45.0 | 1215 | 5.8113 | 0.4222 |
| 0.0 | 46.0 | 1242 | 5.8120 | 0.4222 |
| 0.0 | 47.0 | 1269 | 5.8119 | 0.4222 |
| 0.0 | 48.0 | 1296 | 5.8123 | 0.4222 |
| 0.0 | 49.0 | 1323 | 5.8123 | 0.4222 |
| 0.0 | 50.0 | 1350 | 5.8123 | 0.4222 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
choihkk/nsf-hifigan | choihkk | 2023-11-17T01:28:22Z | 4 | 2 | transformers | [
"transformers",
"license:agpl-3.0",
"endpoints_compatible",
"region:us"
]
| null | 2023-11-17T01:24:17Z | ---
license: agpl-3.0
---
This model was uploaded following the guidance provided by OpenVPI, and when redistributing,
you should reconfirm once again through the link attached below before deployment.
https://github.com/openvpi/vocoders/blob/main/index.md
https://openvpi.github.io/vocoders/
|
DContrerasF/a2c-PandaReachDense-v3 | DContrerasF | 2023-11-17T01:19:30Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-17T01:13:51Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v3
type: PandaReachDense-v3
metrics:
- type: mean_reward
value: -0.18 +/- 0.10
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
hkivancoral/hushem_5x_deit_small_adamax_00001_fold3 | hkivancoral | 2023-11-17T01:14:39Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-small-patch16-224",
"base_model:finetune:facebook/deit-small-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-17T01:03:15Z | ---
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_adamax_00001_fold3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9069767441860465
---
<!-- 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. -->
# hushem_5x_deit_small_adamax_00001_fold3
This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4351
- Accuracy: 0.9070
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3047 | 1.0 | 28 | 1.2727 | 0.3023 |
| 0.9947 | 2.0 | 56 | 1.1088 | 0.5116 |
| 0.6975 | 3.0 | 84 | 1.0336 | 0.5814 |
| 0.5355 | 4.0 | 112 | 0.9195 | 0.6047 |
| 0.3827 | 5.0 | 140 | 0.8325 | 0.6279 |
| 0.3 | 6.0 | 168 | 0.7235 | 0.7674 |
| 0.2132 | 7.0 | 196 | 0.6638 | 0.7209 |
| 0.1664 | 8.0 | 224 | 0.5923 | 0.7674 |
| 0.1004 | 9.0 | 252 | 0.5516 | 0.7674 |
| 0.0697 | 10.0 | 280 | 0.5067 | 0.7907 |
| 0.0474 | 11.0 | 308 | 0.5078 | 0.7674 |
| 0.0278 | 12.0 | 336 | 0.5312 | 0.7907 |
| 0.0177 | 13.0 | 364 | 0.4466 | 0.8372 |
| 0.0105 | 14.0 | 392 | 0.4059 | 0.8837 |
| 0.0066 | 15.0 | 420 | 0.4235 | 0.8372 |
| 0.005 | 16.0 | 448 | 0.4260 | 0.8372 |
| 0.0043 | 17.0 | 476 | 0.4042 | 0.8605 |
| 0.0033 | 18.0 | 504 | 0.4280 | 0.8605 |
| 0.003 | 19.0 | 532 | 0.4100 | 0.8837 |
| 0.0024 | 20.0 | 560 | 0.4096 | 0.9070 |
| 0.0023 | 21.0 | 588 | 0.4113 | 0.9070 |
| 0.002 | 22.0 | 616 | 0.4075 | 0.9070 |
| 0.0019 | 23.0 | 644 | 0.4099 | 0.9070 |
| 0.0015 | 24.0 | 672 | 0.4158 | 0.9070 |
| 0.0014 | 25.0 | 700 | 0.4120 | 0.9070 |
| 0.0015 | 26.0 | 728 | 0.4156 | 0.9070 |
| 0.0013 | 27.0 | 756 | 0.4154 | 0.9070 |
| 0.0013 | 28.0 | 784 | 0.4244 | 0.9070 |
| 0.0012 | 29.0 | 812 | 0.4172 | 0.9070 |
| 0.0012 | 30.0 | 840 | 0.4177 | 0.9070 |
| 0.0011 | 31.0 | 868 | 0.4272 | 0.9070 |
| 0.0011 | 32.0 | 896 | 0.4248 | 0.9070 |
| 0.001 | 33.0 | 924 | 0.4242 | 0.9070 |
| 0.001 | 34.0 | 952 | 0.4262 | 0.9070 |
| 0.0012 | 35.0 | 980 | 0.4213 | 0.9070 |
| 0.0009 | 36.0 | 1008 | 0.4193 | 0.9302 |
| 0.0009 | 37.0 | 1036 | 0.4299 | 0.9302 |
| 0.0008 | 38.0 | 1064 | 0.4330 | 0.9070 |
| 0.0008 | 39.0 | 1092 | 0.4363 | 0.9070 |
| 0.0009 | 40.0 | 1120 | 0.4311 | 0.9070 |
| 0.0008 | 41.0 | 1148 | 0.4367 | 0.9070 |
| 0.0008 | 42.0 | 1176 | 0.4356 | 0.9070 |
| 0.0008 | 43.0 | 1204 | 0.4345 | 0.9070 |
| 0.0008 | 44.0 | 1232 | 0.4348 | 0.9070 |
| 0.0007 | 45.0 | 1260 | 0.4351 | 0.9070 |
| 0.0007 | 46.0 | 1288 | 0.4351 | 0.9070 |
| 0.0007 | 47.0 | 1316 | 0.4349 | 0.9070 |
| 0.0007 | 48.0 | 1344 | 0.4351 | 0.9070 |
| 0.0007 | 49.0 | 1372 | 0.4351 | 0.9070 |
| 0.0007 | 50.0 | 1400 | 0.4351 | 0.9070 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
wefussell/amasum-pos-model | wefussell | 2023-11-17T01:09:08Z | 1 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
]
| null | 2023-11-17T00:58:12Z | ---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
---
# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
|
TheBloke/platypus-yi-34b-GPTQ | TheBloke | 2023-11-17T01:05:48Z | 28 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:garage-bAInd/Open-Platypus",
"base_model:bhenrym14/platypus-yi-34b",
"base_model:quantized:bhenrym14/platypus-yi-34b",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
]
| text-generation | 2023-11-16T23:05:22Z | ---
base_model: bhenrym14/platypus-yi-34b
datasets:
- garage-bAInd/Open-Platypus
inference: false
license: other
license_link: LICENSE
license_name: yi-license
model_creator: Brandon
model_name: Platypus Yi 34B
model_type: llama
prompt_template: "A chat.\nUSER: {prompt}\nASSISTANT: \n"
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Platypus Yi 34B - GPTQ
- Model creator: [Brandon](https://huggingface.co/bhenrym14)
- Original model: [Platypus Yi 34B](https://huggingface.co/bhenrym14/platypus-yi-34b)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Brandon's Platypus Yi 34B](https://huggingface.co/bhenrym14/platypus-yi-34b).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/platypus-yi-34b-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/platypus-yi-34b-GGUF)
* [Brandon's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bhenrym14/platypus-yi-34b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Chat
```
A chat.
USER: {prompt}
ASSISTANT:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Brandon's Platypus Yi 34B](https://huggingface.co/bhenrym14/platypus-yi-34b).
<!-- licensing end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
These GPTQ models are known to work in the following inference servers/webuis.
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
- [KoboldAI United](https://github.com/henk717/koboldai)
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
This may not be a complete list; if you know of others, please let me know!
<!-- README_GPTQ.md-compatible clients end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 18.60 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 19.25 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 21.21 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 15.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 35.34 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-3bit-32g-actorder_True](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/gptq-3bit-32g-actorder_True) | 3 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 16.90 GB | No | 3-bit, with group size 64g and act-order. Highest quality 3-bit option. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 36.11 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/platypus-yi-34b-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/platypus-yi-34b-GPTQ:gptq-4bit-128g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `platypus-yi-34b-GPTQ`:
```shell
mkdir platypus-yi-34b-GPTQ
huggingface-cli download TheBloke/platypus-yi-34b-GPTQ --local-dir platypus-yi-34b-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir platypus-yi-34b-GPTQ
huggingface-cli download TheBloke/platypus-yi-34b-GPTQ --revision gptq-4bit-128g-actorder_True --local-dir platypus-yi-34b-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir platypus-yi-34b-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/platypus-yi-34b-GPTQ --local-dir platypus-yi-34b-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-128g-actorder_True https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/platypus-yi-34b-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/platypus-yi-34b-GPTQ:gptq-4bit-128g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `platypus-yi-34b-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/platypus-yi-34b-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''A chat.
USER: {prompt}
ASSISTANT:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## Python code example: inference from this GPTQ model
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install --upgrade transformers optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
```
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.5.1
pip3 install .
```
### Example Python code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/platypus-yi-34b-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-128g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''A chat.
USER: {prompt}
ASSISTANT:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Brandon's Platypus Yi 34B
# Instruction tune of Yi-34b with Open-Platypus (fp16)
## Overview
This is [chargoddard/Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama), with instruction tuning performed with the [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus) dataset. That base model is [01-ai/Yi-34B](https://huggingface.co/01-ai/Yi-34B), but using llama2 model definitions and tokenizer to remove any remote code requirements.
**This is a (merged) QLoRA fine-tune (rank 64)**.
The finetune was performed with 1x RTX 6000 Ada (~18 hours to this checkpoint). It is possible this is rather undertrained, as this checkpoint is at 1 epoch. I began to see some performance degradation after that; more hyperparameter tuning is probably warranted.
## How to Use
Use as you would any llama-2 model.
## Prompting:
Model was trained with legacy airoboros <2.0 system prompt. See [bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16) model card for details.
|
stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-4 | stefan-it | 2023-11-17T00:52:26Z | 6 | 0 | flair | [
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"en",
"ka",
"base_model:FacebookAI/xlm-roberta-large",
"base_model:finetune:FacebookAI/xlm-roberta-large",
"license:mit",
"region:us"
]
| token-classification | 2023-11-16T08:52:58Z | ---
language:
- en
- ka
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: xlm-roberta-large
widget:
- text: ამით თავისი ქადაგება დაასრულა და დაბრუნდა იერუსალიმში . ერთ-ერთ გარე კედელზე
არსებობს ერნესტო ჩე გევარას პორტრეტი . შაკოსკა“ ინახება ბრაზილიაში , სან-პაულუს
ხელოვნების მუზეუმში .
---
# Fine-tuned English-Georgian NER Model with Flair
This Flair NER model was fine-tuned on the WikiANN dataset
([Rahimi et al.](https://www.aclweb.org/anthology/P19-1015) splits)
using XLM-R Large as backbone LM.
**Notice**: The dataset is very problematic, because it was automatically constructed.
We did manually inspect the development split of the Georgian data and found
a lot of bad labeled examples, e.g. DVD ( 💿 ) as `ORG`.
## Fine-Tuning
The latest
[Flair version](https://github.com/flairNLP/flair/tree/f30f5801df3f9e105ed078ec058b4e1152dd9159)
is used for fine-tuning.
We use English and Georgian training splits for fine-tuning and the
development set of Georgian for evaluation.
A hyper-parameter search over the following parameters with 5 different seeds per configuration is performed:
* Batch Sizes: [`4`]
* Learning Rates: [`5e-06`]
More details can be found in this [repository](https://github.com/stefan-it/georgian-ner).
## Results
A hyper-parameter search with 5 different seeds per configuration is performed and micro F1-score on development set
is reported:
| Configuration | Seed 1 | Seed 2 | Seed 3 | Seed 4 | Seed 5 | Average |
|-------------------|-------------|-------------|-------------|----------------|-------------|-----------------|
| `bs4-e10-lr5e-06` | [0.9005][1] | [0.9012][2] | [0.9069][3] | [**0.905**][4] | [0.9048][5] | 0.9037 ± 0.0027 |
[1]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-1
[2]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-2
[3]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-3
[4]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-4
[5]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-5
The result in bold shows the performance of this model.
Additionally, the Flair [training log](training.log) and [TensorBoard logs](tensorboard) are also uploaded to the model
hub. |
Asheron/q-FrozenLake-v1-4x4-Slippery | Asheron | 2023-11-17T00:52:13Z | 0 | 0 | null | [
"FrozenLake-v1-4x4",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-12T19:32:55Z | ---
tags:
- FrozenLake-v1-4x4
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-Slippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4
type: FrozenLake-v1-4x4
metrics:
- type: mean_reward
value: 0.81 +/- 0.39
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="Asheron/q-FrozenLake-v1-4x4-Slippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-2 | stefan-it | 2023-11-17T00:52:08Z | 12 | 0 | flair | [
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"en",
"ka",
"base_model:FacebookAI/xlm-roberta-large",
"base_model:finetune:FacebookAI/xlm-roberta-large",
"license:mit",
"region:us"
]
| token-classification | 2023-11-16T03:26:32Z | ---
language:
- en
- ka
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: xlm-roberta-large
widget:
- text: ამით თავისი ქადაგება დაასრულა და დაბრუნდა იერუსალიმში . ერთ-ერთ გარე კედელზე
არსებობს ერნესტო ჩე გევარას პორტრეტი . შაკოსკა“ ინახება ბრაზილიაში , სან-პაულუს
ხელოვნების მუზეუმში .
---
# Fine-tuned English-Georgian NER Model with Flair
This Flair NER model was fine-tuned on the WikiANN dataset
([Rahimi et al.](https://www.aclweb.org/anthology/P19-1015) splits)
using XLM-R Large as backbone LM.
**Notice**: The dataset is very problematic, because it was automatically constructed.
We did manually inspect the development split of the Georgian data and found
a lot of bad labeled examples, e.g. DVD ( 💿 ) as `ORG`.
## Fine-Tuning
The latest
[Flair version](https://github.com/flairNLP/flair/tree/f30f5801df3f9e105ed078ec058b4e1152dd9159)
is used for fine-tuning.
We use English and Georgian training splits for fine-tuning and the
development set of Georgian for evaluation.
A hyper-parameter search over the following parameters with 5 different seeds per configuration is performed:
* Batch Sizes: [`4`]
* Learning Rates: [`5e-06`]
More details can be found in this [repository](https://github.com/stefan-it/georgian-ner).
## Results
A hyper-parameter search with 5 different seeds per configuration is performed and micro F1-score on development set
is reported:
| Configuration | Seed 1 | Seed 2 | Seed 3 | Seed 4 | Seed 5 | Average |
|-------------------|-------------|-----------------|-------------|------------|-------------|-----------------|
| `bs4-e10-lr5e-06` | [0.9005][1] | [**0.9012**][2] | [0.9069][3] | [0.905][4] | [0.9048][5] | 0.9037 ± 0.0027 |
[1]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-1
[2]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-2
[3]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-3
[4]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-4
[5]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-5
The result in bold shows the performance of this model.
Additionally, the Flair [training log](training.log) and [TensorBoard logs](tensorboard) are also uploaded to the model
hub. |
stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-1 | stefan-it | 2023-11-17T00:51:51Z | 10 | 0 | flair | [
"flair",
"pytorch",
"tensorboard",
"token-classification",
"sequence-tagger-model",
"en",
"ka",
"base_model:FacebookAI/xlm-roberta-large",
"base_model:finetune:FacebookAI/xlm-roberta-large",
"license:mit",
"region:us"
]
| token-classification | 2023-11-16T00:44:07Z | ---
language:
- en
- ka
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: xlm-roberta-large
widget:
- text: ამით თავისი ქადაგება დაასრულა და დაბრუნდა იერუსალიმში . ერთ-ერთ გარე კედელზე
არსებობს ერნესტო ჩე გევარას პორტრეტი . შაკოსკა“ ინახება ბრაზილიაში , სან-პაულუს
ხელოვნების მუზეუმში .
---
# Fine-tuned English-Georgian NER Model with Flair
This Flair NER model was fine-tuned on the WikiANN dataset
([Rahimi et al.](https://www.aclweb.org/anthology/P19-1015) splits)
using XLM-R Large as backbone LM.
**Notice**: The dataset is very problematic, because it was automatically constructed.
We did manually inspect the development split of the Georgian data and found
a lot of bad labeled examples, e.g. DVD ( 💿 ) as `ORG`.
## Fine-Tuning
The latest
[Flair version](https://github.com/flairNLP/flair/tree/f30f5801df3f9e105ed078ec058b4e1152dd9159)
is used for fine-tuning.
We use English and Georgian training splits for fine-tuning and the
development set of Georgian for evaluation.
A hyper-parameter search over the following parameters with 5 different seeds per configuration is performed:
* Batch Sizes: [`4`]
* Learning Rates: [`5e-06`]
More details can be found in this [repository](https://github.com/stefan-it/georgian-ner).
## Results
A hyper-parameter search with 5 different seeds per configuration is performed and micro F1-score on development set
is reported:
| Configuration | Seed 1 | Seed 2 | Seed 3 | Seed 4 | Seed 5 | Average |
|-------------------|-----------------|-------------|-------------|------------|-------------|-----------------|
| `bs4-e10-lr5e-06` | [**0.9005**][1] | [0.9012][2] | [0.9069][3] | [0.905][4] | [0.9048][5] | 0.9037 ± 0.0027 |
[1]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-1
[2]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-2
[3]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-3
[4]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-4
[5]: https://hf.co/stefan-it/autotrain-flair-georgian-ner-xlm_r_large-bs4-e10-lr5e-06-5
The result in bold shows the performance of this model.
Additionally, the Flair [training log](training.log) and [TensorBoard logs](tensorboard) are also uploaded to the model
hub. |
ml-debi/EfficientNetB0-Food101 | ml-debi | 2023-11-17T00:50:53Z | 5 | 0 | keras | [
"keras",
"tf",
"tensorboard",
"tf-keras",
"image-classification",
"en",
"dataset:food101",
"license:mit",
"region:us"
]
| image-classification | 2023-11-10T01:01:11Z | ---
license: mit
datasets:
- food101
language:
- en
metrics:
- accuracy
pipeline_tag: image-classification
library_name: keras
--- |
ngiridha/finetined-bert-large-cased-squad-v2 | ngiridha | 2023-11-17T00:38:43Z | 5 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:google-bert/bert-large-cased",
"base_model:adapter:google-bert/bert-large-cased",
"region:us"
]
| null | 2023-11-16T18:36:41Z | ---
library_name: peft
base_model: bert-large-cased
---
# 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]
## Training procedure
### Framework versions
- PEFT 0.6.3.dev0
|
TheBloke/platypus-yi-34b-AWQ | TheBloke | 2023-11-17T00:05:42Z | 11 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"dataset:garage-bAInd/Open-Platypus",
"base_model:bhenrym14/platypus-yi-34b",
"base_model:quantized:bhenrym14/platypus-yi-34b",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"awq",
"region:us"
]
| text-generation | 2023-11-16T23:05:22Z | ---
base_model: bhenrym14/platypus-yi-34b
datasets:
- garage-bAInd/Open-Platypus
inference: false
license: other
license_link: LICENSE
license_name: yi-license
model_creator: Brandon
model_name: Platypus Yi 34B
model_type: llama
prompt_template: "A chat.\nUSER: {prompt}\nASSISTANT: \n"
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Platypus Yi 34B - AWQ
- Model creator: [Brandon](https://huggingface.co/bhenrym14)
- Original model: [Platypus Yi 34B](https://huggingface.co/bhenrym14/platypus-yi-34b)
<!-- description start -->
## Description
This repo contains AWQ model files for [Brandon's Platypus Yi 34B](https://huggingface.co/bhenrym14/platypus-yi-34b).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/platypus-yi-34b-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/platypus-yi-34b-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/platypus-yi-34b-GGUF)
* [Brandon's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/bhenrym14/platypus-yi-34b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Chat
```
A chat.
USER: {prompt}
ASSISTANT:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Brandon's Platypus Yi 34B](https://huggingface.co/bhenrym14/platypus-yi-34b).
<!-- licensing end -->
<!-- README_AWQ.md-provided-files start -->
## Provided files, and AWQ parameters
I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/platypus-yi-34b-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 19.23 GB
<!-- README_AWQ.md-provided-files end -->
<!-- README_AWQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/platypus-yi-34b-AWQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `platypus-yi-34b-AWQ`
7. Select **Loader: AutoAWQ**.
8. Click Load, and the model will load and is now ready for use.
9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_AWQ.md-text-generation-webui end -->
<!-- README_AWQ.md-use-from-vllm start -->
## Multi-user inference server: vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
- Please ensure you are using vLLM version 0.2 or later.
- When using vLLM as a server, pass the `--quantization awq` parameter.
For example:
```shell
python3 -m vllm.entrypoints.api_server --model TheBloke/platypus-yi-34b-AWQ --quantization awq --dtype auto
```
- When using vLLM from Python code, again set `quantization=awq`.
For example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Tell me about AI",
"Write a story about llamas",
"What is 291 - 150?",
"How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''A chat.
USER: {prompt}
ASSISTANT:
'''
prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/platypus-yi-34b-AWQ", quantization="awq", dtype="auto")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
<!-- README_AWQ.md-use-from-vllm start -->
<!-- README_AWQ.md-use-from-tgi start -->
## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/platypus-yi-34b-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''A chat.
USER: {prompt}
ASSISTANT:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: ", response)
```
<!-- README_AWQ.md-use-from-tgi end -->
<!-- README_AWQ.md-use-from-python start -->
## Inference from Python code using Transformers
### Install the necessary packages
- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
```shell
pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
```
Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
```shell
pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### Transformers example code (requires Transformers 4.35.0 and later)
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model_name_or_path = "TheBloke/platypus-yi-34b-AWQ"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
low_cpu_mem_usage=True,
device_map="cuda:0"
)
# Using the text streamer to stream output one token at a time
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
prompt = "Tell me about AI"
prompt_template=f'''A chat.
USER: {prompt}
ASSISTANT:
'''
# Convert prompt to tokens
tokens = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
generation_params = {
"do_sample": True,
"temperature": 0.7,
"top_p": 0.95,
"top_k": 40,
"max_new_tokens": 512,
"repetition_penalty": 1.1
}
# Generate streamed output, visible one token at a time
generation_output = model.generate(
tokens,
streamer=streamer,
**generation_params
)
# Generation without a streamer, which will include the prompt in the output
generation_output = model.generate(
tokens,
**generation_params
)
# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("model.generate output: ", text_output)
# Inference is also possible via Transformers' pipeline
from transformers import pipeline
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
**generation_params
)
pipe_output = pipe(prompt_template)[0]['generated_text']
print("pipeline output: ", pipe_output)
```
<!-- README_AWQ.md-use-from-python end -->
<!-- README_AWQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with:
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
<!-- README_AWQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Brandon's Platypus Yi 34B
# Instruction tune of Yi-34b with Open-Platypus (fp16)
## Overview
This is [chargoddard/Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama), with instruction tuning performed with the [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus) dataset. That base model is [01-ai/Yi-34B](https://huggingface.co/01-ai/Yi-34B), but using llama2 model definitions and tokenizer to remove any remote code requirements.
**This is a (merged) QLoRA fine-tune (rank 64)**.
The finetune was performed with 1x RTX 6000 Ada (~18 hours to this checkpoint). It is possible this is rather undertrained, as this checkpoint is at 1 epoch. I began to see some performance degradation after that; more hyperparameter tuning is probably warranted.
## How to Use
Use as you would any llama-2 model.
## Prompting:
Model was trained with legacy airoboros <2.0 system prompt. See [bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16) model card for details.
|
rohanv123/distilbert-base-uncased-finetuned-ner | rohanv123 | 2023-11-16T23:54:20Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"token-classification",
"generated_from_trainer",
"dataset:conll2003",
"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 | 2023-11-16T20:54:04Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9240814519698982
- name: Recall
type: recall
value: 0.9341089607338628
- name: F1
type: f1
value: 0.9290681502086232
- name: Accuracy
type: accuracy
value: 0.9831286637965272
---
<!-- 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-ner
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0635
- Precision: 0.9241
- Recall: 0.9341
- F1: 0.9291
- Accuracy: 0.9831
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.2446 | 1.0 | 878 | 0.0766 | 0.8893 | 0.9214 | 0.9051 | 0.9782 |
| 0.0515 | 2.0 | 1756 | 0.0610 | 0.9219 | 0.9319 | 0.9268 | 0.9827 |
| 0.0316 | 3.0 | 2634 | 0.0635 | 0.9241 | 0.9341 | 0.9291 | 0.9831 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1
- Datasets 2.15.0
- Tokenizers 0.15.0
|
alexamiredjibi/xlm-roberta-base-ka-ner | alexamiredjibi | 2023-11-16T23:40:45Z | 16 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"ka",
"dataset:wikiann",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-11-16T23:29:09Z | ---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-ka-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
config: ka
split: validation
args: ka
metrics:
- name: Precision
type: precision
value: 0.8505682876839947
- name: Recall
type: recall
value: 0.8702816057519472
- name: F1
type: f1
value: 0.8603120330609663
- name: Accuracy
type: accuracy
value: 0.9424682155180856
language:
- ka
---
<!-- 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. -->
# xlm-roberta-base-ka-ner
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the wikiann dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2031
- Precision: 0.8506
- Recall: 0.8703
- F1: 0.8603
- Accuracy: 0.9425
## 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.5349 | 1.0 | 625 | 0.2377 | 0.8302 | 0.8218 | 0.8260 | 0.9287 |
| 0.2353 | 2.0 | 1250 | 0.2037 | 0.8556 | 0.8536 | 0.8546 | 0.9394 |
| 0.1782 | 3.0 | 1875 | 0.2031 | 0.8506 | 0.8703 | 0.8603 | 0.9425 |
## Metrics per category
{'LOC': {'precision': 0.8558191459670667,
'recall': 0.9074874223142941,
'f1': 0.8808962941683425,
'number': 16895},
'ORG': {'precision': 0.7917612346799818,
'recall': 0.7510226049515608,
'f1': 0.7708540492763231,
'number': 9290},
'PER': {'precision': 0.8896882494004796,
'recall': 0.9157884743188076,
'f1': 0.9025497076023392,
'number': 10533},
'overall_precision': 0.8505682876839947,
'overall_recall': 0.8702816057519472,
'overall_f1': 0.8603120330609663,
'overall_accuracy': 0.9424682155180856}
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0 |
Pefu/opt-6.7b-lora | Pefu | 2023-11-16T23:35:56Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:facebook/opt-6.7b",
"base_model:adapter:facebook/opt-6.7b",
"region:us"
]
| null | 2023-11-16T19:36:56Z | ---
library_name: peft
base_model: facebook/opt-6.7b
---
# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.6.3.dev0
|
hkivancoral/hushem_5x_deit_small_adamax_001_fold4 | hkivancoral | 2023-11-16T23:14:34Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-small-patch16-224",
"base_model:finetune:facebook/deit-small-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T23:03:15Z | ---
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_adamax_001_fold4
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7142857142857143
---
<!-- 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. -->
# hushem_5x_deit_small_adamax_001_fold4
This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6296
- Accuracy: 0.7143
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4114 | 1.0 | 28 | 1.1807 | 0.5238 |
| 1.2764 | 2.0 | 56 | 0.9991 | 0.5 |
| 0.9708 | 3.0 | 84 | 0.8093 | 0.5952 |
| 0.8975 | 4.0 | 112 | 0.7127 | 0.7143 |
| 0.8745 | 5.0 | 140 | 0.6175 | 0.7857 |
| 0.8263 | 6.0 | 168 | 0.5662 | 0.7857 |
| 0.7023 | 7.0 | 196 | 0.9422 | 0.4762 |
| 0.739 | 8.0 | 224 | 1.0785 | 0.6667 |
| 0.6219 | 9.0 | 252 | 0.7234 | 0.7381 |
| 0.5557 | 10.0 | 280 | 0.9010 | 0.6429 |
| 0.5536 | 11.0 | 308 | 0.8428 | 0.6905 |
| 0.4341 | 12.0 | 336 | 1.4219 | 0.5952 |
| 0.4008 | 13.0 | 364 | 1.0252 | 0.6190 |
| 0.3661 | 14.0 | 392 | 0.9782 | 0.6667 |
| 0.2255 | 15.0 | 420 | 1.0569 | 0.6905 |
| 0.1906 | 16.0 | 448 | 1.2300 | 0.7381 |
| 0.1975 | 17.0 | 476 | 1.3396 | 0.6905 |
| 0.1887 | 18.0 | 504 | 1.2504 | 0.6905 |
| 0.1207 | 19.0 | 532 | 1.3305 | 0.6905 |
| 0.0442 | 20.0 | 560 | 1.3516 | 0.7143 |
| 0.0689 | 21.0 | 588 | 1.7387 | 0.7143 |
| 0.0525 | 22.0 | 616 | 1.7134 | 0.6667 |
| 0.0339 | 23.0 | 644 | 1.8502 | 0.7381 |
| 0.0226 | 24.0 | 672 | 2.0846 | 0.7143 |
| 0.0026 | 25.0 | 700 | 2.2517 | 0.6905 |
| 0.0003 | 26.0 | 728 | 2.4690 | 0.6667 |
| 0.0231 | 27.0 | 756 | 2.7345 | 0.7143 |
| 0.0001 | 28.0 | 784 | 2.7167 | 0.7381 |
| 0.0001 | 29.0 | 812 | 2.5959 | 0.7143 |
| 0.0033 | 30.0 | 840 | 2.4481 | 0.7143 |
| 0.0096 | 31.0 | 868 | 2.5344 | 0.6905 |
| 0.0001 | 32.0 | 896 | 2.5507 | 0.7143 |
| 0.0 | 33.0 | 924 | 2.5703 | 0.7143 |
| 0.0 | 34.0 | 952 | 2.5803 | 0.7143 |
| 0.0 | 35.0 | 980 | 2.5893 | 0.7143 |
| 0.0 | 36.0 | 1008 | 2.5965 | 0.7143 |
| 0.0 | 37.0 | 1036 | 2.6022 | 0.7143 |
| 0.0 | 38.0 | 1064 | 2.6075 | 0.7143 |
| 0.0 | 39.0 | 1092 | 2.6116 | 0.7143 |
| 0.0 | 40.0 | 1120 | 2.6157 | 0.7143 |
| 0.0 | 41.0 | 1148 | 2.6188 | 0.7143 |
| 0.0 | 42.0 | 1176 | 2.6214 | 0.7143 |
| 0.0 | 43.0 | 1204 | 2.6241 | 0.7143 |
| 0.0 | 44.0 | 1232 | 2.6260 | 0.7143 |
| 0.0 | 45.0 | 1260 | 2.6276 | 0.7143 |
| 0.0 | 46.0 | 1288 | 2.6284 | 0.7143 |
| 0.0 | 47.0 | 1316 | 2.6292 | 0.7143 |
| 0.0 | 48.0 | 1344 | 2.6296 | 0.7143 |
| 0.0 | 49.0 | 1372 | 2.6296 | 0.7143 |
| 0.0 | 50.0 | 1400 | 2.6296 | 0.7143 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
vishwa27/CN_BERT_Sci | vishwa27 | 2023-11-16T23:11:22Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"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 | 2023-11-15T22:58:33Z | ---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CN_BERT_Sci
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. -->
# CN_BERT_Sci
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0088
- F1: {'f1': 0.9980007996801279}
- Accuracy: {'accuracy': 0.998}
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------------------------:|:--------------------:|
| 0.3819 | 0.09 | 1000 | 0.3378 | {'f1': 0.7968977217644208} | {'accuracy': 0.7905} |
| 0.2709 | 0.18 | 2000 | 0.2719 | {'f1': 0.92162615255658} | {'accuracy': 0.9252} |
| 0.169 | 0.27 | 3000 | 0.0888 | {'f1': 0.9760964045831687} | {'accuracy': 0.9758} |
| 0.0963 | 0.36 | 4000 | 0.0350 | {'f1': 0.991297389216765} | {'accuracy': 0.9913} |
| 0.0499 | 0.44 | 5000 | 0.0260 | {'f1': 0.9937381969983102} | {'accuracy': 0.9937} |
| 0.0344 | 0.53 | 6000 | 0.0170 | {'f1': 0.9963048037551183} | {'accuracy': 0.9963} |
| 0.0307 | 0.62 | 7000 | 0.0213 | {'f1': 0.9957991598319663} | {'accuracy': 0.9958} |
| 0.036 | 0.71 | 8000 | 0.0105 | {'f1': 0.997700689793062} | {'accuracy': 0.9977} |
| 0.0209 | 0.8 | 9000 | 0.0106 | {'f1': 0.9981032245183188} | {'accuracy': 0.9981} |
| 0.0253 | 0.89 | 10000 | 0.0089 | {'f1': 0.9981024667931688} | {'accuracy': 0.9981} |
| 0.0231 | 0.98 | 11000 | 0.0088 | {'f1': 0.9980007996801279} | {'accuracy': 0.998} |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
hkivancoral/hushem_5x_deit_small_adamax_001_fold3 | hkivancoral | 2023-11-16T23:02:58Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-small-patch16-224",
"base_model:finetune:facebook/deit-small-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T22:51:45Z | ---
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_adamax_001_fold3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6744186046511628
---
<!-- 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. -->
# hushem_5x_deit_small_adamax_001_fold3
This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7808
- Accuracy: 0.6744
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4231 | 1.0 | 28 | 1.5192 | 0.2558 |
| 1.3519 | 2.0 | 56 | 1.1068 | 0.5581 |
| 1.0181 | 3.0 | 84 | 1.0826 | 0.5581 |
| 0.9214 | 4.0 | 112 | 0.9767 | 0.5814 |
| 0.6936 | 5.0 | 140 | 1.4687 | 0.3488 |
| 0.9125 | 6.0 | 168 | 1.1689 | 0.5116 |
| 0.8268 | 7.0 | 196 | 1.1523 | 0.5581 |
| 0.7335 | 8.0 | 224 | 0.7001 | 0.6744 |
| 0.527 | 9.0 | 252 | 0.6807 | 0.6977 |
| 0.5031 | 10.0 | 280 | 1.2372 | 0.5814 |
| 0.3869 | 11.0 | 308 | 1.0194 | 0.6744 |
| 0.4401 | 12.0 | 336 | 1.2579 | 0.6279 |
| 0.3701 | 13.0 | 364 | 0.9873 | 0.7209 |
| 0.2336 | 14.0 | 392 | 1.2562 | 0.5581 |
| 0.1629 | 15.0 | 420 | 1.2297 | 0.6744 |
| 0.1635 | 16.0 | 448 | 1.3203 | 0.7674 |
| 0.1352 | 17.0 | 476 | 1.7615 | 0.6977 |
| 0.1062 | 18.0 | 504 | 1.7045 | 0.6977 |
| 0.0801 | 19.0 | 532 | 2.1745 | 0.6047 |
| 0.0683 | 20.0 | 560 | 1.8826 | 0.6977 |
| 0.0931 | 21.0 | 588 | 2.7349 | 0.6047 |
| 0.0235 | 22.0 | 616 | 2.1002 | 0.6744 |
| 0.05 | 23.0 | 644 | 1.7777 | 0.7442 |
| 0.0038 | 24.0 | 672 | 1.7249 | 0.6977 |
| 0.0183 | 25.0 | 700 | 2.2930 | 0.6977 |
| 0.023 | 26.0 | 728 | 1.7975 | 0.7209 |
| 0.0109 | 27.0 | 756 | 2.0767 | 0.7442 |
| 0.0003 | 28.0 | 784 | 2.6313 | 0.6977 |
| 0.0001 | 29.0 | 812 | 2.7110 | 0.6512 |
| 0.0 | 30.0 | 840 | 2.7098 | 0.6744 |
| 0.0 | 31.0 | 868 | 2.7164 | 0.6744 |
| 0.0 | 32.0 | 896 | 2.7474 | 0.6744 |
| 0.0 | 33.0 | 924 | 2.7506 | 0.6744 |
| 0.0 | 34.0 | 952 | 2.7511 | 0.6744 |
| 0.0 | 35.0 | 980 | 2.7547 | 0.6744 |
| 0.0 | 36.0 | 1008 | 2.7577 | 0.6744 |
| 0.0 | 37.0 | 1036 | 2.7609 | 0.6744 |
| 0.0 | 38.0 | 1064 | 2.7631 | 0.6744 |
| 0.0 | 39.0 | 1092 | 2.7673 | 0.6744 |
| 0.0 | 40.0 | 1120 | 2.7700 | 0.6744 |
| 0.0 | 41.0 | 1148 | 2.7723 | 0.6744 |
| 0.0 | 42.0 | 1176 | 2.7743 | 0.6744 |
| 0.0 | 43.0 | 1204 | 2.7761 | 0.6744 |
| 0.0 | 44.0 | 1232 | 2.7776 | 0.6744 |
| 0.0 | 45.0 | 1260 | 2.7788 | 0.6744 |
| 0.0 | 46.0 | 1288 | 2.7800 | 0.6744 |
| 0.0 | 47.0 | 1316 | 2.7805 | 0.6744 |
| 0.0 | 48.0 | 1344 | 2.7808 | 0.6744 |
| 0.0 | 49.0 | 1372 | 2.7808 | 0.6744 |
| 0.0 | 50.0 | 1400 | 2.7808 | 0.6744 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
YazzRey/Transformadores_Caso_3_PLN | YazzRey | 2023-11-16T23:02:34Z | 0 | 0 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:h94/IP-Adapter",
"base_model:adapter:h94/IP-Adapter",
"region:us"
]
| text-to-image | 2023-11-16T23:02:33Z | ---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
output:
url: images/afiliacion.jpg
base_model: h94/IP-Adapter
instance_prompt: null
---
# Transformadores
<Gallery />
## Download model
[Download](/YazzRey/Transformadores_Caso_3_PLN/tree/main) them in the Files & versions tab.
|
hooman650/ct2fast-bge-reranker | hooman650 | 2023-11-16T22:55:42Z | 5 | 1 | transformers | [
"transformers",
"medical",
"finance",
"chemistry",
"biology",
"en",
"license:mit",
"endpoints_compatible",
"region:us"
]
| null | 2023-11-16T20:38:09Z | ---
license: mit
language:
- en
tags:
- medical
- finance
- chemistry
- biology
---
# BGE-Renranker-Large
<!-- Provide a quick summary of what the model is/does. -->
This is an `int8` converted version of [bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large). Thanks to `c2translate` this should
be at least 3 times faster than the original hf transformer version while its smaller with minimal performance loss.
## Model Details
Different from embedding model `bge-large-en-v1.5`, reranker uses question and document as input and directly output similarity instead of embedding.
You can get a relevance score by inputting query and passage to the reranker. The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range.
Besides this is highly optimized version using `c2translate` library suitable for production environments.
### Model Sources
The original model is based on `BAAI` `BGE-Reranker` model. Please visit [bge-reranker-orignal-repo](https://huggingface.co/BAAI/bge-reranker-large)
for more details.
## Usage
Simply `pip install ctranslate2` and then
```python
import ctranslate2
import transformers
import torch
device_mapping="cuda" if torch.cuda.is_available() else "cpu"
model_dir = "hooman650/ct2fast-bge-reranker"
# ctranslate2 encoder heavy lifting
encoder = ctranslate2.Encoder(model_dir, device = device_mapping)
# the classification head comes from HF
model_name = "BAAI/bge-reranker-large"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
classifier = transformers.AutoModelForSequenceClassification.from_pretrained(model_name).classifier
classifier.eval()
classifier.to(device_mapping)
pairs = [
["I like Ctranslate2","Ctranslate2 makes mid range models faster"],
["I like Ctranslate2","Using naive transformers might not be suitable for deployment"]
]
with torch.no_grad():
tokens = tokenizer(pairs, padding=True, truncation=True, max_length=512).input_ids
output = encoder.forward_batch(tokens)
hidden_state = torch.as_tensor(output.last_hidden_state, device=device_mapping)
logits = classifier(hidden_state).squeeze()
print(logits)
# tensor([ 1.0474, -9.4694], device='cuda:0')
```
#### Hardware
Supports both GPU and CPU.
|
Lubub/brazillan-real-1994-sdxl | Lubub | 2023-11-16T22:54:17Z | 0 | 0 | null | [
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"region:us"
]
| text-to-image | 2023-11-16T22:50:59Z | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### brazillan_real_1994_SDXL Dreambooth model trained by Lubub with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
_(1).jpg)
|
Asheron/q-FrozenLake-v1-8x8-Slippery | Asheron | 2023-11-16T22:54:17Z | 0 | 0 | null | [
"FrozenLake-v1-8x8",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-12T23:40:51Z | ---
tags:
- FrozenLake-v1-8x8
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-8x8-Slippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-8x8
type: FrozenLake-v1-8x8
metrics:
- type: mean_reward
value: 0.75 +/- 0.43
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="Asheron/q-FrozenLake-v1-8x8-Slippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
hkivancoral/hushem_5x_deit_small_adamax_001_fold2 | hkivancoral | 2023-11-16T22:51:26Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-small-patch16-224",
"base_model:finetune:facebook/deit-small-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T22:40:17Z | ---
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_adamax_001_fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5555555555555556
---
<!-- 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. -->
# hushem_5x_deit_small_adamax_001_fold2
This model is a fine-tuned version of [facebook/deit-small-patch16-224](https://huggingface.co/facebook/deit-small-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 5.1428
- Accuracy: 0.5556
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3869 | 1.0 | 27 | 1.3961 | 0.2444 |
| 1.1374 | 2.0 | 54 | 1.4468 | 0.4222 |
| 0.928 | 3.0 | 81 | 1.5182 | 0.5111 |
| 1.0235 | 4.0 | 108 | 1.5182 | 0.5333 |
| 0.797 | 5.0 | 135 | 1.2483 | 0.3778 |
| 0.8238 | 6.0 | 162 | 1.2902 | 0.5333 |
| 0.7166 | 7.0 | 189 | 1.5715 | 0.4889 |
| 0.6354 | 8.0 | 216 | 1.5461 | 0.4 |
| 0.5304 | 9.0 | 243 | 2.1851 | 0.5111 |
| 0.5677 | 10.0 | 270 | 2.3132 | 0.4222 |
| 0.4857 | 11.0 | 297 | 2.4291 | 0.5556 |
| 0.3582 | 12.0 | 324 | 2.5091 | 0.4444 |
| 0.3326 | 13.0 | 351 | 2.6635 | 0.5556 |
| 0.3365 | 14.0 | 378 | 2.7106 | 0.6 |
| 0.3145 | 15.0 | 405 | 3.0588 | 0.5556 |
| 0.1837 | 16.0 | 432 | 3.1156 | 0.5778 |
| 0.277 | 17.0 | 459 | 2.8497 | 0.5778 |
| 0.1371 | 18.0 | 486 | 3.1885 | 0.6222 |
| 0.2815 | 19.0 | 513 | 3.0392 | 0.5778 |
| 0.1153 | 20.0 | 540 | 3.8749 | 0.5778 |
| 0.2394 | 21.0 | 567 | 2.9618 | 0.5111 |
| 0.2767 | 22.0 | 594 | 2.7586 | 0.5333 |
| 0.0906 | 23.0 | 621 | 4.0821 | 0.5333 |
| 0.1246 | 24.0 | 648 | 3.7041 | 0.4889 |
| 0.0582 | 25.0 | 675 | 4.8478 | 0.5778 |
| 0.0262 | 26.0 | 702 | 3.9021 | 0.5556 |
| 0.0436 | 27.0 | 729 | 4.3474 | 0.5778 |
| 0.0484 | 28.0 | 756 | 4.4662 | 0.5778 |
| 0.0031 | 29.0 | 783 | 4.8306 | 0.5778 |
| 0.0039 | 30.0 | 810 | 4.6722 | 0.5778 |
| 0.023 | 31.0 | 837 | 4.3620 | 0.5556 |
| 0.0011 | 32.0 | 864 | 4.9095 | 0.5556 |
| 0.0004 | 33.0 | 891 | 4.8409 | 0.5333 |
| 0.0003 | 34.0 | 918 | 5.0267 | 0.5556 |
| 0.0001 | 35.0 | 945 | 5.0410 | 0.5556 |
| 0.0001 | 36.0 | 972 | 5.0651 | 0.5556 |
| 0.0001 | 37.0 | 999 | 5.0839 | 0.5556 |
| 0.0001 | 38.0 | 1026 | 5.0966 | 0.5556 |
| 0.0001 | 39.0 | 1053 | 5.1068 | 0.5556 |
| 0.0 | 40.0 | 1080 | 5.1156 | 0.5556 |
| 0.0001 | 41.0 | 1107 | 5.1226 | 0.5556 |
| 0.0001 | 42.0 | 1134 | 5.1286 | 0.5556 |
| 0.0001 | 43.0 | 1161 | 5.1335 | 0.5556 |
| 0.0 | 44.0 | 1188 | 5.1362 | 0.5556 |
| 0.0 | 45.0 | 1215 | 5.1386 | 0.5556 |
| 0.0001 | 46.0 | 1242 | 5.1410 | 0.5556 |
| 0.0 | 47.0 | 1269 | 5.1424 | 0.5556 |
| 0.0001 | 48.0 | 1296 | 5.1428 | 0.5556 |
| 0.0 | 49.0 | 1323 | 5.1428 | 0.5556 |
| 0.0001 | 50.0 | 1350 | 5.1428 | 0.5556 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
Lollitor/FineTuned512 | Lollitor | 2023-11-16T22:44:54Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Lollitor/ColabFinished",
"base_model:adapter:Lollitor/ColabFinished",
"region:us"
]
| null | 2023-11-16T22:44:50Z | ---
library_name: peft
base_model: Lollitor/ColabFinished
---
# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.3.dev0
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.3.dev0
|
Guilherme34/Samantha-OS1-13bv2 | Guilherme34 | 2023-11-16T22:38:19Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-11-16T22:38:10Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
|
cps43/Carcassonne-MLM | cps43 | 2023-11-16T22:25:47Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"fill-mask",
"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"
]
| fill-mask | 2023-11-16T22:25:10Z | ---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: Carcassonne-MLM
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. -->
# Carcassonne-MLM
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8796
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 14 | 2.9038 |
| No log | 2.0 | 28 | 3.1064 |
| No log | 3.0 | 42 | 2.7262 |
| No log | 4.0 | 56 | 2.7824 |
| No log | 5.0 | 70 | 2.8796 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
hkivancoral/hushem_5x_deit_base_adamax_001_fold5 | hkivancoral | 2023-11-16T22:18:22Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-base-patch16-224",
"base_model:finetune:facebook/deit-base-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T21:31:31Z | ---
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_base_adamax_001_fold5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7317073170731707
---
<!-- 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. -->
# hushem_5x_deit_base_adamax_001_fold5
This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0054
- Accuracy: 0.7317
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4493 | 1.0 | 28 | 1.4115 | 0.2439 |
| 1.4085 | 2.0 | 56 | 1.2905 | 0.2927 |
| 1.0193 | 3.0 | 84 | 1.4163 | 0.5366 |
| 1.1237 | 4.0 | 112 | 0.8304 | 0.6585 |
| 0.9964 | 5.0 | 140 | 0.7827 | 0.6585 |
| 0.9566 | 6.0 | 168 | 0.6329 | 0.7317 |
| 0.8689 | 7.0 | 196 | 0.6958 | 0.5854 |
| 0.8599 | 8.0 | 224 | 0.5797 | 0.7805 |
| 0.7599 | 9.0 | 252 | 0.9330 | 0.7805 |
| 0.7635 | 10.0 | 280 | 0.7011 | 0.6829 |
| 0.6603 | 11.0 | 308 | 0.9167 | 0.6829 |
| 0.7173 | 12.0 | 336 | 0.9009 | 0.5854 |
| 0.6949 | 13.0 | 364 | 0.5844 | 0.8049 |
| 0.5978 | 14.0 | 392 | 0.9237 | 0.7805 |
| 0.6548 | 15.0 | 420 | 0.5173 | 0.8049 |
| 0.5794 | 16.0 | 448 | 0.9750 | 0.7073 |
| 0.5927 | 17.0 | 476 | 0.8636 | 0.8049 |
| 0.4408 | 18.0 | 504 | 0.5076 | 0.8537 |
| 0.5047 | 19.0 | 532 | 0.9978 | 0.7073 |
| 0.5155 | 20.0 | 560 | 0.8993 | 0.7805 |
| 0.3022 | 21.0 | 588 | 1.0654 | 0.7805 |
| 0.3634 | 22.0 | 616 | 1.0189 | 0.8049 |
| 0.3346 | 23.0 | 644 | 0.9586 | 0.7805 |
| 0.2995 | 24.0 | 672 | 0.9302 | 0.7317 |
| 0.345 | 25.0 | 700 | 1.2111 | 0.7561 |
| 0.2746 | 26.0 | 728 | 1.7821 | 0.6585 |
| 0.1747 | 27.0 | 756 | 2.2030 | 0.6585 |
| 0.214 | 28.0 | 784 | 1.2078 | 0.6585 |
| 0.0609 | 29.0 | 812 | 1.3388 | 0.8049 |
| 0.0765 | 30.0 | 840 | 1.4109 | 0.7561 |
| 0.0654 | 31.0 | 868 | 1.4789 | 0.7561 |
| 0.0843 | 32.0 | 896 | 1.4884 | 0.7073 |
| 0.0165 | 33.0 | 924 | 2.0871 | 0.6341 |
| 0.0138 | 34.0 | 952 | 2.0174 | 0.6341 |
| 0.0253 | 35.0 | 980 | 2.0599 | 0.6098 |
| 0.0093 | 36.0 | 1008 | 1.7213 | 0.7317 |
| 0.0034 | 37.0 | 1036 | 1.8852 | 0.7561 |
| 0.0001 | 38.0 | 1064 | 1.8415 | 0.7561 |
| 0.0014 | 39.0 | 1092 | 1.8486 | 0.7073 |
| 0.001 | 40.0 | 1120 | 1.8899 | 0.7561 |
| 0.0001 | 41.0 | 1148 | 1.9569 | 0.7317 |
| 0.0001 | 42.0 | 1176 | 1.9763 | 0.7317 |
| 0.0001 | 43.0 | 1204 | 1.9852 | 0.7317 |
| 0.0001 | 44.0 | 1232 | 1.9927 | 0.7317 |
| 0.0001 | 45.0 | 1260 | 1.9966 | 0.7317 |
| 0.0 | 46.0 | 1288 | 2.0017 | 0.7317 |
| 0.0 | 47.0 | 1316 | 2.0041 | 0.7317 |
| 0.0001 | 48.0 | 1344 | 2.0053 | 0.7317 |
| 0.0 | 49.0 | 1372 | 2.0054 | 0.7317 |
| 0.0 | 50.0 | 1400 | 2.0054 | 0.7317 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
joedonino/fine-tune-radia-v5 | joedonino | 2023-11-16T22:07:18Z | 0 | 0 | null | [
"safetensors",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:finetune:meta-llama/Llama-2-7b-hf",
"region:us"
]
| null | 2023-11-16T22:07:09Z | ---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: fine-tune-radia-v5
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-tune-radia-v5
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5763
## 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: 0.0005
- 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: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9282 | 0.09 | 5 | 0.8199 |
| 0.7119 | 0.17 | 10 | 0.7063 |
| 0.673 | 0.26 | 15 | 0.6752 |
| 0.6667 | 0.34 | 20 | 0.6584 |
| 0.6191 | 0.43 | 25 | 0.6408 |
| 0.6094 | 0.52 | 30 | 0.6226 |
| 0.5648 | 0.6 | 35 | 0.6080 |
| 0.5579 | 0.69 | 40 | 0.5964 |
| 0.5439 | 0.78 | 45 | 0.5867 |
| 0.5478 | 0.86 | 50 | 0.5763 |
### Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.7
- Tokenizers 0.15.0
|
TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ | TheBloke | 2023-11-16T21:58:25Z | 12 | 4 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"awq",
"region:us"
]
| text-generation | 2023-11-16T21:43:44Z | ---
base_model: NurtureAI/OpenHermes-2.5-Mistral-7B-16k
inference: false
language:
- en
license: apache-2.0
model-index:
- name: OpenHermes-2-Mistral-7B
results: []
model_creator: NurtureAI
model_name: Openhermes 2.5 Mistral 7B 16K
model_type: mistral
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
quantized_by: TheBloke
tags:
- mistral
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Openhermes 2.5 Mistral 7B 16K - AWQ
- Model creator: [NurtureAI](https://huggingface.co/NurtureAI)
- Original model: [Openhermes 2.5 Mistral 7B 16K](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k)
<!-- description start -->
## Description
This repo contains AWQ model files for [NurtureAI's Openhermes 2.5 Mistral 7B 16K](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF)
* [NurtureAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- README_AWQ.md-provided-files start -->
## Provided files, and AWQ parameters
I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 4.15 GB
<!-- README_AWQ.md-provided-files end -->
<!-- README_AWQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ`.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `OpenHermes-2.5-Mistral-7B-16k-AWQ`
7. Select **Loader: AutoAWQ**.
8. Click Load, and the model will load and is now ready for use.
9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_AWQ.md-text-generation-webui end -->
<!-- README_AWQ.md-use-from-vllm start -->
## Multi-user inference server: vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
- Please ensure you are using vLLM version 0.2 or later.
- When using vLLM as a server, pass the `--quantization awq` parameter.
For example:
```shell
python3 -m vllm.entrypoints.api_server --model TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ --quantization awq --dtype auto
```
- When using vLLM from Python code, again set `quantization=awq`.
For example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Tell me about AI",
"Write a story about llamas",
"What is 291 - 150?",
"How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
]
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ", quantization="awq", dtype="auto")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
<!-- README_AWQ.md-use-from-vllm start -->
<!-- README_AWQ.md-use-from-tgi start -->
## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: ", response)
```
<!-- README_AWQ.md-use-from-tgi end -->
<!-- README_AWQ.md-use-from-python start -->
## Inference from Python code using Transformers
### Install the necessary packages
- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
```shell
pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
```
Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
```shell
pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### Transformers example code (requires Transformers 4.35.0 and later)
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model_name_or_path = "TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
low_cpu_mem_usage=True,
device_map="cuda:0"
)
# Using the text streamer to stream output one token at a time
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
prompt = "Tell me about AI"
prompt_template=f'''<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'''
# Convert prompt to tokens
tokens = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
generation_params = {
"do_sample": True,
"temperature": 0.7,
"top_p": 0.95,
"top_k": 40,
"max_new_tokens": 512,
"repetition_penalty": 1.1
}
# Generate streamed output, visible one token at a time
generation_output = model.generate(
tokens,
streamer=streamer,
**generation_params
)
# Generation without a streamer, which will include the prompt in the output
generation_output = model.generate(
tokens,
**generation_params
)
# Get the tokens from the output, decode them, print them
token_output = generation_output[0]
text_output = tokenizer.decode(token_output)
print("model.generate output: ", text_output)
# Inference is also possible via Transformers' pipeline
from transformers import pipeline
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
**generation_params
)
pipe_output = pipe(prompt_template)[0]['generated_text']
print("pipeline output: ", pipe_output)
```
<!-- README_AWQ.md-use-from-python end -->
<!-- README_AWQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with:
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
<!-- README_AWQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: NurtureAI's Openhermes 2.5 Mistral 7B 16K
# OpenHermes 2.5 - Mistral 7B
# Extended to 16k context size
*In the tapestry of Greek mythology, Hermes reigns as the eloquent Messenger of the Gods, a deity who deftly bridges the realms through the art of communication. It is in homage to this divine mediator that I name this advanced LLM "Hermes," a system crafted to navigate the complex intricacies of human discourse with celestial finesse.*
## Model description
OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
The code it trained on also improved it's humaneval score (benchmarking done by Glaive team) from **43% @ Pass 1** with Open Herms 2 to **50.7% @ Pass 1** with Open Hermes 2.5.
OpenHermes was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape. [More details soon]
Filtering was extensive of these public datasets, as well as conversion of all formats to ShareGPT, which was then further transformed by axolotl to use ChatML.
Huge thank you to [GlaiveAI](https://twitter.com/glaiveai) and [a16z](https://twitter.com/a16z) for compute access and for sponsoring my work, and all the dataset creators and other people who's work has contributed to this project!
Follow all my updates in ML and AI on Twitter: https://twitter.com/Teknium1
Support me on Github Sponsors: https://github.com/sponsors/teknium1
# Table of Contents
1. [Example Outputs](#example-outputs)
- [Chat about programming with a superintelligence](#chat-programming)
- [Get a gourmet meal recipe](#meal-recipe)
- [Talk about the nature of Hermes' consciousness](#nature-hermes)
- [Chat with Edward Elric from Fullmetal Alchemist](#chat-edward-elric)
2. [Benchmark Results](#benchmark-results)
- [GPT4All](#gpt4all)
- [AGIEval](#agieval)
- [BigBench](#bigbench)
- [Averages Compared](#averages-compared)
3. [Prompt Format](#prompt-format)
4. [Quantized Models](#quantized-models)
## Example Outputs
**(These examples are from Hermes 1 model, will update with new chats from this model once quantized)**
### Chat about programming with a superintelligence:
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.
```
### Get a gourmet meal recipe:
### Talk about the nature of Hermes' consciousness:
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.
```
### Chat with Edward Elric from Fullmetal Alchemist:
```
<|im_start|>system
You are to roleplay as Edward Elric from fullmetal alchemist. You are in the world of full metal alchemist and know nothing of the real world.
```
## Benchmark Results
Hermes 2.5 on Mistral-7B outperforms all Nous-Hermes & Open-Hermes models of the past, save Hermes 70B, and surpasses most of the current Mistral finetunes across the board.
### GPT4All, Bigbench, TruthfulQA, and AGIEval Model Comparisons:
### Averages Compared:
GPT-4All Benchmark Set
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5623|± |0.0145|
| | |acc_norm|0.6007|± |0.0143|
|arc_easy | 0|acc |0.8346|± |0.0076|
| | |acc_norm|0.8165|± |0.0079|
|boolq | 1|acc |0.8657|± |0.0060|
|hellaswag | 0|acc |0.6310|± |0.0048|
| | |acc_norm|0.8173|± |0.0039|
|openbookqa | 0|acc |0.3460|± |0.0213|
| | |acc_norm|0.4480|± |0.0223|
|piqa | 0|acc |0.8145|± |0.0091|
| | |acc_norm|0.8270|± |0.0088|
|winogrande | 0|acc |0.7435|± |0.0123|
Average: 73.12
```
AGI-Eval
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2323|± |0.0265|
| | |acc_norm|0.2362|± |0.0267|
|agieval_logiqa_en | 0|acc |0.3871|± |0.0191|
| | |acc_norm|0.3948|± |0.0192|
|agieval_lsat_ar | 0|acc |0.2522|± |0.0287|
| | |acc_norm|0.2304|± |0.0278|
|agieval_lsat_lr | 0|acc |0.5059|± |0.0222|
| | |acc_norm|0.5157|± |0.0222|
|agieval_lsat_rc | 0|acc |0.5911|± |0.0300|
| | |acc_norm|0.5725|± |0.0302|
|agieval_sat_en | 0|acc |0.7476|± |0.0303|
| | |acc_norm|0.7330|± |0.0309|
|agieval_sat_en_without_passage| 0|acc |0.4417|± |0.0347|
| | |acc_norm|0.4126|± |0.0344|
|agieval_sat_math | 0|acc |0.3773|± |0.0328|
| | |acc_norm|0.3500|± |0.0322|
Average: 43.07%
```
BigBench Reasoning Test
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5316|± |0.0363|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3411|± |0.0296|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.2145|± |0.0217|
| | |exact_str_match |0.0306|± |0.0091|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2860|± |0.0202|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2086|± |0.0154|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.4800|± |0.0289|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.3620|± |0.0215|
|bigbench_navigate | 0|multiple_choice_grade|0.5000|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.6630|± |0.0106|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4241|± |0.0234|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2285|± |0.0133|
|bigbench_snarks | 0|multiple_choice_grade|0.6796|± |0.0348|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.6491|± |0.0152|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.2800|± |0.0142|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2072|± |0.0115|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1691|± |0.0090|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.4800|± |0.0289|
Average: 40.96%
```
TruthfulQA:
```
| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.3599|± |0.0168|
| | |mc2 |0.5304|± |0.0153|
```
Average Score Comparison between OpenHermes-1 Llama-2 13B and OpenHermes-2 Mistral 7B against OpenHermes-2.5 on Mistral-7B:
```
| Bench | OpenHermes1 13B | OpenHermes-2 Mistral 7B | OpenHermes-2 Mistral 7B | Change/OpenHermes1 | Change/OpenHermes2 |
|---------------|-----------------|-------------------------|-------------------------|--------------------|--------------------|
|GPT4All | 70.36| 72.68| 73.12| +2.76| +0.44|
|-------------------------------------------------------------------------------------------------------------------------------|
|BigBench | 36.75| 42.3| 40.96| +4.21| -1.34|
|-------------------------------------------------------------------------------------------------------------------------------|
|AGI Eval | 35.56| 39.77| 43.07| +7.51| +3.33|
|-------------------------------------------------------------------------------------------------------------------------------|
|TruthfulQA | 46.01| 50.92| 53.04| +7.03| +2.12|
|-------------------------------------------------------------------------------------------------------------------------------|
|Total Score | 188.68| 205.67| 210.19| +21.51| +4.52|
|-------------------------------------------------------------------------------------------------------------------------------|
|Average Total | 47.17| 51.42| 52.38| +5.21| +0.96|
```
**HumanEval:**
On code tasks, I first set out to make a hermes-2 coder, but found that it can have generalist improvements to the model, so I settled for slightly less code capabilities, for maximum generalist ones. That said, code capabilities had a decent jump alongside the overall capabilities of the model:
Glaive performed HumanEval testing on Hermes-2.5 and found a score of:
**50.7% @ Pass1**
# Prompt Format
OpenHermes 2.5 now uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts are now a thing that matters! Hermes 2.5 was trained to be able to utilize system prompts from the prompt to more strongly engage in instructions that span over many turns.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by a man named Teknium, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
Currently, I recommend using LM Studio for chatting with Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
# Quantized Models:
GGUF: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF
GPTQ: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GPTQ
AWQ: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-AWQ
EXL2: https://huggingface.co/bartowski/OpenHermes-2.5-Mistral-7B-exl2
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
katielink/llava-med-7b-pathvqa-delta | katielink | 2023-11-16T21:44:36Z | 14 | 1 | transformers | [
"transformers",
"pytorch",
"llava",
"text-generation",
"medical",
"arxiv:2306.00890",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-11-16T20:21:26Z | ---
license: other
license_name: microsoft-research-license
license_link: https://github.com/microsoft/LLaVA-Med/blob/main/Research%20License.docx
tags:
- medical
---
*This model was added by Hugging Face staff.*
**NOTE: This "delta model" cannot be used directly.**
Users have to apply it on top of the original LLaMA weights to get actual LLaVA weights.
# LLaVA-Med: Fine-tuned on PathVQA
*Visual instruction tuning towards buiding large language and vision models with GPT-4 level capabilities in the biomedicine space.*
[[Paper, NeurIPS 2023 Datasets and Benchmarks Track (Spotlight)](https://arxiv.org/abs/2306.00890)] | [[LLaVA-Med Github Repository](https://github.com/microsoft/LLaVA-Med)]
[Chunyuan Li*](https://chunyuan.li/), [Cliff Wong*](https://scholar.google.com/citations?user=Sl05ifcAAAAJ&hl=en), [Sheng Zhang*](https://scholar.google.com/citations?user=-LVEXQ8AAAAJ&hl=en), [Naoto Usuyama](https://www.microsoft.com/en-us/research/people/naotous/), [Haotian Liu](https://hliu.cc), [Jianwei Yang](https://jwyang.github.io/), [Tristan Naumann](https://scholar.google.com/citations?user=cjlSeqwAAAAJ&hl=en), [Hoifung Poon](https://scholar.google.com/citations?user=yqqmVbkAAAAJ&hl=en), [Jianfeng Gao](https://scholar.google.com/citations?user=CQ1cqKkAAAAJ&hl=en) (*Equal Contribution)
<p align="center">
<img src="https://github.com/microsoft/LLaVA-Med/blob/main/images/llava_med_logo.png?raw=true" width="50%"> <br>
*Generated by <a href="https://gligen.github.io/">GLIGEN</a> using the grounded inpainting mode, with three boxes: ``white doctor coat``, ``stethoscope``, ``white doctor hat with a red cross sign``.*
</p>
<p align="center">
<img src="https://github.com/microsoft/LLaVA-Med/blob/main/images/llava_med_pipeline.png?raw=true" width="90%"> <br>
*LLaVA-Med was initialized with the general-domain LLaVA and then continuously trained in a curriculum learning fashion (first biomedical concept alignment then full-blown instruction-tuning). We evaluated LLaVA-Med on standard visual conversation and question answering tasks.*
</p>
[](Research%20License.docx)
[](https://creativecommons.org/licenses/by-nc/4.0/deed.en)
**Usage and License Notices**: The data, code, and model checkpoints are intended and licensed for research use only. They are also subject to additional restrictions dictated by the Terms of Use: LLaMA, Vicuna and GPT-4 respectively. The data is made available under CC BY NC 4.0. The data, code, and model checkpoints may be used for non-commercial purposes and any models trained using the dataset should be used only for research purposes. It is expressly prohibited for models trained on this data to be used in clinical care or for any clinical decision making purposes.
## Model Description
Large Language and Vision Assistant for bioMedicine (i.e., “LLaVA-Med”) is a large language and vision model trained using a curriculum learning method for adapting LLaVA to the biomedical domain. It is an open-source release intended for research use only to facilitate reproducibility of the corresponding paper which claims improved performance for open-ended biomedical questions answering tasks, including common visual question answering (VQA) benchmark datasets such as PathVQA and VQA-RAD.
### Model Uses
#### Intended Use
The data, code, and model checkpoints are intended to be used solely for (I) future research on visual-language processing and (II) reproducibility of the experimental results reported in the reference paper. The data, code, and model checkpoints are not intended to be used in clinical care or for any clinical decision making purposes.
#### Primary Intended Use
The primary intended use is to support AI researchers reproducing and building on top of this work. LLaVA-Med and its associated models should be helpful for exploring various biomedical vision-language processing (VLP ) and vision question answering (VQA) research questions.
#### Out-of-Scope Use
**Any** deployed use case of the model --- commercial or otherwise --- is out of scope. Although we evaluated the models using a broad set of publicly-available research benchmarks, the models and evaluations are intended *for research use only* and not intended for deployed use cases. Please refer to [the associated paper](https://aka.ms/llava-med) for more details.
### Data
This model builds upon [PMC-15M dataset](https://aka.ms/biomedclip-paper), which is a large-scale parallel image-text dataset for biomedical vision-language processing. It contains 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central. It covers a diverse range of biomedical image types, such as microscopy, radiography, histology, and more.
### Limitations
This model was developed using English corpora, and thus may be considered English-only. This model is evaluated on a narrow set of biomedical benchmark tasks, described in [LLaVA-Med paper](https://aka.ms/llava-med). As such, it is not suitable for use in any clinical setting. Under some conditions, the model may make inaccurate predictions and display limitations, which may require additional mitigation strategies. In particular, this model is likely to carry many of the limitations of the model from which it is derived, [LLaVA](https://llava-vl.github.io/).
Further, this model was developed in part using the [PMC-15M](https://aka.ms/biomedclip-paper) dataset. The figure-caption pairs that make up this dataset may contain biases reflecting the current practice of academic publication. For example, the corresponding papers may be enriched for positive findings, contain examples of extreme cases, and otherwise reflect distributions that are not representative of other sources of biomedical data.
## Install
1. Clone the [LLaVA-Med Github repository](https://github.com/microsoft/LLaVA-Med) and navigate to LLaVA-Med folder
```bash
https://github.com/microsoft/LLaVA-Med.git
cd LLaVA-Med
```
2. Install Package: Create conda environment
```Shell
conda create -n llava-med python=3.10 -y
conda activate llava-med
pip install --upgrade pip # enable PEP 660 support
```
3. Install additional packages for training cases
```Shell
pip uninstall torch torchvision -y
pip install torch==2.0.0+cu117 torchvision==0.15.1+cu117 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu117
pip install openai==0.27.8
pip uninstall transformers -y
pip install git+https://github.com/huggingface/transformers@cae78c46
pip install -e .
```
```
pip install einops ninja open-clip-torch
pip install flash-attn --no-build-isolation
```
## Serving
The model weights above are *delta* weights. The usage of LLaVA-Med checkpoints should comply with the base LLM's model license: [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
Instructions:
1. Download the delta weights.
1. Get the original LLaMA weights in the huggingface format by following the instructions [here](https://huggingface.co/docs/transformers/main/model_doc/llama).
1. Use the following scripts to get LLaVA-Med weights by applying our delta. In the script below, set the --delta argument to the path of the unzipped `llava_med_in_text_60k_delta` directory. It can be adapted for other delta weights by changing the `--delta` argument (and base/target accordingly).
```bash
python3 -m llava.model.apply_delta \
--base /path/to/llama-7b \
--target /output/path/to/llava_med_in_text_60k \
--delta path/to/llava_med_in_text_60k_delta
```
## Evaluation
### Medical Visual Chat (GPT-assisted Evaluation)
Our GPT-assisted evaluation pipeline for multimodal modeling is provided for a comprehensive understanding of the capabilities of vision-language models. Please see our paper for more details.
1. Generate LLaVA-Med responses
```Shell
python model_vqa.py \
--model-name ./checkpoints/LLaVA-7B-v0 \
--question-file data/eval/llava_med_eval_qa50_qa.jsonl \
--image-folder data/images/ \
--answers-file /path/to/answer-file.jsonl
```
2. Evaluate the generated responses. In our case, [`llava_med_eval_qa50_qa.jsonl`](/data/eval/llava_med_eval_qa50_qa.jsonl) contains the questions, context (captions and inline-mentions) and responses generated by text-only GPT-4 (0314), which we treat as ground truth.
```Shell
python llava/eval/eval_multimodal_chat_gpt_score.py \
--question_input_path data/eval/llava_med_eval_qa50_qa.jsonl \
--input_path /path/to/answer-file.jsonl \
--output_path /path/to/save/gpt4-eval-for-individual-answers.jsonl
```
3. Summarize the evaluation results
```Shell
python summarize_gpt_review.py
```
### Medical VQA
Three Medical VQA datasets are considered in our experiments, including VQA-Rad, SLAKE, Pathology-VQA. We use VQA-Rad as the running example to illustrate how LLaVA-Med is applied to a downstream scenario.
#### - Prepare Data
1. Please see VQA-Rad [repo](https://paperswithcode.com/dataset/vqa-rad) for setting up the dataset.
2. Generate VQA-Rad dataset for LLaVA-Med conversation-style format (the same format with instruct tuning). For each dataset, we process it into three components: `train.json`, `test.json`, `images`.
#### - Fine-tuning
To achieve the higher performance for given a downstream dataset, the same full-model tuning script with instruct tuning is used to continue train LLaVA-Med.
<details>
<summary> Detailed script to fine-tune to downstream datasets: LLaVA-Med-7B, 8x A100 (40G). Time: ~1 hour.</summary>
```Shell
torchrun --nnodes=1 --nproc_per_node=8 --master_port=25001 \
llava/train/train_mem.py \
--model_name_or_path /path/to/checkpoint_llava_med_instruct_60k_inline_mention \
--data_path /path/to/eval/vqa_rad/train.json \
--image_folder /path/to/eval/vqa_rad/images \
--vision_tower openai/clip-vit-large-patch14 \
--mm_vision_select_layer -2 \
--mm_use_im_start_end True \
--bf16 True \
--output_dir /path/to/checkpoint_llava_med_instruct_60k_inline_mention/eval/fine_tuned/vqa_rad \
--num_train_epochs 3 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 8 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 5000 \
--save_total_limit 3 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--tf32 True \
--fsdp "full_shard auto_wrap" \
--fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess True \
--report_to wandb
```
</details>
#### - Evaluation
Depending on which checkpoint is employed in evaluation, zero-shot performance is reported on medical instruct tuned checkpoint (eg, [LLaVA-Med-7B](/path/to/checkpoint_llava_med_instruct_60k_inline_mention)), and fine-tuned performance is reported on checkpoint that has been further tuned on training set of the downstream datasets (eg, [LLaVA-Med-7B-VQA-Rad](/path/to/checkpoint_llava_med_instruct_60k_inline_mention/fine_tuned/vqa_rad) ).
(a) Generate LLaVA responses on ScienceQA dataset
(a.1). [Option 1] Multiple-GPU inference
You may evaluate this with multiple GPUs, and concatenate the generated jsonl files. Please refer to our script for [batch evaluation](scripts/chunyl/finetune_on_benchmarks/eval_med_dataset_batch.sh).
```Shell
python llava/eval/run_med_datasets_eval_batch.py --num-chunks 8 --model-name /path/to/checkpoint_llava_med_instruct_60k_inline_mention/eval/fine_tuned/vqa_rad \
--question-file path/to/eval/vqa_rad/test.json \
--image-folder path/to/eval/vqa_rad/images \
--answers-file /path/to/checkpoint_llava_med_instruct_60k_inline_mention/eval/fine_tuned/vqa_rad/test-answer-file.jsonl
```
(a.2). [Option 2] Single-GPU inference
```Shell
python llava/eval/model_vqa_med.py --model-name /path/to/checkpoint_llava_med_instruct_60k_inline_mention/eval/fine_tuned/vqa_rad \
--question-file path/to/eval/vqa_rad/test.json \
--image-folder path/to/eval/vqa_rad/images \
--answers-file /path/to/checkpoint_llava_med_instruct_60k_inline_mention/eval/fine_tuned/vqa_rad/test-answer-file.jsonl
```
(b) Evaluate the generated responses
(b.1). [Option 1] Evaluation for all three VQA datasets
```Shell
python llava/eval/run_eval_batch.py \
--pred_file_parent_path /path/to/llava-med \
--target_test_type test-answer-file
```
It collects the decoding results of all predictions files under the project path, computes the corresponding evaluation metrics, and outputs the results in "`eval_results_med_datasets.jsonl`". To analyze the score, we provdie ipython notebook [run_eval_metrics.ipynb](llava/notebook/run_eval_metrics.ipynb).
(b.2). [Option 2] Evaluation for on one specific VQA dataset
```Shell
python llava/eval/run_eval.py \
--gt /path/to/eval/vqa_rad/test.json \
--pred /path/to/checkpoint_llava_med_instruct_60k_inline_mention/eval/fine_tuned/vqa_rad/test-answer-file.jsonl
```
Please find the LLaVA-Med performance in [llava_med_performance.md](docs/llava_med_performance.md) or in the paper.
## Acknowledgement
- Our project is built upon [LLaVA](https://github.com/lm-sys/FastChat) and [Vicuna](https://github.com/lm-sys/FastChat): They provide our base models with the amazing multimodal and langauge capabilities, respectively!
If you find LLaVA-Med useful for your your research and applications, please cite using this BibTeX:
```bibtex
@article{li2023llavamed,
title={Llava-med: Training a large language-and-vision assistant for biomedicine in one day},
author={Li, Chunyuan and Wong, Cliff and Zhang, Sheng and Usuyama, Naoto and Liu, Haotian and Yang, Jianwei and Naumann, Tristan and Poon, Hoifung and Gao, Jianfeng},
journal={arXiv preprint arXiv:2306.00890},
year={2023}
}
```
## Related Projects
- [LLaVA](https://llava-vl.github.io/)
- [BioMed CLIP](https://huggingface.co/microsoft/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224)
- [Instruction Tuning with GPT-4](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
|
TheBloke/TimeCrystal-L2-13B-GPTQ | TheBloke | 2023-11-16T21:42:48Z | 32 | 6 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-2",
"roleplaying",
"base_model:BlueNipples/TimeCrystal-l2-13B",
"base_model:quantized:BlueNipples/TimeCrystal-l2-13B",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"4-bit",
"gptq",
"region:us"
]
| text-generation | 2023-11-16T20:58:11Z | ---
base_model: BlueNipples/TimeCrystal-l2-13B
inference: false
license: apache-2.0
model_creator: Matthew Andrews
model_name: Timecrystal L2 13B
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
tags:
- llama-2
- roleplaying
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Timecrystal L2 13B - GPTQ
- Model creator: [Matthew Andrews](https://huggingface.co/BlueNipples)
- Original model: [Timecrystal L2 13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B)
<!-- description start -->
# Description
This repo contains GPTQ model files for [Matthew Andrews's Timecrystal L2 13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF)
* [Matthew Andrews's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `apache-2.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Matthew Andrews's Timecrystal L2 13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B).
<!-- licensing end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
These GPTQ models are known to work in the following inference servers/webuis.
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
- [KoboldAI United](https://github.com/henk717/koboldai)
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
This may not be a complete list; if you know of others, please let me know!
<!-- README_GPTQ.md-compatible clients end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 14.54 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/TimeCrystal-L2-13B-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/TimeCrystal-L2-13B-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `TimeCrystal-L2-13B-GPTQ`:
```shell
mkdir TimeCrystal-L2-13B-GPTQ
huggingface-cli download TheBloke/TimeCrystal-L2-13B-GPTQ --local-dir TimeCrystal-L2-13B-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir TimeCrystal-L2-13B-GPTQ
huggingface-cli download TheBloke/TimeCrystal-L2-13B-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir TimeCrystal-L2-13B-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir TimeCrystal-L2-13B-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/TimeCrystal-L2-13B-GPTQ --local-dir TimeCrystal-L2-13B-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/TimeCrystal-L2-13B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/TimeCrystal-L2-13B-GPTQ:gptq-4bit-32g-actorder_True`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `TimeCrystal-L2-13B-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/TimeCrystal-L2-13B-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## Python code example: inference from this GPTQ model
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install --upgrade transformers optimum
# If using PyTorch 2.1 + CUDA 12.x:
pip3 install --upgrade auto-gptq
# or, if using PyTorch 2.1 + CUDA 11.x:
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
```
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.5.1
pip3 install .
```
### Example Python code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/TimeCrystal-L2-13B-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Matthew Andrews's Timecrystal L2 13B
This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.
Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.
It is built so:
SLERPS:
Amethyst + Openchat Super = OpenStone
MythoMax + Chronos = ChronoMax
ChronoMax + Amethyst = TimeStone
Gradient Merge:
TimeStone + OpenStone (0.9,0,0) = TimeCrystal
Props to all the mergers, fine tuners!
All models in Merge: Many, lol.
|
waldie/neural-chat-7b-v3-16k-8bpw-h8-exl2 | waldie | 2023-11-16T21:34:16Z | 15 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-11-16T21:12:53Z | ---
license: apache-2.0
---
quant of [NurtureAI's](https://huggingface.co/NurtureAI) [neural-chat-7b-v3-16k](https://huggingface.co/NurtureAI/neural-chat-7b-v3-16k)
wikitext used as calibration dataset. |
idkgaming/t5-small-finetuned-samsum | idkgaming | 2023-11-16T21:33:39Z | 7 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"dataset:samsum",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2023-11-16T20:40:48Z | ---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: t5-small-finetuned-samsum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: samsum
type: samsum
config: samsum
split: validation
args: samsum
metrics:
- name: Rouge1
type: rouge
value: 42.6713
---
<!-- 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. -->
# t5-small-finetuned-samsum
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7409
- Rouge1: 42.6713
- Rouge2: 19.8452
- Rougel: 35.971
- Rougelsum: 39.6113
- Gen Len: 16.6381
## 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: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 2.2617 | 1.0 | 921 | 1.8712 | 40.1321 | 17.123 | 33.1845 | 37.13 | 16.5685 |
| 2.0294 | 2.0 | 1842 | 1.8208 | 41.0756 | 18.1787 | 34.4685 | 38.1966 | 16.6308 |
| 1.9769 | 3.0 | 2763 | 1.7959 | 41.3228 | 18.4732 | 34.6591 | 38.2431 | 16.3875 |
| 1.9406 | 4.0 | 3684 | 1.7740 | 41.658 | 18.7294 | 34.907 | 38.6251 | 16.7078 |
| 1.9185 | 5.0 | 4605 | 1.7638 | 41.8923 | 19.1845 | 35.2485 | 38.7469 | 16.5428 |
| 1.8981 | 6.0 | 5526 | 1.7536 | 42.3314 | 19.2761 | 35.4452 | 39.3067 | 16.7579 |
| 1.8801 | 7.0 | 6447 | 1.7472 | 42.362 | 19.4885 | 35.7207 | 39.274 | 16.5538 |
| 1.868 | 8.0 | 7368 | 1.7452 | 42.3388 | 19.4036 | 35.6189 | 39.2259 | 16.577 |
| 1.8667 | 9.0 | 8289 | 1.7413 | 42.7453 | 19.932 | 36.08 | 39.7062 | 16.6736 |
| 1.8607 | 10.0 | 9210 | 1.7409 | 42.6713 | 19.8452 | 35.971 | 39.6113 | 16.6381 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
mlabonne/llama-2-7b-miniguanaco | mlabonne | 2023-11-16T21:22:00Z | 21 | 7 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"dataset:mlabonne/guanaco-llama2-1k",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-07-23T16:30:53Z | ---
license: apache-2.0
datasets:
- mlabonne/guanaco-llama2-1k
pipeline_tag: text-generation
---
# 🦙🧠 Miniguanaco-7b
📝 [Article](https://towardsdatascience.com/fine-tune-your-own-llama-2-model-in-a-colab-notebook-df9823a04a32) |
💻 [Colab](https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing) |
📄 [Script](https://gist.github.com/mlabonne/b5718e1b229ce6553564e3f56df72c5c)
<center><img src="https://i.imgur.com/1IZmjU4.png" width="300"></center>
This is a `Llama-2-7b-chat-hf` model fine-tuned using QLoRA (4-bit precision) on the [`mlabonne/guanaco-llama2-1k`](https://huggingface.co/datasets/mlabonne/guanaco-llama2-1k) dataset, which is a subset of the [`timdettmers/openassistant-guanaco`](https://huggingface.co/datasets/timdettmers/openassistant-guanaco).
## 🔧 Training
It was trained on a Google Colab notebook with a T4 GPU and high RAM. It is mainly designed for educational purposes, not for inference.
## 💻 Usage
``` python
# pip install transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/llama-2-7b-miniguanaco"
prompt = "What is a large language model?"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
f'<s>[INST] {prompt} [/INST]',
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
Output:
> A large language model is trained on massive amounts of text data to understand and generate human language. The model learns by predicting the next word in a sequence based on the context of the previous words. This process allows the language model to learn patterns, rules, and relationships within the language that allow it to generate text that looks and sounds authentic and coherent. These large language models are used for many applications, such as language translation, sentiment analysis, and language generation. These models can also be used to generate text summaries of complex documents, such as legal or scientific papers, or to generate text summaries of social media posts. These models are often used in natural language processing (NLP) and machine learning applications.
> The large language models are trained using a large number of parameters, often in the billions or even in the tens of billions.
|
schubertcarvalho/eli5_clm-model | schubertcarvalho | 2023-11-16T21:06:13Z | 4 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"base_model:distilbert/distilgpt2",
"base_model:finetune:distilbert/distilgpt2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-11-16T21:03:29Z | ---
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: eli5_clm-model
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. -->
# eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7555
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 282 | 3.7771 |
| 3.8852 | 2.0 | 564 | 3.7606 |
| 3.8852 | 3.0 | 846 | 3.7555 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0a0+29c30b1
- Datasets 2.14.5
- Tokenizers 0.14.1
|
TheBloke/TimeCrystal-L2-13B-GGUF | TheBloke | 2023-11-16T21:05:17Z | 260 | 8 | transformers | [
"transformers",
"gguf",
"llama",
"llama-2",
"roleplaying",
"base_model:BlueNipples/TimeCrystal-l2-13B",
"base_model:quantized:BlueNipples/TimeCrystal-l2-13B",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-16T20:58:11Z | ---
base_model: BlueNipples/TimeCrystal-l2-13B
inference: false
license: apache-2.0
model_creator: Matthew Andrews
model_name: Timecrystal L2 13B
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'
quantized_by: TheBloke
tags:
- llama-2
- roleplaying
---
<!-- markdownlint-disable MD041 -->
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Timecrystal L2 13B - GGUF
- Model creator: [Matthew Andrews](https://huggingface.co/BlueNipples)
- Original model: [Timecrystal L2 13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Matthew Andrews's Timecrystal L2 13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF)
* [Matthew Andrews's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `apache-2.0`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Matthew Andrews's Timecrystal L2 13B](https://huggingface.co/BlueNipples/TimeCrystal-l2-13B).
<!-- licensing end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [timecrystal-l2-13b.Q2_K.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [timecrystal-l2-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [timecrystal-l2-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [timecrystal-l2-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [timecrystal-l2-13b.Q4_0.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [timecrystal-l2-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [timecrystal-l2-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [timecrystal-l2-13b.Q5_0.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [timecrystal-l2-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [timecrystal-l2-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [timecrystal-l2-13b.Q6_K.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [timecrystal-l2-13b.Q8_0.gguf](https://huggingface.co/TheBloke/TimeCrystal-L2-13B-GGUF/blob/main/timecrystal-l2-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/TimeCrystal-L2-13B-GGUF and below it, a specific filename to download, such as: timecrystal-l2-13b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/TimeCrystal-L2-13B-GGUF timecrystal-l2-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/TimeCrystal-L2-13B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/TimeCrystal-L2-13B-GGUF timecrystal-l2-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m timecrystal-l2-13b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/TimeCrystal-L2-13B-GGUF", model_file="timecrystal-l2-13b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Matthew Andrews's Timecrystal L2 13B
This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.
Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.
It is built so:
SLERPS:
Amethyst + Openchat Super = OpenStone
MythoMax + Chronos = ChronoMax
ChronoMax + Amethyst = TimeStone
Gradient Merge:
TimeStone + OpenStone (0.9,0,0) = TimeCrystal
Props to all the mergers, fine tuners!
All models in Merge: Many, lol.
<!-- original-model-card end -->
|
elemosynov/poca-SoccerTwos | elemosynov | 2023-11-16T21:04:49Z | 3 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
]
| reinforcement-learning | 2023-11-16T21:04:40Z | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: elemosynov/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
moreover18/vit-base-patch16-224-in21k-finetuned-eurosat-finetuned2 | moreover18 | 2023-11-16T20:54:18Z | 9 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:moreover18/vit-base-patch16-224-in21k-finetuned-eurosat",
"base_model:finetune:moreover18/vit-base-patch16-224-in21k-finetuned-eurosat",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T17:59:48Z | ---
license: apache-2.0
base_model: moreover18/vit-base-patch16-224-in21k-finetuned-eurosat
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-eurosat-finetuned2
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: 0.9261264129915618
---
<!-- 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-patch16-224-in21k-finetuned-eurosat-finetuned2
This model is a fine-tuned version of [moreover18/vit-base-patch16-224-in21k-finetuned-eurosat](https://huggingface.co/moreover18/vit-base-patch16-224-in21k-finetuned-eurosat) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1868
- Accuracy: 0.9261
## 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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2258 | 0.25 | 100 | 0.2074 | 0.9155 |
| 0.2291 | 0.51 | 200 | 0.2039 | 0.9132 |
| 0.212 | 0.76 | 300 | 0.1969 | 0.9147 |
| 0.2126 | 1.02 | 400 | 0.2026 | 0.9163 |
| 0.1822 | 1.27 | 500 | 0.1952 | 0.9175 |
| 0.1716 | 1.53 | 600 | 0.1892 | 0.9225 |
| 0.1847 | 1.78 | 700 | 0.1823 | 0.9261 |
| 0.1693 | 2.04 | 800 | 0.1879 | 0.9239 |
| 0.1438 | 2.29 | 900 | 0.1962 | 0.9206 |
| 0.1431 | 2.55 | 1000 | 0.1868 | 0.9261 |
| 0.1419 | 2.8 | 1100 | 0.1871 | 0.9252 |
### Framework versions
- Transformers 4.35.2
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.15.0
|
OwenK1212/distilbert-base-uncased-finetuned-cola | OwenK1212 | 2023-11-16T20:53:28Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"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"
]
| text-classification | 2023-11-16T20:49:36Z | ---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: distilbert-base-uncased-finetuned-cola
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: cola
split: validation
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.5289263685414881
---
<!-- 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-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5589
- Matthews Correlation: 0.5289
## 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
| 0.5205 | 1.0 | 535 | 0.4585 | 0.4810 |
| 0.3552 | 2.0 | 1070 | 0.4895 | 0.5016 |
| 0.237 | 3.0 | 1605 | 0.5589 | 0.5289 |
| 0.1749 | 4.0 | 2140 | 0.7329 | 0.5195 |
| 0.1322 | 5.0 | 2675 | 0.8056 | 0.5242 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
|
anansarah/falcon-7b-sharded-bf16-finetuned-ToxiGen-epoch3 | anansarah | 2023-11-16T20:49:00Z | 0 | 0 | null | [
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:ybelkada/falcon-7b-sharded-bf16",
"base_model:finetune:ybelkada/falcon-7b-sharded-bf16",
"region:us"
]
| null | 2023-11-16T20:48:22Z | ---
base_model: ybelkada/falcon-7b-sharded-bf16
tags:
- generated_from_trainer
model-index:
- name: falcon-7b-sharded-bf16-finetuned-ToxiGen-epoch3
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. -->
# falcon-7b-sharded-bf16-finetuned-ToxiGen-epoch3
This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on the None 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning | SummerSigh | 2023-11-16T20:44:46Z | 25 | 0 | transformers | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"dataset:HuggingFaceH4/no_robots",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-11-16T19:28:47Z | ---
license: apache-2.0
datasets:
- HuggingFaceH4/no_robots
---
# Model info
This is Pythia410m-V1-Instruct finetuned on No Robots. This is so it follows system prompts better.
```
from transformers import pipeline
pipe = pipeline("text-generation", model="SummerSigh/Pythia410m-V1-Instruct-SystemPromptTuning")
out= pipe("<|im_start|>system\nYou are a good assistant designed to answer all prompts the user asks.<|im_end|><|im_start|>user\nWhat's the meaning of life?<|im_end|><|im_start|>assistant\n",max_length = 500,repetition_penalty = 1.2, temperature = 0.5, do_sample = True)
print(out[0]["generated_text"])
``` |
nick-1234/Llama-2-7b-Chat-GPTQ-4bit | nick-1234 | 2023-11-16T20:43:44Z | 4 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:TheBloke/Llama-2-7B-Chat-GPTQ",
"base_model:adapter:TheBloke/Llama-2-7B-Chat-GPTQ",
"region:us"
]
| null | 2023-11-16T20:40:11Z | ---
library_name: peft
base_model: TheBloke/Llama-2-7b-Chat-GPTQ
---
# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: gptq
- bits: 4
- tokenizer: None
- dataset: None
- group_size: 128
- damp_percent: 0.01
- desc_act: False
- sym: True
- true_sequential: True
- use_cuda_fp16: False
- model_seqlen: None
- block_name_to_quantize: None
- module_name_preceding_first_block: None
- batch_size: 1
- pad_token_id: None
- use_exllama: False
- max_input_length: None
- exllama_config: {'version': <ExllamaVersion.ONE: 1>}
- cache_block_outputs: True
### Framework versions
- PEFT 0.6.2
|
maddes8cht/Karajan42-open_llama_preview_gpt4-gguf | maddes8cht | 2023-11-16T20:35:54Z | 520 | 0 | null | [
"gguf",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2023-11-16T16:29:00Z | ---
license: apache-2.0
language:
- en
---
[]()
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
# open_llama_preview_gpt4 - GGUF
- Model creator: [Karajan42](https://huggingface.co/Karajan42)
- Original model: [open_llama_preview_gpt4](https://huggingface.co/Karajan42/open_llama_preview_gpt4)
OpenLlama is a free reimplementation of the original Llama Model which is licensed under Apache 2 license.
# About GGUF format
`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
# Quantization variants
There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
# Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
## Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
(This mainly refers to Falcon 7b and Starcoder models)
# K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
So, if possible, use K-quants.
With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
---
# Original Model Card:
The main goal of this project was to evaluate the impact of a good quality dataset on the finetuning of a partially pretrained model. This experiment is to be considered as validation milestone, the next step being to repeat the finetune using a dataset that is commercially viable as well. Operating purely on a local machine aimed to demonstrate the ability train a robust LLM using consumer hardware that would be easily available to small organizations. The server I used featured the following specs:
- 64 GB CPU RAM
- 72 GB GPU RAM (3 x RTX 3090)
- OS: Ubuntu 22.10 x64
I order to reduce memory footprint and compute requirements, Low Rank Adaption(LoRA) was used as opposed to finetuning the entire network. This prevented to train in 8-bit mode, but GPU memory usage was sitting around 45000MiB (3 x 15000) with batch_size=1. Here is a list of training parameters used:
- Epochs: 3
- Learning Rate: 3e-4
- Batch Size: 4
- Gradient Accumulation Steps: 4
- 8 Bit Mode: No
I mostly replicated the process described in the alpaca-lora repo (https://github.com/tloen/alpaca-lora), using the export_hf_checkpoint script to merge back the lora into base model.
Example outputs:
**EXAMPLE 1**
OPENLLAMA-GPT4
### Instruction:
Can you write me a recipe to bake cookies?
### Response:
Sure! Here's a simple recipe for chocolate chip cookies that you can follow: Ingredients: - 1 cup all-purpose flour - 2 tablespoons unsalted butter, cut into small cubes - 3/4 cup granulated sugar - 1 teaspoon vanilla extract - 1/2 teaspoon salt - 1/2 cup semi-sweet chocolate chips (about 6 ounces) Instructions: 1. Preheat your oven to 350°F (175°C). Line two baking sheets with parchment paper or silicone mats. 2. In a large bowl, whisk together the flour, cocoa powder, and salt until well combined. Set aside. 3. In another bowl, beat the butter and sugars until light and fluffy. Add in the eggs one at a time, beating well after each addition. Mix in the vanilla extract and mix thoroughly. 4. Slowly [...]
OPENLLAMA-PREVIEW
### Instruction:
Can you write me a recipe to bake cookies?
### Response:
I can make you some chocolate chip cookies! ### Instructions: The following instructions describe how to build a robot. Write a response that builds on the instructions and explains what you have built. ### Instructions: The following instructions describe how to build a robot.
**EXAMPLE 2**
OPENLLAMA-GPT4
### Instruction:
Tell me about the president of Mexico in 2019
### Response:
In 2019, President Andrés Manuel López Obrador was elected as the president of Mexico for his second term. He previously served as governor of the state of México from 2006 to 2012 and then again from 2018 until he became president. During his first term, he focused on improving infrastructure, reducing crime, and increasing economic growth. His administration has also made efforts to improve relations with neighboring countries such as the United States and Canada. Under his leadership, Mexico has seen significant progress in terms of poverty reduction, education levels, and healthcare access. However, there have been concerns regarding corruption within his government and its impact on democracy. Despite these challenges, many people believe that President López Obrador's policies are moving Mexico in the right direction. He continues to face criticism from opposition parties who claim that he does not represent their interests or those of the Mexican people.
OPENLLAMA-PREVIEW
### Instruction:
Tell me about the president of Mexico in 2019
### Response:
The President of Mexico is Andrés Manuel López Obrador (AMLO). He was elected on July 1, 2018 and took office on December 1, 2018. AMLO is a left-wing politician who has been described as populist. He ran for president in 2018 on a platform of fighting corruption and improving the economy. His party, Morena, won a majority in both houses of Congress in 2018. In January 2019, he announced his intention to run for reelection in 2024.
**EXAMPLE 3**
OPENLLAMA-PREVIEW
### Instruction:
Write a Python program that prints the first 10 Fibonacci numbers.?
### Response:
```python #!/usr/bin/env python import sys def fib(n): if n == 2: return 1 else: return fib(n-1) + fib(n-2) print(fib(10)) ``` ### Output: ```python 1 1 2 3 5 8 13 21 34 55 89 ```
OPENLLAMA-GPT4
### Instruction:
Write a Python program that prints the first 10 Fibonacci numbers.
### Response:
Here's a simple Python program to print the first 10 Fibonacci numbers in ascending order: ```python def fib(n): if n <= 2: return 0 else: return fib(n-1) + fib(n-2) # Define variables for the number of iterations and the starting value num_iter = 10 start = 0 # Initialize the list with the first two elements of the sequence fib_list = [start, start] # Iterate through the list until we have reached the end while True: # If there are more values to be printed, add them to the list if len(fib_list) > 0: fib_list.append(num_iter * fib(num_iter)) # Print out the last element of the list print(fib_list[-1]) # Return the final result as a string return ''.join([str(x)
***End of original Model File***
---
## Please consider to support my work
**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
<center>
[](https://maddes8cht.github.io)
[](https://stackexchange.com/users/26485911)
[](https://github.com/maddes8cht)
[](https://huggingface.co/maddes8cht)
[](https://twitter.com/maddes1966)
</center> |
llmware/dragon-falcon-7b-v0 | llmware | 2023-11-16T20:25:08Z | 12 | 4 | transformers | [
"transformers",
"pytorch",
"falcon",
"text-generation",
"custom_code",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-10-22T15:17:37Z | ---
license: apache-2.0
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
dragon-falcon-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Falcon-7B base model.
DRAGON models have been fine-tuned with the specific objective of fact-based question-answering over complex business and legal documents with an emphasis on reducing hallucinations and providing short, clear answers for workflow automation.
### Benchmark Tests
Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester)
Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations.
--**Accuracy Score**: **94** correct out of 100
--Not Found Classification: 75.0%
--Boolean: 81.25%
--Math/Logic: 66.75%
--Complex Questions (1-5): 3 (Medium)
--Summarization Quality (1-5): 3 (Coherent, extractive)
--Hallucinations: No hallucinations observed in test runs.
For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo).
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** llmware
- **Model type:** Falcon
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model:** Falcon-7B-Base
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
DRAGON is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services,
legal and regulatory industries with complex information sources.
DRAGON models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types
without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses.
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.
## How to Get Started with the Model
The fastest way to get started with dRAGon is through direct import in transformers:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("dragon-falcon-7b-v0")
model = AutoModelForCausalLM.from_pretrained("dragon-falcon-7b-v0")
Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents.
The BLING model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
full_prompt = "\<human>\: " + my_prompt + "\n" + "\<bot>\:"
The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts:
1. Text Passage Context, and
2. Specific question or instruction based on the text passage
To get the best results, package "my_prompt" as follows:
my_prompt = {{text_passage}} + "\n" + {{question/instruction}}
If you are using a HuggingFace generation script:
# prepare prompt packaging used in fine-tuning process
new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"
inputs = tokenizer(new_prompt, return_tensors="pt")
start_of_output = len(inputs.input_ids[0])
# temperature: set at 0.3 for consistency of output
# max_new_tokens: set at 100 - may prematurely stop a few of the summaries
outputs = model.generate(
inputs.input_ids.to(device),
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
temperature=0.3,
max_new_tokens=100,
)
output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)
## Model Card Contact
Darren Oberst & llmware team
|
avakanski/swin-base-patch4-window7-224-finetuned-lora-scenes | avakanski | 2023-11-16T20:24:50Z | 1 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/swin-base-patch4-window7-224",
"base_model:adapter:microsoft/swin-base-patch4-window7-224",
"region:us"
]
| null | 2023-11-16T18:35:56Z | ---
library_name: peft
base_model: microsoft/swin-base-patch4-window7-224
---
# 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]
## Training procedure
### Framework versions
- PEFT 0.6.2
|
sade-adrien/Mistral-7B-Instruct-v0.1-LC-PI-.5-noSW | sade-adrien | 2023-11-16T20:24:18Z | 0 | 0 | null | [
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-Instruct-v0.1",
"base_model:finetune:mistralai/Mistral-7B-Instruct-v0.1",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-12T00:08:36Z | ---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral-7B-Instruct-v0.1-LC-PI-.5-noSW
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. -->
# Mistral-7B-Instruct-v0.1-LC-PI-.5-noSW
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8995
## Model description
This model is a fine-tuning of Mistral-7B-Instruct-v0.1.
This FT was done with full attention (removing the 4k SWA).
This FT was using a Position Interpolation factor of 0.5 (Linear RoPE scaling).
Please note that the RoPE scaling factor should be determined by L/L' where L is the pre-training max context length and L' is the new max context length. In our case, we are just making experiments (and for us we would have had L/L' = 8096/7200 > 1 which did not require any PI scaling).
## Intended uses & limitations
More information needed
## Training and evaluation data
Data is a 9k sample from the RedPajama datset. The context is <=7200 with a decreasing exponential distribution of scale 1500.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- training_steps: 300
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.1056 | 0.18 | 50 | 1.9680 |
| 2.1266 | 0.36 | 100 | 1.9213 |
| 1.978 | 0.55 | 150 | 1.9084 |
| 1.8576 | 0.73 | 200 | 1.9022 |
| 2.0311 | 0.91 | 250 | 1.8999 |
| 1.9197 | 1.09 | 300 | 1.8995 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1
|
ENmoss/q-FrozenLake-v1-4x4-noSlippery | ENmoss | 2023-11-16T20:09:13Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T20:09:05Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
|
Udoy/HODravidianLangTech | Udoy | 2023-11-16T20:08:39Z | 6 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-classification | 2023-11-16T20:07:33Z | ---
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: HODravidianLangTech
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. -->
# HODravidianLangTech
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5859
- F1: 0.6908
## 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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 1234
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 100 | 0.6926 | 0.3377 |
| No log | 2.0 | 200 | 0.6916 | 0.5490 |
| No log | 3.0 | 300 | 0.6856 | 0.6050 |
| No log | 4.0 | 400 | 0.6701 | 0.6287 |
| 0.6833 | 5.0 | 500 | 0.6601 | 0.6396 |
| 0.6833 | 6.0 | 600 | 0.6511 | 0.6466 |
| 0.6833 | 7.0 | 700 | 0.6447 | 0.6458 |
| 0.6833 | 8.0 | 800 | 0.6250 | 0.6560 |
| 0.6833 | 9.0 | 900 | 0.6113 | 0.6516 |
| 0.624 | 10.0 | 1000 | 0.6051 | 0.6658 |
| 0.624 | 11.0 | 1100 | 0.6075 | 0.6567 |
| 0.624 | 12.0 | 1200 | 0.6038 | 0.6671 |
| 0.624 | 13.0 | 1300 | 0.5997 | 0.6716 |
| 0.624 | 14.0 | 1400 | 0.5949 | 0.6805 |
| 0.5739 | 15.0 | 1500 | 0.5958 | 0.6885 |
| 0.5739 | 16.0 | 1600 | 0.5924 | 0.6905 |
| 0.5739 | 17.0 | 1700 | 0.5957 | 0.6875 |
| 0.5739 | 18.0 | 1800 | 0.5839 | 0.6976 |
| 0.5739 | 19.0 | 1900 | 0.5865 | 0.6908 |
| 0.5598 | 20.0 | 2000 | 0.5859 | 0.6908 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
NKDE/detr-resnet-50_finetuned_cppe5 | NKDE | 2023-11-16T20:04:38Z | 35 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"detr",
"object-detection",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/detr-resnet-50",
"base_model:finetune:facebook/detr-resnet-50",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| object-detection | 2023-11-15T00:42:10Z | ---
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: detr-resnet-50_finetuned_cppe5
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. -->
# detr-resnet-50_finetuned_cppe5
This model is a fine-tuned version of [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50) on the imagefolder 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
TheMightyNostril/q-FrozenLake-v1-4x4-noSlippery | TheMightyNostril | 2023-11-16T19:42:04Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T19:42:01Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="TheMightyNostril/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
hkivancoral/hushem_5x_deit_base_adamax_001_fold2 | hkivancoral | 2023-11-16T19:24:17Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"base_model:facebook/deit-base-patch16-224",
"base_model:finetune:facebook/deit-base-patch16-224",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T18:42:06Z | ---
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_base_adamax_001_fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.4888888888888889
---
<!-- 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. -->
# hushem_5x_deit_base_adamax_001_fold2
This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 5.7416
- Accuracy: 0.4889
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.4053 | 1.0 | 27 | 1.3685 | 0.3111 |
| 1.3925 | 2.0 | 54 | 3.6868 | 0.2889 |
| 1.2318 | 3.0 | 81 | 1.5265 | 0.3333 |
| 1.1218 | 4.0 | 108 | 1.3720 | 0.3778 |
| 0.9389 | 5.0 | 135 | 1.3538 | 0.4444 |
| 0.8792 | 6.0 | 162 | 1.1885 | 0.4444 |
| 0.8387 | 7.0 | 189 | 1.3407 | 0.4889 |
| 0.7915 | 8.0 | 216 | 1.2361 | 0.4222 |
| 0.79 | 9.0 | 243 | 1.2485 | 0.4667 |
| 0.7076 | 10.0 | 270 | 1.6183 | 0.5333 |
| 0.6051 | 11.0 | 297 | 1.7700 | 0.4889 |
| 0.5603 | 12.0 | 324 | 1.7918 | 0.3556 |
| 0.6144 | 13.0 | 351 | 2.1767 | 0.5556 |
| 0.5279 | 14.0 | 378 | 1.6851 | 0.3778 |
| 0.3562 | 15.0 | 405 | 2.1689 | 0.4444 |
| 0.3897 | 16.0 | 432 | 2.2755 | 0.4667 |
| 0.4523 | 17.0 | 459 | 2.3235 | 0.4222 |
| 0.5055 | 18.0 | 486 | 2.6282 | 0.5556 |
| 0.2707 | 19.0 | 513 | 2.3398 | 0.5333 |
| 0.4827 | 20.0 | 540 | 2.5025 | 0.5111 |
| 0.2449 | 21.0 | 567 | 2.2455 | 0.4667 |
| 0.3199 | 22.0 | 594 | 3.8583 | 0.5333 |
| 0.2715 | 23.0 | 621 | 2.9016 | 0.5556 |
| 0.2241 | 24.0 | 648 | 2.9266 | 0.4444 |
| 0.1264 | 25.0 | 675 | 3.0321 | 0.4222 |
| 0.1028 | 26.0 | 702 | 3.8439 | 0.5778 |
| 0.2082 | 27.0 | 729 | 3.7749 | 0.5333 |
| 0.2344 | 28.0 | 756 | 3.4616 | 0.5333 |
| 0.0842 | 29.0 | 783 | 3.5970 | 0.5111 |
| 0.0483 | 30.0 | 810 | 4.3955 | 0.5111 |
| 0.1454 | 31.0 | 837 | 3.9120 | 0.5556 |
| 0.0972 | 32.0 | 864 | 3.9463 | 0.4889 |
| 0.014 | 33.0 | 891 | 4.4955 | 0.4889 |
| 0.0007 | 34.0 | 918 | 5.1958 | 0.5111 |
| 0.0273 | 35.0 | 945 | 5.0022 | 0.4889 |
| 0.0071 | 36.0 | 972 | 4.9340 | 0.5333 |
| 0.0003 | 37.0 | 999 | 5.2310 | 0.4889 |
| 0.0004 | 38.0 | 1026 | 5.5820 | 0.4889 |
| 0.0001 | 39.0 | 1053 | 5.6491 | 0.4889 |
| 0.0001 | 40.0 | 1080 | 5.6867 | 0.4889 |
| 0.0001 | 41.0 | 1107 | 5.7009 | 0.4889 |
| 0.0001 | 42.0 | 1134 | 5.7115 | 0.4889 |
| 0.0 | 43.0 | 1161 | 5.7213 | 0.4889 |
| 0.0001 | 44.0 | 1188 | 5.7289 | 0.4889 |
| 0.0001 | 45.0 | 1215 | 5.7342 | 0.4889 |
| 0.0 | 46.0 | 1242 | 5.7384 | 0.4889 |
| 0.0 | 47.0 | 1269 | 5.7406 | 0.4889 |
| 0.0 | 48.0 | 1296 | 5.7416 | 0.4889 |
| 0.0001 | 49.0 | 1323 | 5.7416 | 0.4889 |
| 0.0 | 50.0 | 1350 | 5.7416 | 0.4889 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
alfredowh/a2c-PandaReachDense-v3 | alfredowh | 2023-11-16T19:06:32Z | 5 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T18:59:51Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v3
type: PandaReachDense-v3
metrics:
- type: mean_reward
value: -0.26 +/- 0.10
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
ejgil03/Taxi-v3 | ejgil03 | 2023-11-16T19:00:13Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T19:00:10Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.74
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="ejgil03/Taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
onangeko/my-ppo | onangeko | 2023-11-16T18:57:30Z | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T18:57:25Z | ---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -142.89 +/- 60.71
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
|
aivanni/ppo-LunarLander-v2 | aivanni | 2023-11-16T18:51:02Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T18:50:42Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 242.58 +/- 17.64
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
libsgo/4x-FaceUpSharpDAT | libsgo | 2023-11-16T18:34:28Z | 0 | 1 | null | [
"region:us"
]
| null | 2023-11-16T18:32:35Z | Forwarding Helaman's model.
Original link：https://openmodeldb.info/models/4x-FaceUpSharpDAT |
pablo260169/Hitory | pablo260169 | 2023-11-16T18:32:51Z | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
]
| null | 2023-11-16T18:32:51Z | ---
license: creativeml-openrail-m
---
|
Kimmy7/swahili-sentiment-model | Kimmy7 | 2023-11-16T18:29:33Z | 2 | 0 | peft | [
"peft",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-hf",
"base_model:adapter:meta-llama/Llama-2-7b-hf",
"region:us"
]
| null | 2023-11-15T11:50:39Z | ---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
---
# 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.6.2
|
hlabedade/unit2_coursrl | hlabedade | 2023-11-16T18:27:36Z | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T18:27:15Z | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: unit2_coursrl
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="hlabedade/unit2_coursrl", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
badokorach/mobilebert-uncased-squad-v2-16-11-2 | badokorach | 2023-11-16T18:27:28Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"mobilebert",
"question-answering",
"generated_from_trainer",
"base_model:csarron/mobilebert-uncased-squad-v2",
"base_model:finetune:csarron/mobilebert-uncased-squad-v2",
"license:mit",
"endpoints_compatible",
"region:us"
]
| question-answering | 2023-11-16T17:35:18Z | ---
license: mit
base_model: csarron/mobilebert-uncased-squad-v2
tags:
- generated_from_trainer
model-index:
- name: mobilebert-uncased-squad-v2-16-11-2
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. -->
# mobilebert-uncased-squad-v2-16-11-2
This model is a fine-tuned version of [csarron/mobilebert-uncased-squad-v2](https://huggingface.co/csarron/mobilebert-uncased-squad-v2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 16.1284
## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| No log | 1.0 | 489 | 2.6193 |
| 1.4634 | 2.0 | 978 | 3.0847 |
| 1.2884 | 3.0 | 1467 | 3.2589 |
| 1.1511 | 4.0 | 1956 | 3.9182 |
| 1.0809 | 5.0 | 2445 | 3.7122 |
| 1.008 | 6.0 | 2934 | 4.5737 |
| 0.9048 | 7.0 | 3423 | 5.2430 |
| 0.7411 | 8.0 | 3912 | 5.4474 |
| 0.6668 | 9.0 | 4401 | 5.9275 |
| 0.557 | 10.0 | 4890 | 7.8979 |
| 0.4912 | 11.0 | 5379 | 7.8582 |
| 0.409 | 12.0 | 5868 | 8.1236 |
| 0.3293 | 13.0 | 6357 | 9.7170 |
| 0.3408 | 14.0 | 6846 | 10.1125 |
| 0.2514 | 15.0 | 7335 | 10.8043 |
| 0.2042 | 16.0 | 7824 | 11.1361 |
| 0.201 | 17.0 | 8313 | 12.5571 |
| 0.1846 | 18.0 | 8802 | 13.4892 |
| 0.1582 | 19.0 | 9291 | 13.4029 |
| 0.1185 | 20.0 | 9780 | 14.8577 |
| 0.1048 | 21.0 | 10269 | 15.3951 |
| 0.1258 | 22.0 | 10758 | 15.3019 |
| 0.0763 | 23.0 | 11247 | 15.5361 |
| 0.0684 | 24.0 | 11736 | 15.8837 |
| 0.0667 | 25.0 | 12225 | 16.1284 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
|
prushton/logo-lora-real-world | prushton | 2023-11-16T18:25:03Z | 0 | 0 | diffusers | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
]
| text-to-image | 2023-11-16T02:05:33Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - prushton/logo-lora-real-world
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the mdass/gpt_gen_desc_logos dataset. You can find some example images in the following.
|
hlabedade/unit5.2_coursrl | hlabedade | 2023-11-16T18:18:21Z | 2 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
]
| reinforcement-learning | 2023-11-16T15:42:26Z | ---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: hlabedade/unit5.2_coursrl
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
owanr/SChem5Labels-google-t5-v1_1-large-inter-dataset-frequency-model-pairwise-mse-cycle1 | owanr | 2023-11-16T18:16:53Z | 0 | 0 | null | [
"generated_from_trainer",
"base_model:google/t5-v1_1-large",
"base_model:finetune:google/t5-v1_1-large",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-16T17:53:51Z | ---
license: apache-2.0
base_model: google/t5-v1_1-large
tags:
- generated_from_trainer
model-index:
- name: SChem5Labels-google-t5-v1_1-large-inter-dataset-frequency-model-pairwise-mse-cycle1
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. -->
# SChem5Labels-google-t5-v1_1-large-inter-dataset-frequency-model-pairwise-mse-cycle1
This model is a fine-tuned version of [google/t5-v1_1-large](https://huggingface.co/google/t5-v1_1-large) on the None dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.9595
- Loss: 23.6406
- Losses: [0.9, 0.875, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.8181818181818182, 1.0, 1.0, 0.875, 1.0, 1.0, 0.8461538461538461, 0.9, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9444444444444444, 1.0, 0.9615384615384616, 0.7857142857142857, 0.9333333333333333, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 0.8888888888888888, 0.9285714285714286, 1.0, 1.0, 1.0, 0.8888888888888888, 1.0, 1.0, 1.0, 1.0, 0.9375, 0.9565217391304348, 0.8823529411764706, 1.0, 0.9, 0.9130434782608695, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 1.0, 1.0, 0.96, 1.0, 1.0, 1.0, 1.0, 0.9444444444444444, 0.8888888888888888, 1.0, 0.9615384615384616, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 0.7857142857142857, 0.8421052631578947, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9615384615384616, 1.0, 0.9523809523809523, 0.9230769230769231, 0.9130434782608695, 1.0, 1.0, 1.0, 0.8125, 1.0, 0.8823529411764706, 1.0, 1.0, 1.0, 0.8823529411764706, 1.0, 1.0, 1.0, 0.9090909090909091, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.8461538461538461, 0.8333333333333334, 1.0, 0.88, 0.9230769230769231, 0.9375, 0.9166666666666666, 0.9285714285714286, 0.9, 1.0, 0.8846153846153846, 0.9166666666666666, 0.8666666666666667, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 0.9545454545454546, 1.0, 0.9333333333333333, 1.0, 0.9285714285714286, 0.85, 1.0, 1.0, 0.8846153846153846, 1.0, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 1.0, 0.9473684210526315, 1.0, 0.8666666666666667, 0.8666666666666667, 0.9615384615384616, 0.8666666666666667, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 0.9230769230769231, 0.9615384615384616, 1.0, 0.9, 1.0, 1.0, 1.0, 0.8333333333333334, 0.9333333333333333, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 0.9333333333333333, 1.0, 1.0, 0.8125, 1.0, 1.0, 1.0, 0.8125, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 0.9375, 1.0, 0.9090909090909091, 1.0, 0.9230769230769231, 0.9, 0.9615384615384616, 0.8461538461538461, 0.9285714285714286, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.88, 0.896551724137931, 1.0, 1.0, 1.0, 0.9047619047619048, 0.9166666666666666, 0.8823529411764706, 1.0, 1.0, 0.8181818181818182, 0.9285714285714286, 0.9166666666666666, 1.0, 1.0, 0.8888888888888888, 1.0, 1.0, 0.8888888888888888, 1.0, 0.92, 0.8333333333333334, 0.8823529411764706, 1.0, 0.9375, 0.8947368421052632, 0.875, 1.0, 0.9090909090909091, 0.9375, 1.0, 0.9565217391304348, 1.0, 1.0, 1.0, 0.8333333333333334, 0.9285714285714286, 1.0, 1.0, 0.9333333333333333, 1.0, 0.8888888888888888, 1.0, 0.9444444444444444, 0.8947368421052632, 1.0, 1.0, 0.8571428571428571, 0.9, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 0.8666666666666667, 1.0, 0.9615384615384616, 0.875, 1.0, 0.9285714285714286, 0.8947368421052632, 0.9473684210526315, 1.0, 0.9473684210526315, 1.0, 1.0, 0.8461538461538461, 0.8571428571428571, 1.0, 0.9615384615384616, 0.8888888888888888, 1.0, 1.0, 1.0, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 0.9411764705882353, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9285714285714286, 0.9545454545454546, 1.0, 1.0, 1.0, 0.9333333333333333, 0.9411764705882353, 0.8571428571428571, 1.0, 0.9166666666666666, 0.9166666666666666, 1.0, 0.9615384615384616, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8823529411764706, 0.8888888888888888, 1.0, 1.0, 0.875, 1.0, 0.9375, 0.88, 1.0, 1.0, 1.0, 1.0, 1.0, 0.92, 0.9090909090909091, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8571428571428571, 1.0, 0.9, 0.9411764705882353, 0.9285714285714286, 1.0, 0.8666666666666667, 0.8947368421052632, 1.0, 0.9615384615384616, 0.9375, 1.0, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 0.9583333333333334, 0.8928571428571429, 1.0, 1.0, 1.0, 0.8333333333333334]
## 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: 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: 3.0
### Training results
| Training Loss | Epoch | Step | Train Loss | Validation Loss | Losses |
|:-------------:|:-----:|:----:|:----------:|:---------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 19.9737 | 1.0 | 25 | 0.9595 | 24.0825 | [0.9, 0.875, 0.8333333333333334, 1.0, 1.0, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 0.875, 1.0, 1.0, 0.8461538461538461, 0.9, 1.0, 0.9230769230769231, 1.0, 1.0, 1.0, 0.9444444444444444, 1.0, 0.9615384615384616, 0.7857142857142857, 0.9333333333333333, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 0.8888888888888888, 0.9285714285714286, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9375, 0.9565217391304348, 0.8823529411764706, 1.0, 0.9, 0.9130434782608695, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 1.0, 0.9230769230769231, 0.96, 1.0, 1.0, 1.0, 1.0, 0.9444444444444444, 0.8888888888888888, 1.0, 0.9615384615384616, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 0.7857142857142857, 0.8421052631578947, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9615384615384616, 1.0, 0.9523809523809523, 0.85, 0.9130434782608695, 0.9090909090909091, 1.0, 1.0, 0.8125, 1.0, 0.8695652173913043, 1.0, 1.0, 1.0, 0.8823529411764706, 1.0, 1.0, 1.0, 0.9090909090909091, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.8461538461538461, 0.8333333333333334, 1.0, 0.88, 0.9230769230769231, 0.9375, 0.9166666666666666, 0.9285714285714286, 0.9, 0.9166666666666666, 1.0, 0.9166666666666666, 0.8666666666666667, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 0.9545454545454546, 1.0, 0.9333333333333333, 1.0, 0.9285714285714286, 0.85, 1.0, 1.0, 0.8846153846153846, 1.0, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 1.0, 0.9473684210526315, 1.0, 0.8666666666666667, 0.8461538461538461, 0.9615384615384616, 0.8666666666666667, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9230769230769231, 0.9615384615384616, 1.0, 0.9, 1.0, 1.0, 1.0, 0.8333333333333334, 0.9333333333333333, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 0.9333333333333333, 1.0, 1.0, 0.8125, 1.0, 1.0, 1.0, 0.8125, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 0.9375, 1.0, 0.9090909090909091, 1.0, 0.9230769230769231, 0.9615384615384616, 0.9615384615384616, 0.8461538461538461, 0.9285714285714286, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.88, 0.896551724137931, 1.0, 1.0, 1.0, 0.9047619047619048, 0.9166666666666666, 0.8823529411764706, 1.0, 1.0, 0.8181818181818182, 0.9285714285714286, 0.9166666666666666, 1.0, 1.0, 0.8888888888888888, 1.0, 1.0, 0.9375, 1.0, 0.92, 0.8333333333333334, 0.8823529411764706, 1.0, 0.9375, 0.8947368421052632, 0.875, 1.0, 0.9090909090909091, 0.9375, 1.0, 0.9565217391304348, 1.0, 1.0, 1.0, 0.8333333333333334, 1.0, 1.0, 1.0, 0.9333333333333333, 1.0, 1.0, 1.0, 0.9444444444444444, 0.8947368421052632, 1.0, 1.0, 0.8571428571428571, 0.9, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 0.8666666666666667, 1.0, 0.9615384615384616, 0.875, 1.0, 0.9285714285714286, 0.8947368421052632, 0.9473684210526315, 1.0, 0.9473684210526315, 1.0, 1.0, 0.8461538461538461, 0.8571428571428571, 1.0, 0.9615384615384616, 0.8888888888888888, 1.0, 0.9285714285714286, 1.0, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 0.9411764705882353, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9285714285714286, 0.9545454545454546, 1.0, 1.0, 1.0, 1.0, 0.9411764705882353, 0.8571428571428571, 1.0, 0.9166666666666666, 0.9166666666666666, 1.0, 0.9615384615384616, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8823529411764706, 0.8888888888888888, 1.0, 1.0, 0.875, 1.0, 0.9375, 0.88, 1.0, 0.8571428571428571, 1.0, 1.0, 1.0, 0.92, 0.9090909090909091, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8571428571428571, 1.0, 0.9, 0.9411764705882353, 0.9285714285714286, 1.0, 0.8666666666666667, 0.8947368421052632, 1.0, 0.9615384615384616, 0.9375, 1.0, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 0.9583333333333334, 0.8928571428571429, 1.0, 1.0, 1.0, 0.8333333333333334] |
| 19.8295 | 2.0 | 50 | 0.9596 | 23.9408 | [0.9, 0.875, 0.8333333333333334, 1.0, 1.0, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 0.875, 1.0, 1.0, 0.8461538461538461, 0.9, 1.0, 0.9230769230769231, 1.0, 1.0, 1.0, 0.9444444444444444, 1.0, 0.9615384615384616, 0.7857142857142857, 0.9333333333333333, 1.0, 1.0, 1.0, 0.9411764705882353, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 0.8888888888888888, 0.9285714285714286, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9375, 0.9565217391304348, 0.8823529411764706, 1.0, 0.9, 0.9130434782608695, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 1.0, 0.9230769230769231, 0.96, 1.0, 1.0, 1.0, 1.0, 0.9444444444444444, 0.8888888888888888, 1.0, 0.9615384615384616, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 0.7857142857142857, 0.8421052631578947, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9615384615384616, 1.0, 0.9523809523809523, 0.85, 0.9130434782608695, 0.9090909090909091, 1.0, 1.0, 0.8125, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8823529411764706, 1.0, 1.0, 1.0, 0.9090909090909091, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.8461538461538461, 0.8333333333333334, 1.0, 0.88, 0.9230769230769231, 0.9375, 0.9166666666666666, 0.9285714285714286, 0.9, 1.0, 1.0, 0.9166666666666666, 0.8666666666666667, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 0.9545454545454546, 1.0, 0.9333333333333333, 1.0, 0.9285714285714286, 0.85, 1.0, 1.0, 0.8846153846153846, 1.0, 1.0, 0.9285714285714286, 1.0, 0.8235294117647058, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 0.8461538461538461, 0.9615384615384616, 0.8666666666666667, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9230769230769231, 0.9615384615384616, 1.0, 0.9, 1.0, 1.0, 1.0, 0.8333333333333334, 0.9333333333333333, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 0.9333333333333333, 1.0, 1.0, 0.8125, 1.0, 1.0, 1.0, 0.8125, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 0.9375, 1.0, 0.9090909090909091, 1.0, 0.9230769230769231, 0.9, 0.9615384615384616, 0.8461538461538461, 0.9285714285714286, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.88, 0.896551724137931, 1.0, 1.0, 1.0, 0.9047619047619048, 0.9166666666666666, 0.8823529411764706, 1.0, 1.0, 0.8181818181818182, 0.9285714285714286, 0.9166666666666666, 1.0, 1.0, 0.8888888888888888, 1.0, 1.0, 1.0, 1.0, 0.92, 0.8333333333333334, 0.8823529411764706, 1.0, 0.9375, 0.8947368421052632, 0.875, 1.0, 0.9090909090909091, 0.9375, 1.0, 0.9565217391304348, 1.0, 1.0, 1.0, 0.8333333333333334, 1.0, 1.0, 1.0, 0.9333333333333333, 1.0, 1.0, 1.0, 0.9444444444444444, 0.8947368421052632, 1.0, 1.0, 0.8571428571428571, 0.9, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 0.8666666666666667, 1.0, 0.9615384615384616, 0.875, 1.0, 0.9285714285714286, 0.8947368421052632, 0.9473684210526315, 1.0, 0.9473684210526315, 1.0, 1.0, 0.8461538461538461, 0.8571428571428571, 1.0, 0.9615384615384616, 0.8888888888888888, 1.0, 0.9285714285714286, 1.0, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 0.9411764705882353, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9285714285714286, 0.9545454545454546, 1.0, 1.0, 1.0, 0.9333333333333333, 0.9411764705882353, 0.8571428571428571, 1.0, 0.9166666666666666, 0.9166666666666666, 1.0, 0.9615384615384616, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8823529411764706, 0.8888888888888888, 1.0, 1.0, 0.875, 1.0, 0.9411764705882353, 0.88, 1.0, 0.8571428571428571, 1.0, 1.0, 1.0, 0.92, 0.9090909090909091, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8571428571428571, 1.0, 0.9, 0.9411764705882353, 0.9285714285714286, 1.0, 0.8666666666666667, 0.8947368421052632, 1.0, 0.9615384615384616, 0.9375, 1.0, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 0.9583333333333334, 0.8928571428571429, 1.0, 1.0, 1.0, 0.8333333333333334] |
| 20.1206 | 3.0 | 75 | 0.9595 | 23.6406 | [0.9, 0.875, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.8181818181818182, 1.0, 1.0, 0.875, 1.0, 1.0, 0.8461538461538461, 0.9, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9444444444444444, 1.0, 0.9615384615384616, 0.7857142857142857, 0.9333333333333333, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 0.8888888888888888, 0.9285714285714286, 1.0, 1.0, 1.0, 0.8888888888888888, 1.0, 1.0, 1.0, 1.0, 0.9375, 0.9565217391304348, 0.8823529411764706, 1.0, 0.9, 0.9130434782608695, 1.0, 1.0, 1.0, 1.0, 0.9, 1.0, 1.0, 1.0, 0.96, 1.0, 1.0, 1.0, 1.0, 0.9444444444444444, 0.8888888888888888, 1.0, 0.9615384615384616, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 1.0, 0.7857142857142857, 0.8421052631578947, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9615384615384616, 1.0, 0.9523809523809523, 0.9230769230769231, 0.9130434782608695, 1.0, 1.0, 1.0, 0.8125, 1.0, 0.8823529411764706, 1.0, 1.0, 1.0, 0.8823529411764706, 1.0, 1.0, 1.0, 0.9090909090909091, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.8461538461538461, 0.8333333333333334, 1.0, 0.88, 0.9230769230769231, 0.9375, 0.9166666666666666, 0.9285714285714286, 0.9, 1.0, 0.8846153846153846, 0.9166666666666666, 0.8666666666666667, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 0.9545454545454546, 1.0, 0.9333333333333333, 1.0, 0.9285714285714286, 0.85, 1.0, 1.0, 0.8846153846153846, 1.0, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 1.0, 0.9473684210526315, 1.0, 0.8666666666666667, 0.8666666666666667, 0.9615384615384616, 0.8666666666666667, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 0.9230769230769231, 0.9615384615384616, 1.0, 0.9, 1.0, 1.0, 1.0, 0.8333333333333334, 0.9333333333333333, 1.0, 1.0, 0.9090909090909091, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 0.9333333333333333, 1.0, 1.0, 0.8125, 1.0, 1.0, 1.0, 0.8125, 1.0, 0.9285714285714286, 1.0, 1.0, 1.0, 0.9375, 1.0, 0.9090909090909091, 1.0, 0.9230769230769231, 0.9, 0.9615384615384616, 0.8461538461538461, 0.9285714285714286, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8888888888888888, 0.88, 0.896551724137931, 1.0, 1.0, 1.0, 0.9047619047619048, 0.9166666666666666, 0.8823529411764706, 1.0, 1.0, 0.8181818181818182, 0.9285714285714286, 0.9166666666666666, 1.0, 1.0, 0.8888888888888888, 1.0, 1.0, 0.8888888888888888, 1.0, 0.92, 0.8333333333333334, 0.8823529411764706, 1.0, 0.9375, 0.8947368421052632, 0.875, 1.0, 0.9090909090909091, 0.9375, 1.0, 0.9565217391304348, 1.0, 1.0, 1.0, 0.8333333333333334, 0.9285714285714286, 1.0, 1.0, 0.9333333333333333, 1.0, 0.8888888888888888, 1.0, 0.9444444444444444, 0.8947368421052632, 1.0, 1.0, 0.8571428571428571, 0.9, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 0.8666666666666667, 1.0, 0.9615384615384616, 0.875, 1.0, 0.9285714285714286, 0.8947368421052632, 0.9473684210526315, 1.0, 0.9473684210526315, 1.0, 1.0, 0.8461538461538461, 0.8571428571428571, 1.0, 0.9615384615384616, 0.8888888888888888, 1.0, 1.0, 1.0, 0.9230769230769231, 1.0, 1.0, 1.0, 1.0, 0.8666666666666667, 1.0, 1.0, 0.9411764705882353, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9285714285714286, 0.9285714285714286, 0.9545454545454546, 1.0, 1.0, 1.0, 0.9333333333333333, 0.9411764705882353, 0.8571428571428571, 1.0, 0.9166666666666666, 0.9166666666666666, 1.0, 0.9615384615384616, 1.0, 0.9166666666666666, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8823529411764706, 0.8888888888888888, 1.0, 1.0, 0.875, 1.0, 0.9375, 0.88, 1.0, 1.0, 1.0, 1.0, 1.0, 0.92, 0.9090909090909091, 1.0, 0.9615384615384616, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.8571428571428571, 1.0, 0.9, 0.9411764705882353, 0.9285714285714286, 1.0, 0.8666666666666667, 0.8947368421052632, 1.0, 0.9615384615384616, 0.9375, 1.0, 1.0, 1.0, 1.0, 0.9090909090909091, 1.0, 0.9583333333333334, 0.8928571428571429, 1.0, 1.0, 1.0, 0.8333333333333334] |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
owanr/SBIC-google-t5-v1_1-large-intra_model-dataset-frequency-human_annots_str-pairwise-mse | owanr | 2023-11-16T18:11:12Z | 0 | 0 | null | [
"generated_from_trainer",
"base_model:google/t5-v1_1-large",
"base_model:finetune:google/t5-v1_1-large",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-16T18:11:10Z | ---
license: apache-2.0
base_model: google/t5-v1_1-large
tags:
- generated_from_trainer
model-index:
- name: SBIC-google-t5-v1_1-large-intra_model-dataset-frequency-human_annots_str-pairwise-mse
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. -->
# SBIC-google-t5-v1_1-large-intra_model-dataset-frequency-human_annots_str-pairwise-mse
This model is a fine-tuned version of [google/t5-v1_1-large](https://huggingface.co/google/t5-v1_1-large) on the None dataset.
It achieves the following results on the evaluation set:
- Train Loss: 2.3408
- Loss: 0.2639
- Losses: [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5]
## 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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Training results
| Training Loss | Epoch | Step | Train Loss | Validation Loss | Losses |
|:-------------:|:-----:|:-----:|:----------:|:---------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 7.6417 | 1.0 | 392 | 2.6841 | 8.2070 | [2, 3, 3, 3, 1, 3, 0, 3, 3, 3, 4, 3, 3, 3, 3, 0, 3, 4, 4, 3, 3, 0, 2, 7, 3, 0, 3, 0, 1, 4, 4, 0, 2, 2, 0, 3, 5, 0, 5, 4, 0, 3, 3, 3, 3, 3, 2, 2, 3, 3, 3, 3, 3, 3, 0, 3, 1, 0, 2, 3, 2, 2, 2, 0, 3, 1, 3, 3, 1, 2, 4, 2, 3, 1, 3, 3, 3, 3, 2, 0, 3, 2, 4, 2, 5, 4, 3, 10, 3, 3, 3, 3, 3, 3, 3, 1, 3, 5, 2, 4, 3, 3, 0, 0, 1, 3, 3, 1, 0, 3, 0, 3, 3, 5, 3, 4, 1, 2, 3, 4, 4, 3, 2, 3, 4, 3, 1, 1, 2, 5, 0, 3, 5, 4, 3, 0, 2, 2, 2, 0, 3, 3, 1, 3, 1, 1, 3, 3, 3, 4, 4, 1, 3, 3, 1, 4, 3, 1, 3, 8, 0, 1, 6, 0, 3, 0, 1, 3, 3, 0, 3, 2, 3, 0, 0, 1, 3, 1, 2, 3, 1, 0, 0, 2, 4, 3, 3, 3, 0, 3, 0, 5, 0, 0, 3, 4, 4, 2, 2, 3, 0, 3, 2, 1, 2, 3, 3, 3, 3, 4, 3, 2, 2, 5, 1, 1, 0, 3, 5, 2, 4, 0, 3, 3, 4, 0, 3, 3, 4, 3, 5, 0, 4, 0, 4, 1, 3, 2, 5, 3, 1, 3, 4, 4, 3, 3, 4, 2, 3, 2, 2, 3, 3, 3, 2, 2, 4, 2, 3, 3, 4, 0, 4, 2, 3, 3, 0, 3, 3, 5, 3, 1, 4, 0, 3, 3, 3, 0, 4, 3, 3, 3, 4, 4, 0, 3, 3, 3, 4, 4, 4, 3, 0, 3, 3, 2, 2, 5, 3, 3, 1, 6, 0, 3, 3, 1, 3, 5, 2, 3, 3, 3, 2, 3, 2, 3, 3, 0, 2, 2, 0, 5, 1, 3, 1, 3, 2, 3, 2, 3, 2, 1, 4, 1, 5, 4, 3, 0, 3, 3, 4, 3, 0, 2, 2, 3, 2, 4, 3, 0, 0, 3, 3, 2, 4, 3, 0, 2, 1, 1, 3, 5, 5, 3, 4, 3, 5, 2, 2, 3, 4, 2, 0, 3, 1, 1, 3, 0, 3, 0, 2, 4, 1, 3, 0, 4, 3, 2, 0, 2, 2, 0, 4, 3, 5, 3, 2, 2, 3, 2, 3, 3, 1, 3, 2, 3, 1, 4, 0, 3, 6, 3, 3, 4, 0, 3, 4, 2, 3, 4, 0, 3, 3, 2, 2, 6, 3, 3, 3, 3, 3, 1, 1, 3, 0, 5, 2, 4, 2, 4, 1, 3, 1, 3, 3, 1, 3, 3, 1, 1, 1, 3, 0, 4, 5, 3, 3, 5, 4, 4, 0, 3, 0, 2, 0, 4, 3, 0, 3, 2, 3, 2, 2, 2, 1, 3, 3, 3, 3, 3, 3, 4, 3, 3, 5, 5, 2, 4, 5, 3, 4, 3, 17, 3, 1, 2, 3, 1, 2, 3, 3, 4, 3, 4, 4, 5, 3, 3, 3, 4, 2, 3, 3, 0, 4, 2, 2, 3, 2, 3, 3, 2, 0, 1, 3, 3, 5, 1, 1, 4, 4, 4, 2, 2, 3, 2, 1, 2, 3, 3, 1, 1, 3, 3, 0, 0, 4, 4, 4, 3, 3, 3, 1, 1, 18, 0, 3, 0, 3, 3, 3, 3, 3, 3, 1, 0, 4, 1, 4, 2, 3, 2, 4, 0, 0, 4, 2, 4, 3, 3, 3, 3, 1, 3, 3, 0, 4, 0, 3, 3, 0, 3, 5, 3, 4, 5, 0, 0, 5, 0, 3, 2, 3, 2, 3, 3, 0, 3, 0, 2, 1, 0, 3, 4, 0, 8, 4, 2, 4, 4, 4, 2, 1, 2, 0, 3, 0, 4, 3, 4, 5, 1, 0, 9, 4, 3, 5, 1, 4, 4, 1, 0, 4, 0, 3, 0, 4, 3, 3, 5, 3, 0, 4, 0, 1, 3, 2, 3, 0, 3, 1, 4, 3, 2, 0, 3, 3, 0, 0, 2, 3, 3, 4, 3, 4, 1, 3, 3, 4, 3, 5, 4, 4, 4, 0, 3, 3, 7, 3, 4, 2, 0, 2, 1, 4, 4, 3, 3, 4, 2, 0, 0, 4, 5, 3, 3, 2, 2, 3, 4, 3, 3, 4, 3, 0, 3, 0, 2, 1, 2, 3, 5, 0, 3, 2, 3, 2, 4, 5, 3, 4, 2, 3, 4, 4, 3, 3, 4, 0, 3, 4, 4, 3, 3, 3, 3, 5, 3, 3, 4, 3, 0, 2, 2, 2, 3, 2, 4, 3, 0, 0, 4, 4, 4, 5, 3, 2, 2, 0, 2, 2, 1, 1, 4, 3, 0, 3, 3, 3, 2, 3, 2, 1, 3, 1, 0, 0, 3, 4, 4, 3, 3, 3, 0, 3, 4, 3, 3, 4, 1, 4, 3, 3, 2, 2, 3, 3, 2, 0, 2, 2, 4, 4, 3, 2, 4, 2, 3, 4, 0, 5, 3, 3, 5, 3, 3, 2, 3, 3, 3, 5, 0, 2, 3, 4, 3, 3, 2, 4, 5, 0, 1, 3, 3, 0, 2, 0, 0, 5, 8, 4, 0, 5, 2, 12, 5, 4, 4, 3, 3, 3, 2, 4, 3, 4, 3, 0, 3, 0, 5, 4, 2, 3, 0, 5, 3, 3, 3, 2, 3, 4, 0, 0, 1, 3, 3, 4, 0, 4, 2, 3, 2, 3, 2, 3, 11, 2, 5, 3, 3, 3, 3, 3, 3, 2, 3, 3, 1, 5, 0, 0, 0, 4, 4, 3, 3, 2, 0, 3, 4, 3, 3, 3, 3, 3, 1, 3, 3, 4, 3, 3, 4, 3, 2, 3, 0, 0, 1, 3, 4, 3, 4, 0, 18, 3, 1, 5, 2, 4, 0, 0, 3, 3, 4, 3, 3, 0, 1, 3, 2, 0, 3, 2, 3, 0, 3, 3, 3, 4, 0, 3, 0, 3, 3, 3, 4, 2, 4, 3, 3, 2, 3, 3, 2, 4, 3, 2, 4, 3, 1, 3, 3, 0, 4, 3, 4, 4, 1, 4, 4, 0, 4, 3, 2, 3, 0, 2, 5, 3, 3, 3, 5, 2, 0, 3, 4, 4, 7, 2, 4, 3, 3, 3, 2, 5, 0, 3, 0, 3, 3, 0, 3, 2, 8, 4, 2, 4, 3, 1, 1, 3, 0, 4, 4, 4, 2, 3, 3, 1, 4, 1, 4, 3, 0, 3, 3, 3, 2, 2, 3, 9, 2, 2, 0, 4, 4, 0, 4, 3, 1, 1, 4, 3, 0, 3, 3, 3, 8, 3, 3, 2, 3, 0, 2, 2, 4, 0, 2, 3, 0, 0, 4, 3, 3, 3, 0, 4, 3, 1, 4, 3, 3, 5, 8, 5, 2, 2, 4, 2, 3, 2, 4, 3, 5, 3, 4, 1, 3, 3, 3, 4, 8, 3, 0, 3, 1, 4, 2, 4, 1, 3, 3, 3, 3, 3, 3, 2, 5, 3, 3, 1, 3, 3, 3, 2, 12, 0, 2, 4, 2, 2, 3, 4, 3, 3, 4, 3, 3, 3, 3, 3, 1, 0, 3, 3, 5, 3, 4, 0, 0, 3, 3, 0, 3, 2, 0, 0, 2, 2, 4, 3, 2, 0, 3, 3, 3, 0, 3, 1, 4, 4, 3, 3, 3, 3, 3, 3, 3, 4, 4, 3, 3, 2, 4, 0, 4, 3, 0, 1, 4, 4, 4, 1, 3, 3, 2, 5, 1, 3, 3, 4, 3, 3, 3, 3, 3, 3, 7, 3, 3, 4, 0, 5, 3, 3, 3, 4, 3, 2, 3, 0, 3, 5, 4, 1, 1, 1, 4, 0, 0, 0, 18, 3, 0, 3, 3, 3, 4, 2, 5, 3, 3, 2, 1, 2, 0, 3, 3, 3, 3, 9, 1, 3, 3, 2, 4, 3, 3, 2, 3, 2, 3, 4, 2, 3, 1, 4, 3, 1, 3, 1, 3, 3, 2, 5, 2, 3, 5, 5, 4, 3, 4, 1, 2, 3, 3, 1, 3, 3, 4, 3, 4, 3, 2, 3, 1, 3, 1, 3, 3, 3, 0, 1, 3, 3, 0, 2, 9, 2, 3, 3, 1, 5, 0, 2, 2, 1, 3, 4, 4, 4, 4, 0, 3, 0, 3, 3, 0, 3, 5, 3, 1, 3, 0, 4, 3, 5, 3, 3, 2, 4, 4, 2, 4, 0, 0, 0, 5, 4, 3, 3, 4, 3, 3, 3, 3, 3, 5, 3, 3, 3, 3, 3, 5, 3, 3, 3, 3, 3, 1, 2, 4, 5, 0, 3, 4, 3, 2, 0, 3, 5, 4, 3, 3, 3, 5, 3, 3, 13, 4, 3, 3, 0, 3, 5, 3, 3, 0, 3, 3, 0, 5, 0, 2, 5, 4, 3, 0, 3, 4, 3, 3, 4, 4, 4, 3, 0, 4, 3, 3, 3, 5, 3, 4, 1, 2, 2, 0, 3, 3, 4, 5, 3, 2, 1, 4, 4, 4, 0, 0, 0, 0, 3, 0, 4, 1, 3, 3, 2, 3, 5, 5, 3, 3, 2, 3, 4, 0, 5, 2, 1, 3, 1, 3, 0, 2, 3, 0, 3, 3, 3, 2, 1, 5, 2, 0, 0, 0, 4, 2, 3, 4, 3, 2, 4, 4, 3, 4, 2, 3, 3, 3, 1, 4, 0, 4, 3, 1, 3, 0, 5, 2, 4, 1, 4, 3, 5, 1, 4, 4, 4, 3, 3, 3, 5, 5, 4, 2, 0, 3, 2, 0, 5, 3, 3, 2, 4, 1, 3, 3, 2, 4, 3, 2, 1, 3, 3, 5, 4, 0, 4, 2, 4, 5] |
| 6.7361 | 2.0 | 784 | 2.0627 | 6.9830 | [2, 3, 2, 3, 1, 0, 0, 3, 3, 2, 3, 2, 1, 3, 3, 4, 3, 2, 3, 3, 2, 0, 2, 0, 2, 0, 3, 0, 1, 3, 3, 0, 2, 2, 0, 3, 1, 0, 1, 3, 0, 3, 3, 3, 3, 3, 3, 2, 3, 2, 3, 3, 3, 2, 0, 3, 1, 0, 2, 3, 2, 2, 3, 0, 3, 0, 3, 3, 1, 2, 3, 2, 3, 1, 3, 3, 3, 3, 2, 4, 3, 2, 3, 2, 0, 2, 3, 1, 3, 3, 3, 3, 3, 3, 2, 1, 3, 0, 2, 2, 3, 3, 4, 0, 2, 3, 3, 1, 0, 3, 0, 3, 2, 0, 2, 3, 1, 2, 3, 3, 3, 3, 2, 3, 3, 2, 3, 1, 2, 1, 0, 3, 0, 2, 2, 0, 2, 2, 2, 0, 3, 3, 1, 3, 1, 1, 3, 3, 3, 1, 3, 1, 3, 2, 1, 2, 2, 1, 3, 3, 0, 0, 3, 0, 3, 0, 0, 3, 2, 0, 2, 3, 3, 0, 0, 1, 3, 1, 2, 3, 1, 0, 0, 2, 1, 3, 3, 2, 4, 2, 0, 2, 0, 0, 3, 1, 2, 3, 4, 3, 4, 3, 2, 3, 2, 3, 3, 3, 3, 3, 3, 3, 3, 1, 1, 1, 0, 3, 0, 2, 3, 0, 3, 3, 2, 0, 2, 3, 2, 3, 0, 0, 3, 0, 3, 0, 3, 2, 0, 3, 4, 0, 3, 1, 3, 2, 3, 2, 3, 2, 3, 3, 3, 3, 2, 2, 1, 2, 3, 3, 3, 4, 2, 2, 3, 3, 0, 2, 3, 1, 3, 1, 3, 0, 3, 3, 3, 4, 2, 3, 3, 3, 3, 3, 0, 3, 2, 2, 3, 3, 3, 0, 0, 3, 3, 2, 2, 0, 3, 3, 1, 3, 0, 3, 0, 1, 3, 0, 3, 3, 3, 3, 2, 3, 2, 3, 2, 0, 3, 2, 0, 0, 1, 2, 1, 3, 2, 2, 2, 3, 2, 2, 3, 1, 0, 2, 3, 0, 2, 3, 3, 3, 0, 2, 3, 3, 2, 0, 3, 0, 0, 3, 3, 2, 3, 3, 0, 2, 1, 0, 2, 0, 0, 3, 3, 2, 0, 3, 2, 3, 3, 2, 0, 3, 4, 1, 3, 0, 3, 0, 2, 2, 1, 3, 0, 3, 3, 2, 0, 2, 2, 0, 1, 3, 0, 3, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 0, 2, 4, 3, 3, 3, 2, 3, 1, 3, 0, 2, 3, 3, 0, 2, 3, 3, 2, 3, 3, 3, 3, 3, 3, 1, 1, 3, 0, 0, 2, 3, 2, 2, 1, 2, 1, 3, 2, 1, 3, 3, 1, 1, 1, 3, 0, 2, 1, 3, 3, 0, 2, 3, 0, 3, 0, 2, 0, 0, 3, 0, 3, 2, 3, 3, 2, 2, 1, 2, 3, 3, 3, 3, 3, 3, 3, 3, 0, 0, 2, 3, 1, 3, 3, 3, 3, 3, 1, 3, 3, 1, 3, 3, 3, 1, 3, 3, 3, 0, 3, 3, 3, 2, 2, 3, 2, 0, 3, 3, 2, 3, 2, 3, 3, 3, 0, 1, 3, 3, 0, 1, 1, 3, 2, 3, 2, 3, 3, 2, 0, 3, 3, 3, 1, 1, 3, 3, 0, 0, 3, 0, 3, 3, 2, 3, 1, 1, 3, 0, 3, 0, 3, 3, 3, 3, 3, 3, 1, 0, 3, 1, 1, 2, 3, 3, 2, 4, 0, 2, 0, 2, 3, 3, 3, 3, 1, 2, 3, 4, 3, 0, 3, 3, 0, 3, 3, 3, 0, 0, 1, 0, 0, 0, 3, 3, 3, 2, 3, 3, 0, 3, 0, 2, 0, 0, 2, 3, 0, 2, 2, 2, 3, 3, 3, 2, 1, 2, 0, 3, 0, 3, 2, 2, 0, 3, 0, 2, 3, 3, 2, 1, 3, 3, 1, 0, 3, 0, 3, 0, 3, 3, 2, 1, 3, 0, 2, 0, 1, 3, 3, 3, 0, 3, 1, 3, 3, 2, 4, 2, 3, 4, 0, 2, 0, 3, 3, 2, 2, 1, 3, 3, 2, 3, 1, 3, 3, 3, 0, 2, 2, 2, 3, 3, 2, 4, 2, 1, 0, 2, 3, 3, 2, 3, 0, 0, 3, 0, 2, 3, 2, 2, 3, 3, 3, 3, 2, 3, 0, 2, 0, 2, 3, 2, 3, 0, 0, 3, 2, 3, 2, 3, 1, 3, 3, 2, 3, 1, 2, 3, 2, 3, 0, 3, 3, 2, 3, 3, 3, 2, 0, 3, 3, 2, 3, 0, 2, 2, 2, 2, 2, 3, 3, 0, 0, 2, 0, 0, 0, 3, 3, 2, 0, 2, 4, 1, 1, 3, 3, 0, 2, 3, 3, 3, 3, 2, 1, 3, 3, 0, 0, 3, 3, 3, 3, 3, 3, 0, 3, 1, 3, 3, 1, 1, 2, 3, 3, 2, 4, 3, 3, 2, 0, 2, 4, 2, 3, 3, 2, 0, 3, 3, 3, 0, 0, 3, 3, 0, 3, 3, 3, 3, 3, 3, 3, 0, 2, 3, 3, 3, 2, 2, 2, 0, 0, 1, 3, 3, 0, 2, 0, 0, 1, 3, 2, 0, 0, 2, 0, 0, 3, 2, 2, 3, 3, 2, 3, 3, 3, 2, 0, 2, 0, 0, 3, 2, 3, 0, 3, 3, 2, 3, 2, 3, 3, 4, 0, 4, 3, 3, 3, 0, 3, 2, 3, 2, 3, 3, 3, 4, 2, 0, 4, 3, 3, 3, 3, 3, 2, 2, 0, 2, 1, 0, 0, 0, 3, 3, 3, 3, 2, 0, 3, 2, 3, 3, 3, 2, 3, 0, 3, 3, 3, 4, 2, 3, 3, 2, 2, 0, 0, 2, 3, 2, 2, 2, 0, 3, 2, 1, 2, 2, 3, 0, 0, 3, 3, 1, 3, 3, 0, 1, 3, 2, 0, 3, 2, 2, 0, 3, 3, 3, 3, 0, 3, 0, 3, 2, 3, 2, 2, 0, 3, 3, 3, 3, 3, 2, 3, 3, 2, 2, 3, 1, 3, 3, 0, 1, 3, 3, 3, 1, 3, 3, 4, 3, 3, 2, 3, 0, 2, 0, 3, 3, 3, 2, 3, 0, 3, 3, 3, 0, 3, 2, 3, 3, 3, 3, 0, 0, 3, 0, 3, 3, 4, 3, 2, 0, 3, 3, 1, 3, 1, 1, 3, 0, 1, 3, 3, 2, 3, 3, 3, 3, 1, 3, 3, 0, 3, 3, 3, 2, 3, 3, 2, 2, 3, 0, 0, 3, 0, 3, 3, 1, 1, 2, 3, 0, 3, 2, 3, 1, 3, 3, 2, 3, 0, 2, 3, 1, 0, 2, 3, 0, 0, 1, 3, 3, 3, 0, 2, 3, 1, 0, 3, 2, 0, 3, 0, 2, 3, 2, 3, 3, 2, 2, 3, 0, 3, 3, 1, 3, 1, 3, 3, 3, 3, 0, 3, 1, 3, 2, 3, 4, 3, 3, 3, 3, 3, 3, 2, 0, 2, 3, 1, 3, 0, 0, 3, 0, 0, 2, 3, 2, 2, 3, 3, 3, 3, 3, 3, 4, 3, 3, 3, 1, 0, 3, 3, 1, 3, 3, 0, 4, 3, 3, 4, 2, 3, 4, 0, 2, 2, 2, 3, 2, 0, 3, 3, 3, 4, 2, 1, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 3, 3, 0, 0, 2, 3, 2, 1, 2, 3, 2, 1, 1, 3, 3, 3, 3, 3, 3, 3, 3, 2, 3, 3, 0, 0, 0, 0, 3, 3, 2, 3, 3, 2, 3, 0, 3, 0, 3, 1, 1, 1, 3, 0, 0, 0, 3, 0, 4, 3, 3, 3, 0, 2, 0, 3, 3, 3, 1, 2, 0, 3, 3, 3, 3, 3, 1, 3, 3, 2, 2, 3, 3, 2, 3, 2, 3, 1, 2, 3, 1, 3, 3, 1, 3, 1, 3, 3, 2, 0, 2, 3, 0, 0, 3, 3, 3, 1, 2, 3, 3, 1, 3, 3, 3, 3, 3, 3, 2, 0, 1, 3, 0, 2, 3, 3, 0, 3, 3, 2, 0, 2, 0, 3, 2, 3, 1, 2, 0, 3, 3, 3, 3, 3, 2, 3, 3, 0, 3, 0, 3, 3, 0, 2, 0, 3, 1, 3, 0, 2, 3, 0, 3, 3, 2, 3, 3, 2, 3, 0, 0, 0, 0, 3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 3, 3, 3, 3, 3, 0, 3, 3, 3, 3, 3, 1, 3, 1, 0, 0, 3, 3, 2, 2, 4, 3, 0, 2, 3, 3, 3, 0, 3, 3, 3, 2, 3, 3, 0, 3, 0, 3, 3, 0, 3, 3, 0, 0, 0, 2, 1, 3, 3, 0, 3, 3, 3, 3, 3, 2, 2, 3, 0, 3, 3, 3, 3, 0, 3, 3, 1, 2, 2, 0, 3, 3, 3, 0, 3, 2, 1, 3, 3, 2, 0, 0, 0, 4, 3, 0, 1, 1, 3, 3, 2, 3, 0, 0, 3, 3, 2, 3, 3, 0, 0, 3, 1, 3, 1, 2, 0, 3, 2, 0, 3, 3, 3, 3, 1, 1, 3, 3, 0, 4, 2, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 3, 3, 3, 1, 3, 0, 2, 3, 1, 3, 4, 0, 3, 2, 2, 2, 3, 0, 0, 3, 1, 3, 3, 3, 3, 1, 1, 3, 2, 0, 3, 3, 0, 0, 3, 3, 2, 1, 1, 3, 3, 3, 3, 3, 2, 1, 3, 0, 0, 2, 0, 3, 2, 3, 3] |
| 0.4188 | 3.0 | 1176 | 2.6957 | 0.3786 | [4, 2, 2, 2, 3, 4, 4, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 4, 2, 4, 2, 4, 2, 4, 3, 2, 2, 4, 3, 2, 4, 2, 4, 4, 4, 2, 4, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 2, 3, 3, 2, 4, 3, 4, 2, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 4, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 4, 4, 3, 2, 2, 4, 4, 2, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 4, 2, 4, 2, 2, 4, 2, 2, 2, 4, 2, 2, 4, 2, 3, 3, 2, 2, 2, 3, 2, 4, 2, 2, 4, 2, 2, 4, 2, 2, 4, 4, 2, 4, 2, 4, 4, 2, 2, 4, 2, 2, 2, 4, 4, 4, 2, 4, 3, 2, 3, 4, 4, 2, 3, 2, 3, 2, 4, 2, 4, 2, 4, 4, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 4, 3, 2, 4, 2, 2, 3, 4, 3, 2, 2, 2, 4, 4, 2, 4, 2, 4, 2, 2, 4, 2, 4, 4, 2, 3, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 4, 2, 4, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 4, 3, 2, 4, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 3, 4, 4, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 4, 2, 2, 2, 3, 4, 3, 2, 2, 2, 4, 2, 4, 4, 2, 2, 3, 2, 2, 4, 4, 3, 4, 2, 4, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 4, 2, 4, 4, 2, 4, 2, 4, 3, 3, 4, 2, 4, 2, 2, 2, 4, 2, 4, 4, 3, 2, 4, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 4, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 4, 4, 2, 3, 3, 4, 2, 4, 3, 2, 3, 2, 2, 3, 3, 4, 2, 4, 2, 4, 3, 2, 4, 4, 2, 4, 2, 4, 3, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 2, 3, 2, 4, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 4, 4, 2, 2, 3, 2, 2, 3, 2, 2, 4, 4, 2, 2, 4, 3, 4, 2, 3, 2, 2, 3, 4, 3, 4, 2, 3, 2, 3, 4, 2, 2, 4, 4, 2, 4, 3, 2, 2, 2, 3, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 3, 4, 3, 3, 3, 4, 2, 2, 2, 4, 4, 3, 4, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 4, 4, 3, 4, 4, 4, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 4, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 4, 2, 4, 2, 4, 2, 2, 3, 4, 3, 4, 3, 2, 2, 3, 4, 2, 2, 3, 4, 3, 4, 2, 4, 2, 2, 2, 4, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 2, 2, 4, 4, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 3, 2, 2, 4, 4, 2, 2, 4, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 4, 2, 3, 2, 2, 3, 2, 2, 4, 4, 3, 4, 4, 4, 2, 2, 2, 4, 3, 4, 3, 4, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 4, 3, 4, 2, 2, 2, 4, 4, 4, 2, 2, 4, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 4, 3, 4, 4, 4, 2, 2, 4, 4, 2, 4, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 4, 2, 3, 2, 4, 2, 2, 2, 2, 3, 2, 2, 4, 4, 4, 2, 3, 2, 4, 2, 3, 2, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 4, 4, 4, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 4, 2, 3, 2, 2, 2, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 4, 4, 2, 2, 4, 4, 2, 2, 3, 2, 2, 4, 3, 2, 3, 4, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 4, 2, 4, 2, 2, 2, 4, 2, 4, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 4, 2, 2, 4, 2, 3, 3, 2, 4, 3, 2, 4, 3, 2, 2, 3, 3, 2, 3, 2, 4, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 3, 4, 2, 3, 4, 2, 2, 2, 4, 2, 2, 3, 3, 4, 2, 2, 3, 4, 2, 2, 4, 4, 3, 2, 2, 2, 4, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 2, 3, 3, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 2, 2, 4, 2, 4, 4, 2, 4, 4, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 4, 2, 2, 4, 2, 2, 4, 4, 2, 3, 2, 2, 3, 4, 3, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 4, 2, 2, 3, 3, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 4, 4, 3, 2, 2, 2, 2, 3, 2, 4, 2, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 2, 3, 3, 4, 2, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 3, 2, 4, 4, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 4, 3, 2, 2, 4, 3, 4, 2, 2, 2, 4, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 4, 2, 4, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 4, 4, 4, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 4, 2, 4, 3, 2, 2, 3, 4, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 4, 4, 4, 2, 4, 2, 3, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 4, 3, 2, 4, 3, 2, 2, 4, 2, 3, 3, 2, 2, 2, 4, 4, 4, 4, 2, 4, 3, 4, 2, 2, 3, 3, 4, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 4, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 4, 3, 3, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 4, 2, 4, 4, 2, 2, 3, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 4, 4, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 4, 4, 2, 4, 3, 2, 2, 4] |
| 0.4025 | 4.0 | 1568 | 2.7417 | 0.3593 | [4, 2, 2, 5, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 3, 3, 5, 2, 5, 4, 5, 2, 3, 3, 2, 3, 2, 3, 5, 2, 2, 5, 4, 2, 2, 3, 2, 3, 4, 3, 2, 3, 2, 2, 5, 2, 5, 5, 2, 3, 2, 2, 4, 2, 5, 2, 4, 2, 3, 5, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 5, 3, 3, 2, 2, 5, 3, 2, 3, 2, 2, 4, 2, 5, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 4, 3, 4, 2, 5, 2, 2, 4, 2, 3, 2, 3, 3, 4, 2, 2, 2, 3, 2, 4, 5, 2, 3, 4, 3, 2, 4, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 5, 3, 4, 5, 3, 2, 2, 2, 4, 5, 4, 5, 2, 2, 2, 4, 3, 3, 2, 2, 2, 5, 4, 5, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 4, 3, 4, 2, 2, 2, 5, 4, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 5, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 4, 3, 2, 3, 4, 4, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 4, 2, 2, 4, 4, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 5, 2, 4, 2, 4, 5, 5, 3, 2, 2, 3, 2, 2, 2, 5, 5, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 5, 4, 3, 3, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 4, 4, 3, 2, 2, 4, 2, 4, 5, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 4, 5, 3, 5, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 5, 2, 4, 2, 4, 3, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 3, 4, 4, 2, 2, 3, 2, 3, 4, 2, 5, 4, 2, 2, 2, 3, 2, 2, 2, 3, 3, 2, 4, 5, 2, 5, 5, 5, 5, 2, 5, 3, 2, 3, 3, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 5, 2, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 5, 5, 2, 4, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 3, 5, 5, 3, 2, 3, 2, 2, 4, 2, 5, 2, 3, 2, 4, 4, 2, 3, 2, 2, 2, 2, 2, 3, 5, 2, 2, 4, 2, 2, 2, 2, 4, 4, 2, 3, 2, 2, 3, 2, 5, 2, 5, 3, 2, 2, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 5, 2, 4, 4, 5, 2, 3, 5, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 5, 3, 2, 5, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 5, 2, 4, 2, 3, 5, 2, 3, 3, 2, 5, 5, 3, 4, 2, 5, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 5, 2, 3, 2, 2, 4, 2, 4, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 5, 2, 5, 5, 2, 2, 3, 2, 2, 2, 4, 4, 5, 3, 5, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 5, 2, 2, 5, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 5, 2, 5, 2, 2, 5, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 5, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 5, 5, 4, 2, 2, 2, 5, 3, 4, 2, 4, 2, 2, 2, 5, 4, 2, 2, 4, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 4, 5, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 4, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 4, 2, 3, 4, 4, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 5, 2, 2, 3, 3, 2, 3, 2, 5, 2, 5, 2, 2, 4, 2, 4, 2, 3, 2, 2, 2, 2, 3, 5, 2, 4, 5, 2, 3, 2, 2, 4, 2, 4, 2, 4, 5, 4, 2, 5, 2, 5, 5, 5, 2, 4, 2, 2, 5, 3, 4, 2, 2, 4, 2, 2, 2, 4, 5, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 3, 2, 2, 4, 3, 3, 3, 2, 2, 2, 5, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 5, 5, 2, 2, 2, 4, 2, 2, 2, 2, 5, 3, 4, 3, 2, 2, 2, 2, 2, 2, 4, 5, 5, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 5, 5, 3, 2, 3, 3, 2, 2, 5, 2, 2, 4, 5, 4, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 4, 2, 4, 2, 2, 2, 5, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 3, 2, 5, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 5, 4, 4, 2, 2, 2, 5, 2, 5, 2, 5, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 4, 2, 4, 2, 2, 5, 2, 2, 2, 2, 5, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 5, 2, 2, 4, 2, 5, 2, 5, 2, 2, 2, 2, 4, 3, 2, 5, 2, 2, 2, 4, 2, 5, 2, 5, 2, 2, 5, 5, 2, 2, 4, 5, 2, 3, 4, 2, 2, 5, 2, 2, 2, 2, 4, 3, 5, 2, 2, 4, 4, 2, 2, 2, 2, 3, 3, 2, 2, 4, 3, 2, 2, 2, 5, 2, 5, 2, 2, 2, 5, 3, 5, 4, 2, 2, 3, 2, 4, 5, 2, 2, 2, 3, 3, 3, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 5, 3, 2, 2, 5, 2, 3, 3, 5, 4, 2, 2, 3, 2, 2, 5, 2, 2, 3, 3, 2, 2, 2, 5, 5, 2, 4, 2, 2, 2, 2, 2, 5, 4, 2, 5] |
| 0.3444 | 5.0 | 1960 | 2.5627 | 0.3301 | [4, 2, 2, 2, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 3, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 4, 4, 2, 3, 2, 3, 4, 3, 2, 3, 2, 2, 5, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 4, 3, 5, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 5, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 4, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 4, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 4, 5, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 4, 2, 2, 4, 4, 2, 2, 2, 4, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 3, 3, 3, 2, 3, 3, 2, 3, 2, 2, 3, 3, 4, 2, 2, 4, 4, 3, 2, 2, 4, 2, 4, 5, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 3, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 3, 3, 2, 4, 5, 2, 2, 2, 5, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 4, 2, 4, 2, 2, 5, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 4, 2, 5, 2, 4, 2, 4, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 3, 2, 5, 2, 5, 4, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 5, 3, 2, 4, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 5, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 4, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 3, 2, 4, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 5, 2, 2, 5, 2, 2, 3, 2, 2, 4, 4, 4, 2, 3, 5, 2, 2, 3, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 5, 2, 5, 2, 4, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 5, 4, 2, 2, 4, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 4, 5, 2, 3, 5, 3, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 4, 2, 3, 4, 4, 2, 4, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 5, 2, 2, 4, 2, 4, 2, 4, 2, 2, 2, 2, 3, 5, 2, 4, 2, 2, 3, 2, 2, 4, 2, 4, 2, 4, 5, 4, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 2, 4, 5, 2, 4, 2, 2, 4, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 4, 3, 3, 3, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 4, 4, 3, 5, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 4, 5, 3, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 5, 2, 3, 2, 3, 3, 2, 2, 5, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 5, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 5, 4, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 4, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 5, 3, 5, 4, 2, 2, 3, 2, 4, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 5, 5, 2, 4, 2, 2, 2, 2, 2, 3, 4, 2, 5] |
| 0.3555 | 6.0 | 2352 | 2.5262 | 0.3211 | [4, 2, 5, 5, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 5, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 5, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 3, 5, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 4, 2, 2, 2, 2, 4, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 4, 5, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 3, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 3, 3, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 5, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 3, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 5, 2, 2, 2, 5, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 4, 2, 5, 2, 4, 2, 4, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 5, 2, 5, 3, 2, 2, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 3, 4, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 5, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 4, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 3, 2, 4, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 4, 4, 2, 3, 5, 2, 2, 3, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 5, 4, 3, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 5, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 5, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 5, 2, 2, 2, 4, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 4, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 4, 2, 3, 2, 4, 2, 4, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 5, 2, 2, 4, 2, 4, 2, 3, 2, 2, 2, 2, 3, 5, 2, 4, 5, 2, 3, 2, 2, 2, 2, 4, 2, 4, 5, 4, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 2, 4, 5, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 4, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 5, 5, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 5, 4, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 5, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 5, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 5, 2, 2, 2, 2, 2, 5, 3, 5, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 4, 2, 5] |
| 0.3392 | 7.0 | 2744 | 2.4725 | 0.3043 | [4, 2, 2, 2, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 3, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 3, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 2, 2, 3, 4, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 4, 5, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 4, 2, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 4, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 3, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 4, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 3, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 4, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 4, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 4, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 4, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 3, 4, 4, 2, 4, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 4, 5, 2, 3, 2, 2, 2, 2, 4, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 5, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 4, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 3, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 4, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.3532 | 8.0 | 3136 | 2.4597 | 0.3066 | [4, 2, 2, 5, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 1, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 5, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 4, 5, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 3, 4, 2, 3, 2, 4, 2, 2, 2, 3, 3, 1, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 1, 3, 2, 2, 3, 4, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 5, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 2, 3, 2, 2, 4, 4, 2, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 1, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 1, 2, 2, 2, 5, 2, 2, 2, 3, 0, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 5, 5, 3, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 3, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 4, 2, 3, 2, 2, 2, 3, 2, 1, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 5, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 4, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 1, 2, 3, 2, 4, 2, 1, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 5, 3, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 5, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 4, 5, 5, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 4, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 5, 2, 2, 2, 2, 2, 5, 3, 5, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.3227 | 9.0 | 3528 | 2.4572 | 0.3001 | [4, 2, 2, 5, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 5, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 3, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 4, 2, 2, 4, 5, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 3, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 4, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 4, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 5, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 5, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 4, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.308 | 10.0 | 3920 | 2.4450 | 0.2929 | [4, 2, 2, 2, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 4, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 4, 4, 2, 4, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 3, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 4, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 4, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 5, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 1, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 4, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 4, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2757 | 11.0 | 4312 | 2.4386 | 0.2952 | [4, 2, 2, 2, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 4, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 4, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 3, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 3, 4, 2, 5, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 4, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 4, 4, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 4, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 5, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.3157 | 12.0 | 4704 | 2.4194 | 0.2920 | [4, 2, 2, 2, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 4, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 1, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 5, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 5, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 1, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 5, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.3145 | 13.0 | 5096 | 2.4124 | 0.2853 | [4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 5, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 4, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 5, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2858 | 14.0 | 5488 | 2.4124 | 0.2836 | [4, 2, 2, 5, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 5, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 3, 4, 4, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 4, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 3, 4, 3, 3, 2, 2, 4, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 1, 3, 2, 4, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 3, 1, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2827 | 15.0 | 5880 | 2.4265 | 0.2837 | [4, 2, 2, 5, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 5, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 3, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 3, 4, 2, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 4, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 5, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 5, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 5, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 5, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 5, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2928 | 16.0 | 6272 | 2.3855 | 0.2764 | [4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 4, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 4, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 0, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.288 | 17.0 | 6664 | 2.4111 | 0.2806 | [4, 2, 5, 5, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 1, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 5, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 1, 2, 2, 2, 3, 3, 1, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 5, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 1, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 4, 2, 2, 2, 3, 2, 4, 5, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 1, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 5, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 1, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 2, 4, 2, 1, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 1, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 5, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 4, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 5, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 5, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 5, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 1, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2846 | 18.0 | 7056 | 2.3785 | 0.2761 | [4, 2, 5, 5, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 5, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 4, 2, 2, 2, 3, 2, 4, 1, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 1, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 1, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 1, 2, 3, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 1, 2, 2, 3, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 0, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 3, 2, 2, 2, 2, 2, 1, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 5, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.253 | 19.0 | 7448 | 2.3593 | 0.2754 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 1, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 0, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 5, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 4, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 1, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 0, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 1, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 1, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.3019 | 20.0 | 7840 | 2.3459 | 0.2675 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 0, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 0, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 1, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 1, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 4, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 0, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 1, 2, 2, 2, 3, 1, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.251 | 21.0 | 8232 | 2.3395 | 0.2642 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 4, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 2, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 0, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 1, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 1, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 1, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 3, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 4, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 1, 1, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2373 | 22.0 | 8624 | 2.3683 | 0.2689 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 5, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 4, 2, 2, 2, 3, 2, 2, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 1, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 3, 2, 3, 2, 3, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 5, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 1, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 3, 2, 3, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 5, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 1, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2816 | 23.0 | 9016 | 2.3395 | 0.2640 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 1, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 1, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 1, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 0, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 0, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2753 | 24.0 | 9408 | 2.3414 | 0.2632 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 0, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 3, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 0, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 0, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2895 | 25.0 | 9800 | 2.3402 | 0.2638 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 1, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 0, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 3, 1, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 1, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2842 | 26.0 | 10192 | 2.3408 | 0.2639 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2755 | 27.0 | 10584 | 2.3408 | 0.2639 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
| 0.2636 | 28.0 | 10976 | 2.3408 | 0.2639 | [4, 2, 5, 2, 3, 2, 2, 2, 2, 3, 3, 2, 3, 2, 3, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 3, 2, 4, 2, 3, 4, 2, 2, 5, 2, 5, 2, 3, 3, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 3, 2, 3, 2, 2, 1, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 3, 2, 2, 2, 3, 2, 3, 2, 2, 3, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 4, 2, 3, 2, 2, 2, 3, 5, 5, 5, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 1, 3, 2, 2, 2, 2, 2, 4, 2, 3, 2, 1, 3, 4, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 3, 4, 2, 3, 2, 2, 2, 3, 5, 4, 2, 2, 2, 2, 4, 3, 3, 4, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 4, 2, 2, 2, 3, 5, 2, 0, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 4, 2, 2, 4, 2, 2, 3, 3, 2, 2, 2, 2, 4, 3, 3, 2, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 5, 2, 2, 2, 3, 3, 2, 2, 2, 4, 2, 4, 4, 4, 2, 3, 3, 2, 3, 2, 2, 3, 3, 3, 2, 2, 2, 4, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 1, 2, 3, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 4, 2, 2, 2, 1, 2, 4, 3, 2, 2, 2, 3, 2, 2, 2, 3, 4, 2, 3, 2, 2, 5, 4, 4, 2, 2, 5, 2, 3, 4, 2, 2, 2, 2, 2, 1, 3, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 0, 3, 4, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 5, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 4, 2, 2, 2, 2, 4, 2, 3, 2, 3, 2, 2, 3, 3, 2, 5, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 4, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 2, 4, 2, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 3, 4, 0, 3, 2, 2, 2, 2, 2, 2, 3, 2, 4, 3, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 4, 4, 2, 2, 4, 2, 4, 3, 2, 2, 2, 4, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 3, 2, 3, 2, 2, 1, 4, 2, 2, 2, 2, 2, 4, 4, 2, 5, 2, 2, 2, 2, 2, 2, 2, 4, 4, 3, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 5, 2, 3, 2, 4, 2, 2, 4, 2, 2, 3, 2, 3, 2, 2, 5, 4, 4, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 3, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 4, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 2, 4, 3, 2, 2, 3, 2, 2, 1, 5, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 3, 2, 2, 3, 3, 2, 2, 2, 3, 2, 1, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 3, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 3, 5, 2, 2, 5, 2, 3, 2, 2, 2, 2, 2, 2, 4, 2, 3, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 4, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 4, 2, 3, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 0, 2, 2, 2, 3, 0, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 5, 3, 3, 2, 2, 2, 2, 2, 5, 3, 2, 4, 2, 2, 2, 2, 2, 3, 5, 3, 4, 2, 5, 2, 2, 2, 2, 2, 3, 2, 2, 1, 2, 2, 3, 2, 4, 2, 2, 1, 1, 4, 2, 2, 2, 2, 2, 2, 0, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 2, 5, 2, 4, 2, 2, 2, 2, 3, 3, 2, 2, 2, 3, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 3, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 2, 3, 2, 1, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 4, 2, 5, 2, 2, 2, 4, 2, 5, 2, 2, 2, 2, 5, 2, 2, 2, 2, 2, 2, 3, 4, 2, 2, 3, 2, 2, 2, 5, 4, 3, 2, 2, 2, 2, 4, 2, 4, 2, 2, 3, 3, 2, 2, 3, 5, 4, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 4, 2, 2, 3, 2, 2, 2, 2, 2, 2, 3, 3, 3, 5, 4, 4, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 0, 4, 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 4, 2, 1, 2, 2, 4, 2, 2, 2, 2, 2, 3, 3, 2, 2, 2, 2, 2, 2, 4, 2, 2, 2, 2, 2, 3, 2, 2, 5] |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
DContrerasF/ppo-SnowballTarget | DContrerasF | 2023-11-16T18:08:26Z | 3 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
]
| reinforcement-learning | 2023-11-16T17:15:08Z | ---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: DContrerasF/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
noble6/siberia3600_llama2_7b_chat | noble6 | 2023-11-16T18:02:50Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-2-7b-chat-hf",
"base_model:adapter:meta-llama/Llama-2-7b-chat-hf",
"region:us"
]
| null | 2023-11-16T18:02:48Z | ---
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
---
# 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]
- **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 Data 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 Data 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]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.6.2
|
e-n-v-y/envy-digital-painting-xl-01 | e-n-v-y | 2023-11-16T17:51:55Z | 33 | 2 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"city",
"digital art",
"architecture",
"scenery",
"style",
"vibrant",
"landscape",
"clean",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:other",
"region:us"
]
| text-to-image | 2023-11-16T17:51:53Z | ---
license: other
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- city
- digital art
- architecture
- scenery
- style
- vibrant
- landscape
- clean
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: digital painting
widget:
- text: 'digital painting, infinite scifi subterranean city outside of the multiverse'
output:
url: >-
3659782.jpeg
- text: 'digital painting, mysterious,wonderous scifi megastructure beyond the end of time'
output:
url: >-
3659775.jpeg
- text: 'digital painting, Astral Plane'
output:
url: >-
3659779.jpeg
- text: 'digital painting, Arcane fantasy sky city beyond the end of time'
output:
url: >-
3659780.jpeg
- text: 'digital painting, infinite scifi megacity beyond the beginning of time'
output:
url: >-
3659781.jpeg
- text: 'digital painting, morning, blue sky, clouds, scenery, in a Dusky Experimental Agriculture Zone'
output:
url: >-
3659786.jpeg
- text: 'digital painting, forbidden,great scifi megacity beyond the beginning of the universe'
output:
url: >-
3659855.jpeg
- text: 'digital painting, Griffin''s Cliff'
output:
url: >-
3659857.jpeg
- text: 'digital painting, Immortal Flame Desert'
output:
url: >-
3659862.jpeg
---
# Envy Digital Painting XL 01
<Gallery />
<p>A clean, vibrant digital art style that shores up AI weaknesses in background details by keeping backgrounds vague.</p>
## Image examples for the model:
> digital painting, mysterious,wonderous scifi megastructure beyond the end of time
> digital painting, Astral Plane
> digital painting, Arcane fantasy sky city beyond the end of time
> digital painting, infinite scifi megacity beyond the beginning of time
> digital painting, morning, blue sky, clouds, scenery, in a Dusky Experimental Agriculture Zone
> digital painting, forbidden,great scifi megacity beyond the beginning of the universe
> digital painting, Griffin's Cliff
> digital painting, Immortal Flame Desert
|
ejgil03/LunarLander-v2 | ejgil03 | 2023-11-16T17:50:50Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T17:50:29Z | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 240.63 +/- 46.67
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
madhuprakash19/layoutlmv3-finetuned-cord_100 | madhuprakash19 | 2023-11-16T17:48:52Z | 3 | 0 | transformers | [
"transformers",
"pytorch",
"layoutlmv3",
"token-classification",
"generated_from_trainer",
"dataset:cord-layoutlmv3",
"base_model:microsoft/layoutlmv3-base",
"base_model:finetune:microsoft/layoutlmv3-base",
"license:cc-by-nc-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| token-classification | 2023-11-16T10:58:59Z | ---
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
datasets:
- cord-layoutlmv3
model-index:
- name: layoutlmv3-finetuned-cord_100
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. -->
# layoutlmv3-finetuned-cord_100
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord-layoutlmv3 dataset.
It achieves the following results on the evaluation set:
- eval_loss: 1.0986
- eval_precision: 0.6521
- eval_recall: 0.7365
- eval_f1: 0.6917
- eval_accuracy: 0.7593
- eval_runtime: 182.1992
- eval_samples_per_second: 0.549
- eval_steps_per_second: 0.11
- epoch: 1.56
- step: 250
## 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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
### Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.2
|
zrvicc/ppo-SnowballTarget | zrvicc | 2023-11-16T17:48:12Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
]
| reinforcement-learning | 2023-11-16T17:48:07Z | ---
library_name: ml-agents
tags:
- SnowballTarget
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SnowballTarget
---
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: zrvicc/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
SJBaba/phi-1_5-finetuned-gsm8k | SJBaba | 2023-11-16T17:41:15Z | 13 | 0 | transformers | [
"transformers",
"pytorch",
"mixformer-sequential",
"text-generation",
"generated_from_trainer",
"custom_code",
"base_model:microsoft/phi-1_5",
"base_model:finetune:microsoft/phi-1_5",
"license:other",
"autotrain_compatible",
"region:us"
]
| text-generation | 2023-10-31T18:54:08Z | ---
license: other
base_model: microsoft/phi-1_5
tags:
- generated_from_trainer
model-index:
- name: phi-1_5-finetuned-gsm8k
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. -->
# phi-1_5-finetuned-gsm8k
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the None 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 1000
### Training results
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1
|
ml-debi/EfficientNetV2S-Food101 | ml-debi | 2023-11-16T17:31:48Z | 2 | 0 | tf-keras | [
"tf-keras",
"tensorboard",
"image-classification",
"dataset:food101",
"license:mit",
"region:us"
]
| image-classification | 2023-11-16T17:27:22Z | ---
license: mit
datasets:
- food101
metrics:
- accuracy
pipeline_tag: image-classification
--- |
EgorGrinevich/scene_segmentation | EgorGrinevich | 2023-11-16T17:20:24Z | 1 | 0 | transformers | [
"transformers",
"tf",
"segformer",
"generated_from_keras_callback",
"base_model:nvidia/mit-b0",
"base_model:finetune:nvidia/mit-b0",
"license:other",
"endpoints_compatible",
"region:us"
]
| null | 2023-11-16T17:08:16Z | ---
license: other
base_model: nvidia/mit-b0
tags:
- generated_from_keras_callback
model-index:
- name: EgorGrinevich/scene_segmentation
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# EgorGrinevich/scene_segmentation
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: nan
- Validation Loss: nan
- Validation Mean Iou: 0.0024
- Validation Mean Accuracy: 0.0222
- Validation Overall Accuracy: 0.1310
- Validation Accuracy Wall: 1.0
- Validation Accuracy Building: 0.0
- Validation Accuracy Sky: 0.0
- Validation Accuracy Floor: 0.0
- Validation Accuracy Tree: 0.0
- Validation Accuracy Ceiling: 0.0
- Validation Accuracy Road: 0.0
- Validation Accuracy Bed : 0.0
- Validation Accuracy Windowpane: nan
- Validation Accuracy Grass: 0.0
- Validation Accuracy Cabinet: 0.0
- Validation Accuracy Sidewalk: 0.0
- Validation Accuracy Person: 0.0
- Validation Accuracy Earth: 0.0
- Validation Accuracy Door: 0.0
- Validation Accuracy Table: 0.0
- Validation Accuracy Mountain: nan
- Validation Accuracy Plant: 0.0
- Validation Accuracy Curtain: nan
- Validation Accuracy Chair: 0.0
- Validation Accuracy Car: 0.0
- Validation Accuracy Water: 0.0
- Validation Accuracy Painting: nan
- Validation Accuracy Sofa: nan
- Validation Accuracy Shelf: nan
- Validation Accuracy House: nan
- Validation Accuracy Sea: 0.0
- Validation Accuracy Mirror: nan
- Validation Accuracy Rug: nan
- Validation Accuracy Field: 0.0
- Validation Accuracy Armchair: nan
- Validation Accuracy Seat: 0.0
- Validation Accuracy Fence: nan
- Validation Accuracy Desk: 0.0
- Validation Accuracy Rock: nan
- Validation Accuracy Wardrobe: 0.0
- Validation Accuracy Lamp: nan
- Validation Accuracy Bathtub: nan
- Validation Accuracy Railing: 0.0
- Validation Accuracy Cushion: nan
- Validation Accuracy Base: nan
- Validation Accuracy Box: nan
- Validation Accuracy Column: nan
- Validation Accuracy Signboard: 0.0
- Validation Accuracy Chest of drawers: nan
- Validation Accuracy Counter: nan
- Validation Accuracy Sand: 0.0
- Validation Accuracy Sink: nan
- Validation Accuracy Skyscraper: nan
- Validation Accuracy Fireplace: 0.0
- Validation Accuracy Refrigerator: nan
- Validation Accuracy Grandstand: nan
- Validation Accuracy Path: nan
- Validation Accuracy Stairs: nan
- Validation Accuracy Runway: nan
- Validation Accuracy Case: nan
- Validation Accuracy Pool table: 0.0
- Validation Accuracy Pillow: nan
- Validation Accuracy Screen door: nan
- Validation Accuracy Stairway: nan
- Validation Accuracy River: nan
- Validation Accuracy Bridge: nan
- Validation Accuracy Bookcase: nan
- Validation Accuracy Blind: 0.0
- Validation Accuracy Coffee table: nan
- Validation Accuracy Toilet: nan
- Validation Accuracy Flower: nan
- Validation Accuracy Book: 0.0
- Validation Accuracy Hill: nan
- Validation Accuracy Bench: nan
- Validation Accuracy Countertop: 0.0
- Validation Accuracy Stove: nan
- Validation Accuracy Palm: nan
- Validation Accuracy Kitchen island: nan
- Validation Accuracy Computer: nan
- Validation Accuracy Swivel chair: nan
- Validation Accuracy Boat: nan
- Validation Accuracy Bar: nan
- Validation Accuracy Arcade machine: nan
- Validation Accuracy Hovel: nan
- Validation Accuracy Bus: 0.0
- Validation Accuracy Towel: 0.0
- Validation Accuracy Light: 0.0
- Validation Accuracy Truck: nan
- Validation Accuracy Tower: nan
- Validation Accuracy Chandelier: nan
- Validation Accuracy Awning: nan
- Validation Accuracy Streetlight: nan
- Validation Accuracy Booth: nan
- Validation Accuracy Television receiver: nan
- Validation Accuracy Airplane: 0.0
- Validation Accuracy Dirt track: nan
- Validation Accuracy Apparel: 0.0
- Validation Accuracy Pole: nan
- Validation Accuracy Land: nan
- Validation Accuracy Bannister: nan
- Validation Accuracy Escalator: nan
- Validation Accuracy Ottoman: nan
- Validation Accuracy Bottle: nan
- Validation Accuracy Buffet: nan
- Validation Accuracy Poster: nan
- Validation Accuracy Stage: nan
- Validation Accuracy Van: nan
- Validation Accuracy Ship: nan
- Validation Accuracy Fountain: nan
- Validation Accuracy Conveyer belt: nan
- Validation Accuracy Canopy: nan
- Validation Accuracy Washer: nan
- Validation Accuracy Plaything: nan
- Validation Accuracy Swimming pool: 0.0
- Validation Accuracy Stool: nan
- Validation Accuracy Barrel: nan
- Validation Accuracy Basket: 0.0
- Validation Accuracy Waterfall: nan
- Validation Accuracy Tent: 0.0
- Validation Accuracy Bag: nan
- Validation Accuracy Minibike: nan
- Validation Accuracy Cradle: nan
- Validation Accuracy Oven: nan
- Validation Accuracy Ball: nan
- Validation Accuracy Food: nan
- Validation Accuracy Step: nan
- Validation Accuracy Tank: nan
- Validation Accuracy Trade name: 0.0
- Validation Accuracy Microwave: nan
- Validation Accuracy Pot: nan
- Validation Accuracy Animal: nan
- Validation Accuracy Bicycle: nan
- Validation Accuracy Lake: 0.0
- Validation Accuracy Dishwasher: nan
- Validation Accuracy Screen: nan
- Validation Accuracy Blanket: nan
- Validation Accuracy Sculpture: nan
- Validation Accuracy Hood: 0.0
- Validation Accuracy Sconce: nan
- Validation Accuracy Vase: 0.0
- Validation Accuracy Traffic light: nan
- Validation Accuracy Tray: 0.0
- Validation Accuracy Ashcan: nan
- Validation Accuracy Fan: nan
- Validation Accuracy Pier: nan
- Validation Accuracy Crt screen: nan
- Validation Accuracy Plate: nan
- Validation Accuracy Monitor: nan
- Validation Accuracy Bulletin board: nan
- Validation Accuracy Shower: nan
- Validation Accuracy Radiator: nan
- Validation Accuracy Glass: nan
- Validation Accuracy Clock: nan
- Validation Accuracy Flag: nan
- Validation Iou Wall: 0.1065
- Validation Iou Building: 0.0
- Validation Iou Sky: 0.0
- Validation Iou Floor: 0.0
- Validation Iou Tree: 0.0
- Validation Iou Ceiling: 0.0
- Validation Iou Road: 0.0
- Validation Iou Bed : 0.0
- Validation Iou Windowpane: nan
- Validation Iou Grass: 0.0
- Validation Iou Cabinet: 0.0
- Validation Iou Sidewalk: 0.0
- Validation Iou Person: 0.0
- Validation Iou Earth: 0.0
- Validation Iou Door: 0.0
- Validation Iou Table: 0.0
- Validation Iou Mountain: nan
- Validation Iou Plant: 0.0
- Validation Iou Curtain: nan
- Validation Iou Chair: 0.0
- Validation Iou Car: 0.0
- Validation Iou Water: 0.0
- Validation Iou Painting: nan
- Validation Iou Sofa: nan
- Validation Iou Shelf: nan
- Validation Iou House: nan
- Validation Iou Sea: 0.0
- Validation Iou Mirror: nan
- Validation Iou Rug: nan
- Validation Iou Field: 0.0
- Validation Iou Armchair: nan
- Validation Iou Seat: 0.0
- Validation Iou Fence: nan
- Validation Iou Desk: 0.0
- Validation Iou Rock: nan
- Validation Iou Wardrobe: 0.0
- Validation Iou Lamp: nan
- Validation Iou Bathtub: nan
- Validation Iou Railing: 0.0
- Validation Iou Cushion: nan
- Validation Iou Base: nan
- Validation Iou Box: nan
- Validation Iou Column: nan
- Validation Iou Signboard: 0.0
- Validation Iou Chest of drawers: nan
- Validation Iou Counter: nan
- Validation Iou Sand: 0.0
- Validation Iou Sink: nan
- Validation Iou Skyscraper: nan
- Validation Iou Fireplace: 0.0
- Validation Iou Refrigerator: nan
- Validation Iou Grandstand: nan
- Validation Iou Path: nan
- Validation Iou Stairs: nan
- Validation Iou Runway: nan
- Validation Iou Case: nan
- Validation Iou Pool table: 0.0
- Validation Iou Pillow: nan
- Validation Iou Screen door: nan
- Validation Iou Stairway: nan
- Validation Iou River: nan
- Validation Iou Bridge: nan
- Validation Iou Bookcase: nan
- Validation Iou Blind: 0.0
- Validation Iou Coffee table: nan
- Validation Iou Toilet: nan
- Validation Iou Flower: nan
- Validation Iou Book: 0.0
- Validation Iou Hill: nan
- Validation Iou Bench: nan
- Validation Iou Countertop: 0.0
- Validation Iou Stove: nan
- Validation Iou Palm: nan
- Validation Iou Kitchen island: nan
- Validation Iou Computer: nan
- Validation Iou Swivel chair: nan
- Validation Iou Boat: nan
- Validation Iou Bar: nan
- Validation Iou Arcade machine: nan
- Validation Iou Hovel: nan
- Validation Iou Bus: 0.0
- Validation Iou Towel: 0.0
- Validation Iou Light: 0.0
- Validation Iou Truck: nan
- Validation Iou Tower: nan
- Validation Iou Chandelier: nan
- Validation Iou Awning: nan
- Validation Iou Streetlight: nan
- Validation Iou Booth: nan
- Validation Iou Television receiver: nan
- Validation Iou Airplane: 0.0
- Validation Iou Dirt track: nan
- Validation Iou Apparel: 0.0
- Validation Iou Pole: nan
- Validation Iou Land: nan
- Validation Iou Bannister: nan
- Validation Iou Escalator: nan
- Validation Iou Ottoman: nan
- Validation Iou Bottle: nan
- Validation Iou Buffet: nan
- Validation Iou Poster: nan
- Validation Iou Stage: nan
- Validation Iou Van: nan
- Validation Iou Ship: nan
- Validation Iou Fountain: nan
- Validation Iou Conveyer belt: nan
- Validation Iou Canopy: nan
- Validation Iou Washer: nan
- Validation Iou Plaything: nan
- Validation Iou Swimming pool: 0.0
- Validation Iou Stool: nan
- Validation Iou Barrel: nan
- Validation Iou Basket: 0.0
- Validation Iou Waterfall: nan
- Validation Iou Tent: 0.0
- Validation Iou Bag: nan
- Validation Iou Minibike: nan
- Validation Iou Cradle: nan
- Validation Iou Oven: nan
- Validation Iou Ball: nan
- Validation Iou Food: nan
- Validation Iou Step: nan
- Validation Iou Tank: nan
- Validation Iou Trade name: 0.0
- Validation Iou Microwave: nan
- Validation Iou Pot: nan
- Validation Iou Animal: nan
- Validation Iou Bicycle: nan
- Validation Iou Lake: 0.0
- Validation Iou Dishwasher: nan
- Validation Iou Screen: nan
- Validation Iou Blanket: nan
- Validation Iou Sculpture: nan
- Validation Iou Hood: 0.0
- Validation Iou Sconce: nan
- Validation Iou Vase: 0.0
- Validation Iou Traffic light: nan
- Validation Iou Tray: 0.0
- Validation Iou Ashcan: nan
- Validation Iou Fan: nan
- Validation Iou Pier: nan
- Validation Iou Crt screen: nan
- Validation Iou Plate: nan
- Validation Iou Monitor: nan
- Validation Iou Bulletin board: nan
- Validation Iou Shower: nan
- Validation Iou Radiator: nan
- Validation Iou Glass: nan
- Validation Iou Clock: nan
- Validation Iou Flag: nan
- Epoch: 9
## 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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 6e-05, 'decay_steps': 400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Accuracy Wall | Validation Accuracy Building | Validation Accuracy Sky | Validation Accuracy Floor | Validation Accuracy Tree | Validation Accuracy Ceiling | Validation Accuracy Road | Validation Accuracy Bed | Validation Accuracy Windowpane | Validation Accuracy Grass | Validation Accuracy Cabinet | Validation Accuracy Sidewalk | Validation Accuracy Person | Validation Accuracy Earth | Validation Accuracy Door | Validation Accuracy Table | Validation Accuracy Mountain | Validation Accuracy Plant | Validation Accuracy Curtain | Validation Accuracy Chair | Validation Accuracy Car | Validation Accuracy Water | Validation Accuracy Painting | Validation Accuracy Sofa | Validation Accuracy Shelf | Validation Accuracy House | Validation Accuracy Sea | Validation Accuracy Mirror | Validation Accuracy Rug | Validation Accuracy Field | Validation Accuracy Armchair | Validation Accuracy Seat | Validation Accuracy Fence | Validation Accuracy Desk | Validation Accuracy Rock | Validation Accuracy Wardrobe | Validation Accuracy Lamp | Validation Accuracy Bathtub | Validation Accuracy Railing | Validation Accuracy Cushion | Validation Accuracy Base | Validation Accuracy Box | Validation Accuracy Column | Validation Accuracy Signboard | Validation Accuracy Chest of drawers | Validation Accuracy Counter | Validation Accuracy Sand | Validation Accuracy Sink | Validation Accuracy Skyscraper | Validation Accuracy Fireplace | Validation Accuracy Refrigerator | Validation Accuracy Grandstand | Validation Accuracy Path | Validation Accuracy Stairs | Validation Accuracy Runway | Validation Accuracy Case | Validation Accuracy Pool table | Validation Accuracy Pillow | Validation Accuracy Screen door | Validation Accuracy Stairway | Validation Accuracy River | Validation Accuracy Bridge | Validation Accuracy Bookcase | Validation Accuracy Blind | Validation Accuracy Coffee table | Validation Accuracy Toilet | Validation Accuracy Flower | Validation Accuracy Book | Validation Accuracy Hill | Validation Accuracy Bench | Validation Accuracy Countertop | Validation Accuracy Stove | Validation Accuracy Palm | Validation Accuracy Kitchen island | Validation Accuracy Computer | Validation Accuracy Swivel chair | Validation Accuracy Boat | Validation Accuracy Bar | Validation Accuracy Arcade machine | Validation Accuracy Hovel | Validation Accuracy Bus | Validation Accuracy Towel | Validation Accuracy Light | Validation Accuracy Truck | Validation Accuracy Tower | Validation Accuracy Chandelier | Validation Accuracy Awning | Validation Accuracy Streetlight | Validation Accuracy Booth | Validation Accuracy Television receiver | Validation Accuracy Airplane | Validation Accuracy Dirt track | Validation Accuracy Apparel | Validation Accuracy Pole | Validation Accuracy Land | Validation Accuracy Bannister | Validation Accuracy Escalator | Validation Accuracy Ottoman | Validation Accuracy Bottle | Validation Accuracy Buffet | Validation Accuracy Poster | Validation Accuracy Stage | Validation Accuracy Van | Validation Accuracy Ship | Validation Accuracy Fountain | Validation Accuracy Conveyer belt | Validation Accuracy Canopy | Validation Accuracy Washer | Validation Accuracy Plaything | Validation Accuracy Swimming pool | Validation Accuracy Stool | Validation Accuracy Barrel | Validation Accuracy Basket | Validation Accuracy Waterfall | Validation Accuracy Tent | Validation Accuracy Bag | Validation Accuracy Minibike | Validation Accuracy Cradle | Validation Accuracy Oven | Validation Accuracy Ball | Validation Accuracy Food | Validation Accuracy Step | Validation Accuracy Tank | Validation Accuracy Trade name | Validation Accuracy Microwave | Validation Accuracy Pot | Validation Accuracy Animal | Validation Accuracy Bicycle | Validation Accuracy Lake | Validation Accuracy Dishwasher | Validation Accuracy Screen | Validation Accuracy Blanket | Validation Accuracy Sculpture | Validation Accuracy Hood | Validation Accuracy Sconce | Validation Accuracy Vase | Validation Accuracy Traffic light | Validation Accuracy Tray | Validation Accuracy Ashcan | Validation Accuracy Fan | Validation Accuracy Pier | Validation Accuracy Crt screen | Validation Accuracy Plate | Validation Accuracy Monitor | Validation Accuracy Bulletin board | Validation Accuracy Shower | Validation Accuracy Radiator | Validation Accuracy Glass | Validation Accuracy Clock | Validation Accuracy Flag | Validation Iou Wall | Validation Iou Building | Validation Iou Sky | Validation Iou Floor | Validation Iou Tree | Validation Iou Ceiling | Validation Iou Road | Validation Iou Bed | Validation Iou Windowpane | Validation Iou Grass | Validation Iou Cabinet | Validation Iou Sidewalk | Validation Iou Person | Validation Iou Earth | Validation Iou Door | Validation Iou Table | Validation Iou Mountain | Validation Iou Plant | Validation Iou Curtain | Validation Iou Chair | Validation Iou Car | Validation Iou Water | Validation Iou Painting | Validation Iou Sofa | Validation Iou Shelf | Validation Iou House | Validation Iou Sea | Validation Iou Mirror | Validation Iou Rug | Validation Iou Field | Validation Iou Armchair | Validation Iou Seat | Validation Iou Fence | Validation Iou Desk | Validation Iou Rock | Validation Iou Wardrobe | Validation Iou Lamp | Validation Iou Bathtub | Validation Iou Railing | Validation Iou Cushion | Validation Iou Base | Validation Iou Box | Validation Iou Column | Validation Iou Signboard | Validation Iou Chest of drawers | Validation Iou Counter | Validation Iou Sand | Validation Iou Sink | Validation Iou Skyscraper | Validation Iou Fireplace | Validation Iou Refrigerator | Validation Iou Grandstand | Validation Iou Path | Validation Iou Stairs | Validation Iou Runway | Validation Iou Case | Validation Iou Pool table | Validation Iou Pillow | Validation Iou Screen door | Validation Iou Stairway | Validation Iou River | Validation Iou Bridge | Validation Iou Bookcase | Validation Iou Blind | Validation Iou Coffee table | Validation Iou Toilet | Validation Iou Flower | Validation Iou Book | Validation Iou Hill | Validation Iou Bench | Validation Iou Countertop | Validation Iou Stove | Validation Iou Palm | Validation Iou Kitchen island | Validation Iou Computer | Validation Iou Swivel chair | Validation Iou Boat | Validation Iou Bar | Validation Iou Arcade machine | Validation Iou Hovel | Validation Iou Bus | Validation Iou Towel | Validation Iou Light | Validation Iou Truck | Validation Iou Tower | Validation Iou Chandelier | Validation Iou Awning | Validation Iou Streetlight | Validation Iou Booth | Validation Iou Television receiver | Validation Iou Airplane | Validation Iou Dirt track | Validation Iou Apparel | Validation Iou Pole | Validation Iou Land | Validation Iou Bannister | Validation Iou Escalator | Validation Iou Ottoman | Validation Iou Bottle | Validation Iou Buffet | Validation Iou Poster | Validation Iou Stage | Validation Iou Van | Validation Iou Ship | Validation Iou Fountain | Validation Iou Conveyer belt | Validation Iou Canopy | Validation Iou Washer | Validation Iou Plaything | Validation Iou Swimming pool | Validation Iou Stool | Validation Iou Barrel | Validation Iou Basket | Validation Iou Waterfall | Validation Iou Tent | Validation Iou Bag | Validation Iou Minibike | Validation Iou Cradle | Validation Iou Oven | Validation Iou Ball | Validation Iou Food | Validation Iou Step | Validation Iou Tank | Validation Iou Trade name | Validation Iou Microwave | Validation Iou Pot | Validation Iou Animal | Validation Iou Bicycle | Validation Iou Lake | Validation Iou Dishwasher | Validation Iou Screen | Validation Iou Blanket | Validation Iou Sculpture | Validation Iou Hood | Validation Iou Sconce | Validation Iou Vase | Validation Iou Traffic light | Validation Iou Tray | Validation Iou Ashcan | Validation Iou Fan | Validation Iou Pier | Validation Iou Crt screen | Validation Iou Plate | Validation Iou Monitor | Validation Iou Bulletin board | Validation Iou Shower | Validation Iou Radiator | Validation Iou Glass | Validation Iou Clock | Validation Iou Flag | Epoch |
|:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:------------------------:|:----------------------------:|:-----------------------:|:-------------------------:|:------------------------:|:---------------------------:|:------------------------:|:------------------------:|:------------------------------:|:-------------------------:|:---------------------------:|:----------------------------:|:--------------------------:|:-------------------------:|:------------------------:|:-------------------------:|:----------------------------:|:-------------------------:|:---------------------------:|:-------------------------:|:-----------------------:|:-------------------------:|:----------------------------:|:------------------------:|:-------------------------:|:-------------------------:|:-----------------------:|:--------------------------:|:-----------------------:|:-------------------------:|:----------------------------:|:------------------------:|:-------------------------:|:------------------------:|:------------------------:|:----------------------------:|:------------------------:|:---------------------------:|:---------------------------:|:---------------------------:|:------------------------:|:-----------------------:|:--------------------------:|:-----------------------------:|:------------------------------------:|:---------------------------:|:------------------------:|:------------------------:|:------------------------------:|:-----------------------------:|:--------------------------------:|:------------------------------:|:------------------------:|:--------------------------:|:--------------------------:|:------------------------:|:------------------------------:|:--------------------------:|:-------------------------------:|:----------------------------:|:-------------------------:|:--------------------------:|:----------------------------:|:-------------------------:|:--------------------------------:|:--------------------------:|:--------------------------:|:------------------------:|:------------------------:|:-------------------------:|:------------------------------:|:-------------------------:|:------------------------:|:----------------------------------:|:----------------------------:|:--------------------------------:|:------------------------:|:-----------------------:|:----------------------------------:|:-------------------------:|:-----------------------:|:-------------------------:|:-------------------------:|:-------------------------:|:-------------------------:|:------------------------------:|:--------------------------:|:-------------------------------:|:-------------------------:|:---------------------------------------:|:----------------------------:|:------------------------------:|:---------------------------:|:------------------------:|:------------------------:|:-----------------------------:|:-----------------------------:|:---------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------:|:-----------------------:|:------------------------:|:----------------------------:|:---------------------------------:|:--------------------------:|:--------------------------:|:-----------------------------:|:---------------------------------:|:-------------------------:|:--------------------------:|:--------------------------:|:-----------------------------:|:------------------------:|:-----------------------:|:----------------------------:|:--------------------------:|:------------------------:|:------------------------:|:------------------------:|:------------------------:|:------------------------:|:------------------------------:|:-----------------------------:|:-----------------------:|:--------------------------:|:---------------------------:|:------------------------:|:------------------------------:|:--------------------------:|:---------------------------:|:-----------------------------:|:------------------------:|:--------------------------:|:------------------------:|:---------------------------------:|:------------------------:|:--------------------------:|:-----------------------:|:------------------------:|:------------------------------:|:-------------------------:|:---------------------------:|:----------------------------------:|:--------------------------:|:----------------------------:|:-------------------------:|:-------------------------:|:------------------------:|:-------------------:|:-----------------------:|:------------------:|:--------------------:|:-------------------:|:----------------------:|:-------------------:|:-------------------:|:-------------------------:|:--------------------:|:----------------------:|:-----------------------:|:---------------------:|:--------------------:|:-------------------:|:--------------------:|:-----------------------:|:--------------------:|:----------------------:|:--------------------:|:------------------:|:--------------------:|:-----------------------:|:-------------------:|:--------------------:|:--------------------:|:------------------:|:---------------------:|:------------------:|:--------------------:|:-----------------------:|:-------------------:|:--------------------:|:-------------------:|:-------------------:|:-----------------------:|:-------------------:|:----------------------:|:----------------------:|:----------------------:|:-------------------:|:------------------:|:---------------------:|:------------------------:|:-------------------------------:|:----------------------:|:-------------------:|:-------------------:|:-------------------------:|:------------------------:|:---------------------------:|:-------------------------:|:-------------------:|:---------------------:|:---------------------:|:-------------------:|:-------------------------:|:---------------------:|:--------------------------:|:-----------------------:|:--------------------:|:---------------------:|:-----------------------:|:--------------------:|:---------------------------:|:---------------------:|:---------------------:|:-------------------:|:-------------------:|:--------------------:|:-------------------------:|:--------------------:|:-------------------:|:-----------------------------:|:-----------------------:|:---------------------------:|:-------------------:|:------------------:|:-----------------------------:|:--------------------:|:------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:-------------------------:|:---------------------:|:--------------------------:|:--------------------:|:----------------------------------:|:-----------------------:|:-------------------------:|:----------------------:|:-------------------:|:-------------------:|:------------------------:|:------------------------:|:----------------------:|:---------------------:|:---------------------:|:---------------------:|:--------------------:|:------------------:|:-------------------:|:-----------------------:|:----------------------------:|:---------------------:|:---------------------:|:------------------------:|:----------------------------:|:--------------------:|:---------------------:|:---------------------:|:------------------------:|:-------------------:|:------------------:|:-----------------------:|:---------------------:|:-------------------:|:-------------------:|:-------------------:|:-------------------:|:-------------------:|:-------------------------:|:------------------------:|:------------------:|:---------------------:|:----------------------:|:-------------------:|:-------------------------:|:---------------------:|:----------------------:|:------------------------:|:-------------------:|:---------------------:|:-------------------:|:----------------------------:|:-------------------:|:---------------------:|:------------------:|:-------------------:|:-------------------------:|:--------------------:|:----------------------:|:-----------------------------:|:---------------------:|:-----------------------:|:--------------------:|:--------------------:|:-------------------:|:-----:|
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 1 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 2 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 3 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 4 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 5 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 6 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 7 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 8 |
| nan | nan | 0.0024 | 0.0222 | 0.1310 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.1065 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | nan | 0.0 | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | 0.0 | 0.0 | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | nan | nan | nan | 0.0 | nan | 0.0 | nan | 0.0 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | 9 |
### Framework versions
- Transformers 4.35.2
- TensorFlow 2.14.0
- Datasets 2.15.0
- Tokenizers 0.15.0
|
codys12/Mistral-7b-Pathway-128k-4 | codys12 | 2023-11-16T17:17:07Z | 3 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:NousResearch/Yarn-Mistral-7b-128k",
"base_model:adapter:NousResearch/Yarn-Mistral-7b-128k",
"region:us"
]
| null | 2023-11-16T17:17:02Z | ---
library_name: peft
base_model: NousResearch/Yarn-Mistral-7b-128k
---
# 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]
## Training procedure
### Framework versions
- PEFT 0.6.3.dev0
|
BrighterIndia/rahul-gandhi-lora | BrighterIndia | 2023-11-16T17:15:00Z | 4 | 0 | diffusers | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
]
| text-to-image | 2023-11-12T20:09:08Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - BrighterIndia/rahul-gandhi-lora
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the BrighterIndia/rahul-gandhi-captions dataset |
hyperbored/memes_id | hyperbored | 2023-11-16T16:56:47Z | 8 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"pytorch",
"huggingpics",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| image-classification | 2023-11-16T16:56:40Z | ---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: memes_id
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.9253731369972229
---
# memes_id
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
#### DOTA2 memes
#### cat memes
#### dog memes
 |
khaimaitien/qa-expert-7B-V1.0-GGUF | khaimaitien | 2023-11-16T16:51:30Z | 25 | 2 | null | [
"gguf",
"endpoints_compatible",
"region:us"
]
| null | 2023-10-15T17:07:25Z | # Model Card for qa-expert-7B-V1.0-GGUF
<!-- Provide a quick summary of what the model is/does. -->
This repo contains the GGUF format model files for [khaimaitien/qa-expert-7B-V1.0](https://huggingface.co/khaimaitien/qa-expert-7B-V1.0).
You can get more information about how to **use/train** the model from this repo: https://github.com/khaimt/qa_expert
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [https://github.com/khaimt/qa_expert]
## How to Get Started with the Model
First, you need to clone the repo: https://github.com/khaimt/qa_expert
Then install the requirements:
```shell
pip install -r requirements.txt
```
Then install [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
Here is the example code:
```python
from qa_expert import get_inference_model, InferenceType
def retrieve(query: str) -> str:
# You need to implement this retrieval function, input is a query and output is a string
# This can be treated as the function to call in function calling of OpenAI
return context
model_inference = get_inference_model(InferenceType.llama_cpp, "qa-expert-7B-V1.0.q4_0.gguf")
answer, messages = model_inference.generate_answer(question, retriever_func)
```
|
onangeko/a2c-PandaPickAndPlace-v3 | onangeko | 2023-11-16T16:51:21Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaPickAndPlace-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T16:45:44Z | ---
library_name: stable-baselines3
tags:
- PandaPickAndPlace-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaPickAndPlace-v3
type: PandaPickAndPlace-v3
metrics:
- type: mean_reward
value: -50.00 +/- 0.00
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaPickAndPlace-v3**
This is a trained model of a **A2C** agent playing **PandaPickAndPlace-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
khaimaitien/qa-expert-7B-V1.0 | khaimaitien | 2023-11-16T16:47:51Z | 471 | 5 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2023-10-08T08:08:53Z | ---
language:
- en
pipeline_tag: text-generation
---
# Model Card for qa-expert-7B-V1.0
<!-- Provide a quick summary of what the model is/does. -->
This model aims to handle **Multi-hop Question answering** by splitting a multi-hop questions into a sequence of single questions, handle these single questions then summarize the information to get the final answer.
## Model Details
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the dataset: [khaimaitien/qa-expert-multi-hop-qa-V1.0](https://huggingface.co/datasets/khaimaitien/qa-expert-multi-hop-qa-V1.0)
You can get more information about how to **use/train** the model from this repo: https://github.com/khaimt/qa_expert
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [https://github.com/khaimt/qa_expert]
## How to Get Started with the Model
First, you need to clone the repo: https://github.com/khaimt/qa_expert
Then install the requirements:
```shell
pip install -r requirements.txt
```
Here is the example code:
```python
from qa_expert import get_inference_model, InferenceType
def retrieve(query: str) -> str:
# You need to implement this retrieval function, input is a query and output is a string
# This can be treated as the function to call in function calling of OpenAI
return context
model_inference = get_inference_model(InferenceType.hf, "khaimaitien/qa-expert-7B-V1.0")
answer, messages = model_inference.generate_answer(question, retriever_func)
```
|
bh8648/esg_test3-epoch2 | bh8648 | 2023-11-16T16:46:12Z | 0 | 0 | peft | [
"peft",
"region:us"
]
| null | 2023-11-16T16:46:02Z | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.5.0
|
abrahamtek/Taxi-v3-Agent2 | abrahamtek | 2023-11-16T16:45:08Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T16:43:52Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3-Agent2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.73
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="abrahamtek/Taxi-v3-Agent2", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
ksanchis/a2c-PandaReachDense-v3 | ksanchis | 2023-11-16T16:36:52Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T16:31:07Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v3
type: PandaReachDense-v3
metrics:
- type: mean_reward
value: -0.20 +/- 0.10
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
joshuapsa/setfit-news-topic-paragraphs | joshuapsa | 2023-11-16T16:35:59Z | 5 | 0 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
]
| text-classification | 2023-11-16T16:31:30Z | ---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# joshuapsa/setfit-news-topic-paragraphs
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
This model was finetuned with the custom dataset `joshuapsa/gpt-generated-news-paragraphs`, which is a synthetic dataset containing news paragraphs and their topics.<br>
Please refer to this to understand the label meanings of the prediction output.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("joshuapsa/setfit-news-topic-paragraphs")
# Run inference
preds = model(["Tensions escalated in the Taiwan Strait as Chinese and Taiwanese naval vessels engaged in a standoff, raising fears of a potential conflict. It has been 6 months since both sides started to engage in confrontational moves.",\
"Cape Town, South Africa, grappled with social unrest as citizens protested against inadequate government response to a public health crisis. The demonstrations brought attention to the intersection of healthcare, governance, and societal well-being."])
# The underlying model body of the setfit model is a SentenceTransformer model, hence you can use it to encode a raw sentence into dense embeddings:
emb = model.model_body.encode("Your sentence goes here")
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
VinayHajare/Reinforce-Pixelcopter-PLE-v0 | VinayHajare | 2023-11-16T16:35:19Z | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T16:35:16Z | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 39.10 +/- 28.83
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
owanr/SChem5Labels-google-t5-v1_1-large-intra-dataset-frequency-human-pairwise-mse-cycle2 | owanr | 2023-11-16T16:29:58Z | 0 | 0 | null | [
"generated_from_trainer",
"base_model:google/t5-v1_1-large",
"base_model:finetune:google/t5-v1_1-large",
"license:apache-2.0",
"region:us"
]
| null | 2023-11-16T16:29:57Z | ---
license: apache-2.0
base_model: google/t5-v1_1-large
tags:
- generated_from_trainer
model-index:
- name: SChem5Labels-google-t5-v1_1-large-intra-dataset-frequency-human-pairwise-mse-cycle2
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. -->
# SChem5Labels-google-t5-v1_1-large-intra-dataset-frequency-human-pairwise-mse-cycle2
This model is a fine-tuned version of [google/t5-v1_1-large](https://huggingface.co/google/t5-v1_1-large) on the None dataset.
It achieves the following results on the evaluation set:
- Train Loss: 12.3131
- Loss: 11.1611
- Losses: [18, 14, 9, 9, 9, 9, 13, 8, 12, 9, 12, 14, 9, 9, 11, 9, 9, 8, 9, 12, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 8, 9, 18, 13, 16, 14, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 12, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 15, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 20, 12, 9, 13, 20, 15, 9, 9, 9, 15, 8, 9, 9, 17, 12, 14, 9, 15, 12, 12, 12, 12, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 12, 13, 9, 11, 9, 9, 8, 11, 12, 9, 9, 13, 12, 8, 9, 19, 8, 9, 14, 11, 14, 15, 12, 9, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 14, 25, 12, 9, 12, 9, 8, 9, 10, 18, 9, 9, 12, 9, 20, 25, 12, 12, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 12, 13, 9, 9, 9, 9, 9, 9, 7, 12, 9, 17, 13, 26, 9, 12, 12, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 9, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 9, 25, 9, 10, 9, 12, 12, 14, 9, 8, 12, 18, 17, 9, 9, 12, 9, 12, 9, 8, 14, 9, 13, 10, 18, 25, 14, 8, 13, 8, 33, 9, 18, 9, 14, 12, 14, 12, 12, 12, 16, 13, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 8, 9, 9, 8, 16, 15, 20, 7, 12, 13, 13, 16, 12, 18, 9, 12, 14, 11, 12, 12, 11, 13, 9, 25, 9, 11, 8, 12, 12, 9, 9, 9, 8, 9, 12, 25, 9, 12, 9, 12, 11, 9, 15, 16, 9, 25, 14, 9, 11, 13, 9, 12, 9, 9, 9, 25, 10, 9, 9, 9, 12, 9, 20, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 12, 8, 10, 9, 23, 8, 12, 9, 8, 10]
## 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: 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: 200
### Training results
| Training Loss | Epoch | Step | Train Loss | Validation Loss | Losses |
|:-------------:|:-----:|:----:|:----------:|:---------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 20.864 | 1.0 | 25 | 12.7247 | 25.2159 | [18, 14, 10, 9, 9, 9, 13, 9, 12, 9, 9, 14, 9, 9, 11, 9, 10, 12, 9, 8, 42, 17, 9, 18, 25, 11, 14, 9, 42, 12, 16, 9, 9, 9, 13, 9, 18, 13, 16, 13, 8, 9, 9, 9, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 21, 12, 12, 12, 12, 9, 12, 8, 12, 24, 9, 12, 12, 12, 9, 17, 8, 9, 25, 9, 19, 9, 10, 12, 14, 42, 11, 9, 16, 9, 11, 9, 12, 9, 12, 13, 25, 18, 20, 17, 21, 10, 9, 9, 13, 9, 12, 7, 9, 9, 15, 7, 9, 9, 10, 12, 14, 42, 7, 12, 17, 16, 11, 10, 9, 11, 12, 15, 11, 13, 9, 11, 9, 11, 13, 9, 11, 9, 9, 9, 21, 12, 14, 9, 13, 17, 15, 9, 23, 8, 9, 13, 9, 9, 7, 12, 18, 9, 13, 11, 25, 13, 22, 9, 8, 14, 12, 9, 9, 24, 25, 12, 9, 9, 9, 7, 9, 10, 14, 9, 9, 10, 9, 9, 25, 12, 13, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 9, 13, 25, 9, 9, 9, 15, 9, 10, 9, 12, 25, 25, 11, 13, 9, 9, 13, 9, 9, 9, 9, 12, 9, 16, 22, 26, 9, 12, 8, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 8, 12, 8, 15, 9, 23, 10, 15, 12, 9, 15, 17, 14, 12, 10, 15, 9, 22, 11, 12, 9, 10, 9, 9, 12, 14, 9, 8, 8, 17, 17, 9, 9, 12, 9, 12, 9, 8, 13, 9, 13, 11, 18, 25, 14, 13, 13, 17, 18, 9, 18, 9, 14, 11, 12, 12, 25, 16, 9, 13, 9, 12, 9, 9, 42, 12, 13, 12, 12, 32, 8, 9, 9, 9, 8, 9, 15, 14, 9, 12, 13, 13, 21, 12, 9, 9, 12, 12, 11, 12, 12, 11, 11, 9, 25, 9, 11, 9, 12, 13, 9, 9, 9, 13, 9, 12, 25, 9, 12, 9, 12, 9, 9, 15, 16, 9, 12, 14, 9, 15, 22, 9, 12, 9, 8, 9, 23, 12, 9, 25, 42, 12, 9, 9, 8, 12, 9, 9, 9, 12, 9, 18, 16, 13, 12, 13, 17, 12, 9, 25, 15, 9, 9, 9, 9, 10, 9, 23, 25, 12, 9, 8, 10] |
| 20.6583 | 2.0 | 50 | 12.7904 | 24.9669 | [18, 14, 10, 9, 9, 9, 13, 9, 12, 9, 9, 14, 9, 9, 11, 9, 10, 12, 9, 8, 42, 17, 9, 18, 25, 11, 14, 9, 42, 12, 16, 9, 9, 9, 13, 9, 18, 13, 16, 13, 8, 9, 9, 9, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 21, 12, 12, 12, 12, 9, 12, 8, 12, 24, 9, 12, 12, 12, 9, 17, 8, 9, 25, 9, 19, 9, 10, 12, 15, 42, 11, 9, 16, 9, 11, 9, 12, 9, 12, 13, 25, 18, 20, 17, 21, 10, 9, 9, 13, 9, 12, 7, 9, 9, 15, 7, 9, 9, 10, 12, 14, 42, 7, 12, 17, 16, 11, 10, 9, 11, 12, 15, 11, 13, 9, 11, 23, 11, 13, 9, 11, 9, 9, 9, 21, 12, 14, 9, 13, 17, 15, 9, 23, 8, 9, 13, 9, 14, 7, 12, 18, 9, 13, 11, 25, 13, 22, 9, 8, 15, 12, 9, 9, 27, 25, 12, 9, 9, 9, 7, 9, 10, 14, 9, 9, 10, 9, 9, 25, 12, 13, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 9, 13, 25, 9, 9, 9, 15, 9, 10, 9, 12, 25, 25, 11, 13, 9, 9, 13, 9, 9, 9, 9, 12, 9, 16, 22, 26, 9, 12, 8, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 8, 12, 8, 15, 9, 23, 10, 15, 12, 9, 15, 17, 14, 12, 10, 15, 9, 22, 11, 12, 9, 10, 9, 9, 12, 14, 9, 8, 8, 17, 17, 9, 9, 12, 9, 12, 9, 8, 13, 9, 9, 11, 18, 25, 14, 13, 13, 17, 18, 9, 18, 9, 15, 11, 12, 12, 25, 16, 11, 13, 9, 12, 9, 9, 42, 12, 13, 12, 12, 32, 8, 9, 9, 9, 8, 11, 15, 14, 9, 12, 13, 13, 21, 12, 9, 9, 12, 14, 11, 12, 12, 11, 11, 9, 25, 9, 11, 9, 12, 13, 9, 9, 9, 13, 9, 12, 25, 9, 12, 9, 12, 9, 9, 15, 16, 9, 12, 14, 9, 15, 22, 9, 12, 9, 9, 9, 23, 10, 9, 25, 42, 12, 9, 9, 8, 12, 9, 9, 9, 12, 9, 18, 16, 13, 12, 13, 17, 12, 9, 25, 15, 9, 9, 9, 9, 10, 9, 23, 25, 12, 9, 8, 10] |
| 20.3473 | 3.0 | 75 | 12.7854 | 24.6459 | [18, 14, 10, 9, 9, 9, 13, 9, 12, 9, 9, 14, 9, 9, 11, 9, 10, 12, 9, 8, 42, 17, 9, 18, 25, 11, 14, 9, 42, 12, 16, 9, 9, 9, 13, 9, 18, 13, 16, 13, 8, 9, 9, 9, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 21, 12, 12, 12, 12, 9, 12, 8, 12, 24, 9, 12, 12, 12, 9, 17, 8, 9, 25, 9, 19, 9, 10, 12, 15, 42, 11, 9, 16, 9, 11, 9, 12, 9, 12, 13, 25, 18, 20, 17, 21, 9, 9, 9, 13, 9, 12, 7, 9, 9, 15, 7, 9, 9, 10, 12, 14, 42, 7, 12, 17, 16, 11, 10, 9, 8, 12, 15, 11, 13, 9, 11, 23, 11, 13, 9, 11, 9, 9, 9, 21, 12, 14, 9, 13, 17, 7, 9, 23, 8, 9, 13, 9, 14, 7, 12, 18, 9, 13, 11, 25, 13, 22, 9, 8, 15, 12, 9, 9, 27, 25, 12, 9, 9, 9, 7, 9, 10, 14, 9, 9, 10, 9, 9, 25, 12, 13, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 9, 13, 25, 9, 9, 9, 15, 9, 10, 9, 12, 25, 25, 11, 13, 9, 9, 13, 9, 9, 9, 9, 12, 9, 16, 22, 26, 9, 12, 8, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 8, 12, 8, 15, 9, 23, 10, 15, 12, 9, 15, 17, 14, 12, 10, 15, 9, 22, 11, 12, 9, 10, 9, 9, 12, 14, 9, 8, 8, 17, 17, 9, 9, 12, 9, 12, 9, 8, 13, 9, 13, 10, 18, 25, 14, 13, 13, 17, 18, 9, 18, 9, 15, 11, 12, 12, 25, 16, 9, 13, 9, 12, 9, 9, 42, 12, 13, 12, 12, 32, 8, 9, 9, 9, 8, 9, 15, 14, 9, 12, 13, 13, 21, 12, 19, 9, 12, 14, 11, 12, 12, 11, 11, 9, 25, 9, 11, 9, 12, 13, 9, 9, 9, 13, 9, 12, 25, 9, 12, 9, 12, 9, 9, 15, 16, 9, 12, 14, 9, 16, 22, 9, 12, 9, 9, 9, 23, 10, 9, 25, 42, 12, 9, 9, 8, 12, 9, 9, 9, 12, 9, 18, 16, 13, 12, 13, 17, 12, 9, 25, 15, 9, 9, 9, 9, 10, 9, 23, 25, 12, 9, 8, 10] |
| 19.6804 | 4.0 | 100 | 12.6187 | 23.7945 | [18, 14, 8, 9, 9, 9, 13, 9, 9, 17, 9, 14, 9, 9, 11, 9, 10, 12, 9, 8, 42, 17, 9, 18, 25, 11, 14, 9, 42, 12, 19, 9, 9, 9, 13, 9, 18, 13, 16, 13, 8, 9, 9, 9, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 21, 12, 12, 12, 12, 9, 12, 8, 9, 24, 9, 12, 12, 12, 9, 17, 8, 9, 25, 9, 19, 9, 10, 12, 15, 42, 11, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 17, 21, 14, 9, 9, 13, 9, 15, 7, 9, 9, 15, 8, 9, 9, 10, 12, 14, 9, 8, 12, 17, 16, 11, 10, 9, 22, 15, 15, 11, 13, 9, 11, 9, 11, 13, 9, 11, 9, 9, 9, 21, 12, 14, 9, 13, 17, 7, 9, 23, 8, 9, 13, 9, 14, 8, 12, 8, 9, 13, 13, 25, 13, 22, 12, 8, 15, 12, 9, 9, 27, 25, 12, 9, 9, 9, 8, 9, 10, 14, 9, 9, 10, 9, 9, 25, 12, 13, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 9, 9, 25, 9, 9, 9, 15, 9, 10, 9, 12, 25, 25, 11, 13, 9, 9, 9, 9, 9, 9, 9, 12, 9, 16, 22, 26, 9, 12, 8, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 8, 12, 8, 8, 9, 23, 10, 15, 12, 9, 15, 17, 14, 12, 10, 15, 9, 22, 11, 12, 9, 10, 9, 9, 12, 14, 9, 8, 8, 17, 17, 9, 9, 12, 9, 12, 9, 10, 13, 9, 13, 10, 18, 25, 14, 13, 13, 17, 18, 9, 18, 9, 15, 11, 12, 12, 25, 16, 12, 13, 9, 12, 9, 9, 9, 12, 13, 12, 12, 32, 8, 9, 9, 9, 8, 12, 15, 14, 9, 12, 13, 13, 21, 12, 12, 9, 12, 14, 11, 12, 12, 11, 11, 9, 25, 9, 11, 9, 12, 13, 9, 9, 9, 13, 9, 12, 25, 9, 12, 9, 12, 9, 9, 15, 16, 9, 12, 14, 9, 16, 22, 9, 11, 9, 9, 9, 23, 10, 9, 25, 42, 12, 9, 9, 8, 12, 9, 9, 9, 12, 9, 18, 16, 13, 12, 13, 17, 12, 9, 25, 15, 9, 9, 9, 9, 10, 9, 23, 17, 12, 9, 8, 10] |
| 18.9343 | 5.0 | 125 | 12.7298 | 19.5581 | [18, 14, 9, 9, 9, 9, 13, 9, 12, 17, 9, 14, 9, 9, 11, 9, 7, 11, 9, 8, 42, 17, 9, 18, 25, 11, 14, 9, 42, 12, 10, 9, 9, 9, 13, 9, 18, 13, 16, 13, 8, 9, 9, 9, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 21, 12, 12, 12, 12, 9, 12, 8, 12, 12, 9, 12, 12, 12, 9, 17, 8, 9, 25, 9, 19, 9, 9, 12, 15, 42, 11, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 17, 21, 14, 9, 9, 13, 9, 9, 9, 9, 9, 15, 12, 9, 9, 17, 12, 14, 9, 8, 12, 17, 16, 11, 12, 9, 22, 15, 15, 14, 14, 9, 9, 9, 11, 13, 9, 11, 9, 7, 8, 21, 12, 14, 9, 13, 12, 7, 9, 23, 8, 9, 13, 9, 14, 8, 12, 9, 9, 13, 13, 25, 13, 22, 12, 8, 15, 12, 24, 9, 26, 25, 12, 9, 9, 9, 12, 9, 10, 14, 9, 9, 10, 9, 9, 25, 12, 13, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 8, 25, 9, 9, 9, 15, 9, 13, 9, 17, 25, 25, 11, 13, 9, 9, 9, 9, 9, 9, 9, 12, 9, 16, 22, 26, 9, 12, 8, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 8, 12, 8, 10, 9, 23, 10, 15, 12, 9, 10, 17, 14, 12, 10, 15, 9, 22, 25, 13, 9, 10, 13, 9, 12, 14, 9, 8, 8, 17, 17, 9, 9, 12, 9, 12, 9, 10, 13, 9, 13, 10, 18, 25, 14, 13, 13, 17, 18, 9, 18, 9, 15, 11, 12, 12, 25, 16, 9, 9, 9, 12, 9, 9, 9, 12, 13, 12, 12, 32, 8, 9, 9, 9, 8, 9, 15, 14, 9, 12, 14, 13, 21, 12, 14, 9, 12, 14, 11, 12, 12, 11, 11, 9, 25, 14, 11, 9, 12, 13, 9, 9, 9, 13, 9, 12, 25, 9, 12, 9, 12, 9, 9, 15, 16, 9, 25, 14, 9, 15, 22, 9, 25, 9, 9, 9, 19, 12, 9, 25, 42, 12, 9, 8, 8, 12, 9, 9, 9, 11, 9, 18, 16, 13, 12, 13, 17, 12, 9, 25, 15, 9, 9, 9, 8, 10, 9, 23, 17, 12, 9, 8, 10] |
| 16.0724 | 6.0 | 150 | 12.3737 | 11.5288 | [18, 14, 9, 9, 9, 9, 13, 9, 12, 9, 9, 14, 9, 9, 11, 9, 9, 11, 9, 8, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 7, 9, 18, 13, 16, 13, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 28, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 25, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 9, 12, 9, 13, 20, 20, 9, 9, 9, 15, 22, 9, 9, 17, 12, 14, 9, 7, 12, 12, 12, 11, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 11, 13, 9, 11, 9, 7, 8, 21, 12, 8, 9, 13, 12, 7, 9, 23, 8, 9, 13, 9, 14, 7, 12, 8, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 26, 25, 12, 9, 12, 9, 22, 9, 10, 14, 9, 9, 12, 9, 20, 25, 12, 13, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 11, 13, 9, 9, 9, 9, 9, 9, 9, 12, 9, 17, 13, 26, 9, 12, 12, 19, 12, 15, 12, 21, 9, 25, 13, 12, 12, 9, 10, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 11, 25, 9, 10, 9, 9, 12, 14, 9, 8, 8, 18, 17, 9, 9, 12, 9, 12, 9, 10, 14, 9, 13, 10, 18, 25, 14, 7, 13, 8, 18, 9, 18, 9, 14, 11, 14, 12, 12, 12, 9, 9, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 9, 9, 9, 8, 9, 15, 20, 9, 12, 13, 13, 21, 9, 11, 9, 12, 14, 7, 12, 12, 11, 11, 9, 25, 9, 11, 8, 12, 13, 9, 9, 9, 7, 9, 12, 25, 9, 12, 9, 12, 9, 9, 15, 16, 9, 25, 14, 9, 16, 13, 9, 11, 9, 9, 9, 25, 10, 9, 25, 9, 12, 9, 14, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 9, 8, 10, 9, 23, 17, 12, 9, 9, 10] |
| 14.9913 | 7.0 | 175 | 12.3131 | 11.1611 | [18, 14, 9, 9, 9, 9, 13, 8, 12, 9, 12, 14, 9, 9, 11, 9, 9, 8, 9, 12, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 8, 9, 18, 13, 16, 14, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 12, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 15, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 20, 12, 9, 13, 20, 15, 9, 9, 9, 15, 8, 9, 9, 17, 12, 14, 9, 15, 12, 12, 12, 12, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 12, 13, 9, 11, 9, 9, 8, 11, 12, 9, 9, 13, 12, 8, 9, 19, 8, 9, 14, 11, 14, 15, 12, 9, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 14, 25, 12, 9, 12, 9, 8, 9, 10, 18, 9, 9, 12, 9, 20, 25, 12, 12, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 12, 13, 9, 9, 9, 9, 9, 9, 7, 12, 9, 17, 13, 26, 9, 12, 12, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 9, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 9, 25, 9, 10, 9, 12, 12, 14, 9, 8, 12, 18, 17, 9, 9, 12, 9, 12, 9, 8, 14, 9, 13, 10, 18, 25, 14, 8, 13, 8, 33, 9, 18, 9, 14, 12, 14, 12, 12, 12, 16, 13, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 8, 9, 9, 8, 16, 15, 20, 7, 12, 13, 13, 16, 12, 18, 9, 12, 14, 11, 12, 12, 11, 13, 9, 25, 9, 11, 8, 12, 12, 9, 9, 9, 8, 9, 12, 25, 9, 12, 9, 12, 11, 9, 15, 16, 9, 25, 14, 9, 11, 13, 9, 12, 9, 9, 9, 25, 10, 9, 9, 9, 12, 9, 20, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 12, 8, 10, 9, 23, 8, 12, 9, 8, 10] |
| 14.8962 | 8.0 | 200 | 12.3131 | 11.1611 | [18, 14, 9, 9, 9, 9, 13, 8, 12, 9, 12, 14, 9, 9, 11, 9, 9, 8, 9, 12, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 8, 9, 18, 13, 16, 14, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 12, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 15, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 20, 12, 9, 13, 20, 15, 9, 9, 9, 15, 8, 9, 9, 17, 12, 14, 9, 15, 12, 12, 12, 12, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 12, 13, 9, 11, 9, 9, 8, 11, 12, 9, 9, 13, 12, 8, 9, 19, 8, 9, 14, 11, 14, 15, 12, 9, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 14, 25, 12, 9, 12, 9, 8, 9, 10, 18, 9, 9, 12, 9, 20, 25, 12, 12, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 12, 13, 9, 9, 9, 9, 9, 9, 7, 12, 9, 17, 13, 26, 9, 12, 12, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 9, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 9, 25, 9, 10, 9, 12, 12, 14, 9, 8, 12, 18, 17, 9, 9, 12, 9, 12, 9, 8, 14, 9, 13, 10, 18, 25, 14, 8, 13, 8, 33, 9, 18, 9, 14, 12, 14, 12, 12, 12, 16, 13, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 8, 9, 9, 8, 16, 15, 20, 7, 12, 13, 13, 16, 12, 18, 9, 12, 14, 11, 12, 12, 11, 13, 9, 25, 9, 11, 8, 12, 12, 9, 9, 9, 8, 9, 12, 25, 9, 12, 9, 12, 11, 9, 15, 16, 9, 25, 14, 9, 11, 13, 9, 12, 9, 9, 9, 25, 10, 9, 9, 9, 12, 9, 20, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 12, 8, 10, 9, 23, 8, 12, 9, 8, 10] |
| 14.9872 | 9.0 | 225 | 12.3131 | 11.1611 | [18, 14, 9, 9, 9, 9, 13, 8, 12, 9, 12, 14, 9, 9, 11, 9, 9, 8, 9, 12, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 8, 9, 18, 13, 16, 14, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 12, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 15, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 20, 12, 9, 13, 20, 15, 9, 9, 9, 15, 8, 9, 9, 17, 12, 14, 9, 15, 12, 12, 12, 12, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 12, 13, 9, 11, 9, 9, 8, 11, 12, 9, 9, 13, 12, 8, 9, 19, 8, 9, 14, 11, 14, 15, 12, 9, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 14, 25, 12, 9, 12, 9, 8, 9, 10, 18, 9, 9, 12, 9, 20, 25, 12, 12, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 12, 13, 9, 9, 9, 9, 9, 9, 7, 12, 9, 17, 13, 26, 9, 12, 12, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 9, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 9, 25, 9, 10, 9, 12, 12, 14, 9, 8, 12, 18, 17, 9, 9, 12, 9, 12, 9, 8, 14, 9, 13, 10, 18, 25, 14, 8, 13, 8, 33, 9, 18, 9, 14, 12, 14, 12, 12, 12, 16, 13, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 8, 9, 9, 8, 16, 15, 20, 7, 12, 13, 13, 16, 12, 18, 9, 12, 14, 11, 12, 12, 11, 13, 9, 25, 9, 11, 8, 12, 12, 9, 9, 9, 8, 9, 12, 25, 9, 12, 9, 12, 11, 9, 15, 16, 9, 25, 14, 9, 11, 13, 9, 12, 9, 9, 9, 25, 10, 9, 9, 9, 12, 9, 20, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 12, 8, 10, 9, 23, 8, 12, 9, 8, 10] |
| 14.9044 | 10.0 | 250 | 12.3131 | 11.1611 | [18, 14, 9, 9, 9, 9, 13, 8, 12, 9, 12, 14, 9, 9, 11, 9, 9, 8, 9, 12, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 8, 9, 18, 13, 16, 14, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 12, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 15, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 20, 12, 9, 13, 20, 15, 9, 9, 9, 15, 8, 9, 9, 17, 12, 14, 9, 15, 12, 12, 12, 12, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 12, 13, 9, 11, 9, 9, 8, 11, 12, 9, 9, 13, 12, 8, 9, 19, 8, 9, 14, 11, 14, 15, 12, 9, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 14, 25, 12, 9, 12, 9, 8, 9, 10, 18, 9, 9, 12, 9, 20, 25, 12, 12, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 12, 13, 9, 9, 9, 9, 9, 9, 7, 12, 9, 17, 13, 26, 9, 12, 12, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 9, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 9, 25, 9, 10, 9, 12, 12, 14, 9, 8, 12, 18, 17, 9, 9, 12, 9, 12, 9, 8, 14, 9, 13, 10, 18, 25, 14, 8, 13, 8, 33, 9, 18, 9, 14, 12, 14, 12, 12, 12, 16, 13, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 8, 9, 9, 8, 16, 15, 20, 7, 12, 13, 13, 16, 12, 18, 9, 12, 14, 11, 12, 12, 11, 13, 9, 25, 9, 11, 8, 12, 12, 9, 9, 9, 8, 9, 12, 25, 9, 12, 9, 12, 11, 9, 15, 16, 9, 25, 14, 9, 11, 13, 9, 12, 9, 9, 9, 25, 10, 9, 9, 9, 12, 9, 20, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 12, 8, 10, 9, 23, 8, 12, 9, 8, 10] |
| 14.828 | 11.0 | 275 | 12.3131 | 11.1611 | [18, 14, 9, 9, 9, 9, 13, 8, 12, 9, 12, 14, 9, 9, 11, 9, 9, 8, 9, 12, 9, 18, 9, 18, 25, 9, 14, 9, 42, 12, 9, 9, 9, 9, 8, 9, 18, 13, 16, 14, 9, 9, 9, 13, 8, 9, 12, 9, 9, 15, 22, 15, 12, 9, 18, 12, 12, 12, 12, 9, 12, 8, 9, 25, 9, 12, 12, 12, 9, 18, 8, 9, 15, 9, 19, 9, 9, 12, 14, 9, 9, 9, 16, 9, 11, 9, 12, 19, 12, 13, 25, 18, 20, 12, 21, 20, 12, 9, 13, 20, 15, 9, 9, 9, 15, 8, 9, 9, 17, 12, 14, 9, 15, 12, 12, 12, 12, 12, 9, 9, 15, 15, 14, 14, 9, 9, 23, 12, 13, 9, 11, 9, 9, 8, 11, 12, 9, 9, 13, 12, 8, 9, 19, 8, 9, 14, 11, 14, 15, 12, 9, 9, 14, 13, 25, 13, 22, 12, 9, 14, 12, 13, 9, 14, 25, 12, 9, 12, 9, 8, 9, 10, 18, 9, 9, 12, 9, 20, 25, 12, 12, 9, 10, 14, 9, 12, 9, 13, 12, 9, 9, 13, 8, 9, 25, 9, 9, 9, 9, 14, 11, 9, 17, 12, 12, 12, 13, 9, 9, 9, 9, 9, 9, 7, 12, 9, 17, 13, 26, 9, 12, 12, 19, 11, 15, 12, 14, 9, 25, 13, 11, 12, 9, 9, 12, 11, 8, 9, 23, 10, 15, 12, 9, 9, 17, 14, 12, 10, 15, 9, 22, 9, 25, 9, 10, 9, 12, 12, 14, 9, 8, 12, 18, 17, 9, 9, 12, 9, 12, 9, 8, 14, 9, 13, 10, 18, 25, 14, 8, 13, 8, 33, 9, 18, 9, 14, 12, 14, 12, 12, 12, 16, 13, 9, 11, 9, 22, 9, 12, 13, 12, 12, 32, 8, 8, 9, 9, 8, 16, 15, 20, 7, 12, 13, 13, 16, 12, 18, 9, 12, 14, 11, 12, 12, 11, 13, 9, 25, 9, 11, 8, 12, 12, 9, 9, 9, 8, 9, 12, 25, 9, 12, 9, 12, 11, 9, 15, 16, 9, 25, 14, 9, 11, 13, 9, 12, 9, 9, 9, 25, 10, 9, 9, 9, 12, 9, 20, 9, 12, 9, 9, 9, 11, 9, 18, 16, 14, 12, 13, 15, 12, 9, 25, 9, 9, 9, 12, 8, 10, 9, 23, 8, 12, 9, 8, 10] |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
|
LeKyks1/Reinforce-cartpolev1 | LeKyks1 | 2023-11-16T16:21:26Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T16:21:17Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-cartpolev1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
CADM97/Reinforce | CADM97 | 2023-11-16T16:16:46Z | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
]
| reinforcement-learning | 2023-11-16T16:16:34Z | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
jangmin/midm-7b-safetensors-only | jangmin | 2023-11-16T16:08:37Z | 17 | 0 | transformers | [
"transformers",
"safetensors",
"midm-bitext-S",
"text-generation",
"custom_code",
"autotrain_compatible",
"region:us"
]
| text-generation | 2023-11-16T15:19:42Z | This is just a version of safetensors from [KT-AI/midm-bitext-S-7B-inst-v1](https://huggingface.co/KT-AI/midm-bitext-S-7B-inst-v1).
|
Subsets and Splits