modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-26 06:27:38
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 496
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-26 06:27:10
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
mmnga/aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf | mmnga | 2024-05-19T08:27:09Z | 390 | 4 | null | [
"gguf",
"mistral",
"en",
"ja",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-03-31T12:40:33Z | ---
license: apache-2.0
language:
- en
- ja
tags:
- mistral
---
# aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf
[aixsatoshiさんが公開しているHonyaku-Multi-Translator-Swallow-ms7b](https://huggingface.co/aixsatoshi/Honyaku-Multi-Translator-Swallow-ms7b)のggufフォーマット変換版です。
## 他のモデル
[mmnga/aixsatoshi-Honyaku-13b-gguf](https://huggingface.co/mmnga/aixsatoshi-Honyaku-13b-gguf)
[mmnga/aixsatoshi-Ex-karakuri-8x12B-chat-v1-gguf](https://huggingface.co/mmnga/aixsatoshi-Ex-karakuri-8x12B-chat-v1-gguf)
[mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf](https://huggingface.co/mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf)
[mmnga/aixsatoshi-Honyaku-7b-v2-gguf](https://huggingface.co/mmnga/aixsatoshi-Honyaku-7b-v2-gguf)
[mmnga/aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf](https://huggingface.co/mmnga/aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf)
[mmnga/aixsatoshi-Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2-gguf](https://huggingface.co/mmnga/aixsatoshi-Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2-gguf)
[mmnga/aixsatoshi-Mixtral-8x7B-ja-sft-ChatbotArenaJAcalm2-bnb4bit](https://huggingface.co/mmnga/aixsatoshi-Mixtral-8x7B-ja-sft-ChatbotArenaJAcalm2-bnb4bit)
[mmnga/aixsatoshi-calm2-7b-chat-7b-moe-gguf](https://huggingface.co/mmnga/aixsatoshi-calm2-7b-chat-7b-moe-gguf)
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-q4_0.gguf' -p "<english>: I'm going to take a bath now. </english>\n\n<japanese>:" -n 128
```
|
mmnga/aixsatoshi-Honyaku-7b-v2-gguf | mmnga | 2024-05-19T08:26:26Z | 107 | 1 | null | [
"gguf",
"mistral",
"en",
"ja",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-04-09T14:45:20Z | ---
license: apache-2.0
language:
- en
- ja
tags:
- mistral
---
# aixsatoshi-Honyaku-7b-v2-gguf
[aixsatoshiさんが公開しているHonyaku-7b-v2](https://huggingface.co/aixsatoshi/Honyaku-7b-v2)のggufフォーマット変換版です。
## 他のモデル
[mmnga/aixsatoshi-Honyaku-13b-gguf](https://huggingface.co/mmnga/aixsatoshi-Honyaku-13b-gguf)
[mmnga/aixsatoshi-Ex-karakuri-8x12B-chat-v1-gguf](https://huggingface.co/mmnga/aixsatoshi-Ex-karakuri-8x12B-chat-v1-gguf)
[mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf](https://huggingface.co/mmnga/aixsatoshi-Llama-3-8b-Cosmopedia-japanese-gguf)
[mmnga/aixsatoshi-Honyaku-7b-v2-gguf](https://huggingface.co/mmnga/aixsatoshi-Honyaku-7b-v2-gguf)
[mmnga/aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf](https://huggingface.co/mmnga/aixsatoshi-Honyaku-Multi-Translator-Swallow-ms7b-gguf)
[mmnga/aixsatoshi-Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2-gguf](https://huggingface.co/mmnga/aixsatoshi-Swallow-MX-8x7b-NVE-chatvector-Mixtral-instruct-v2-gguf)
[mmnga/aixsatoshi-Mixtral-8x7B-ja-sft-ChatbotArenaJAcalm2-bnb4bit](https://huggingface.co/mmnga/aixsatoshi-Mixtral-8x7B-ja-sft-ChatbotArenaJAcalm2-bnb4bit)
[mmnga/aixsatoshi-calm2-7b-chat-7b-moe-gguf](https://huggingface.co/mmnga/aixsatoshi-calm2-7b-chat-7b-moe-gguf)
## Usage
```
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'aixsatoshi-Honyaku-7b-v2-q4_0.gguf' -p "<english>: I'm going to take a bath now. </english>\n\n<japanese>:" -n 128
```
|
hansmueller464/Llama3-Aloe-8B-Alpha-Q8_0-GGUF | hansmueller464 | 2024-05-19T08:22:06Z | 5 | 0 | transformers | [
"transformers",
"gguf",
"biology",
"medical",
"llama-cpp",
"gguf-my-repo",
"question-answering",
"en",
"dataset:argilla/dpo-mix-7k",
"dataset:nvidia/HelpSteer",
"dataset:jondurbin/airoboros-3.2",
"dataset:hkust-nlp/deita-10k-v0",
"dataset:LDJnr/Capybara",
"dataset:HPAI-BSC/CareQA",
"dataset:GBaker/MedQA-USMLE-4-options",
"dataset:lukaemon/mmlu",
"dataset:bigbio/pubmed_qa",
"dataset:openlifescienceai/medmcqa",
"dataset:bigbio/med_qa",
"dataset:HPAI-BSC/better-safe-than-sorry",
"dataset:HPAI-BSC/pubmedqa-cot",
"dataset:HPAI-BSC/medmcqa-cot",
"dataset:HPAI-BSC/medqa-cot",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"conversational"
] | question-answering | 2024-05-19T08:21:43Z | ---
language:
- en
license: cc-by-nc-4.0
library_name: transformers
tags:
- biology
- medical
- llama-cpp
- gguf-my-repo
datasets:
- argilla/dpo-mix-7k
- nvidia/HelpSteer
- jondurbin/airoboros-3.2
- hkust-nlp/deita-10k-v0
- LDJnr/Capybara
- HPAI-BSC/CareQA
- GBaker/MedQA-USMLE-4-options
- lukaemon/mmlu
- bigbio/pubmed_qa
- openlifescienceai/medmcqa
- bigbio/med_qa
- HPAI-BSC/better-safe-than-sorry
- HPAI-BSC/pubmedqa-cot
- HPAI-BSC/medmcqa-cot
- HPAI-BSC/medqa-cot
pipeline_tag: question-answering
---
# hansmueller464/Llama3-Aloe-8B-Alpha-Q8_0-GGUF
This model was converted to GGUF format from [`HPAI-BSC/Llama3-Aloe-8B-Alpha`](https://huggingface.co/HPAI-BSC/Llama3-Aloe-8B-Alpha) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/HPAI-BSC/Llama3-Aloe-8B-Alpha) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo hansmueller464/Llama3-Aloe-8B-Alpha-Q8_0-GGUF --model llama3-aloe-8b-alpha.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo hansmueller464/Llama3-Aloe-8B-Alpha-Q8_0-GGUF --model llama3-aloe-8b-alpha.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama3-aloe-8b-alpha.Q8_0.gguf -n 128
```
|
apwic/sentiment-lora-r8a2d0.05-1 | apwic | 2024-05-19T08:13:33Z | 0 | 0 | null | [
"tensorboard",
"generated_from_trainer",
"id",
"base_model:indolem/indobert-base-uncased",
"base_model:finetune:indolem/indobert-base-uncased",
"license:mit",
"region:us"
] | null | 2024-05-19T07:40:24Z | ---
language:
- id
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment-lora-r8a2d0.05-1
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. -->
# sentiment-lora-r8a2d0.05-1
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3148
- Accuracy: 0.8697
- Precision: 0.8474
- Recall: 0.8328
- F1: 0.8395
## 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: 30
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.5657 | 1.0 | 122 | 0.5161 | 0.7243 | 0.6616 | 0.6474 | 0.6529 |
| 0.5088 | 2.0 | 244 | 0.4913 | 0.7393 | 0.6917 | 0.7056 | 0.6971 |
| 0.4682 | 3.0 | 366 | 0.4424 | 0.7845 | 0.7401 | 0.7425 | 0.7413 |
| 0.4114 | 4.0 | 488 | 0.3980 | 0.8095 | 0.7702 | 0.7702 | 0.7702 |
| 0.3862 | 5.0 | 610 | 0.3890 | 0.8145 | 0.7783 | 0.8088 | 0.7889 |
| 0.3512 | 6.0 | 732 | 0.3583 | 0.8496 | 0.8245 | 0.8036 | 0.8128 |
| 0.3428 | 7.0 | 854 | 0.3496 | 0.8521 | 0.8207 | 0.8254 | 0.8229 |
| 0.3254 | 8.0 | 976 | 0.3425 | 0.8496 | 0.8245 | 0.8036 | 0.8128 |
| 0.3226 | 9.0 | 1098 | 0.3388 | 0.8571 | 0.8310 | 0.8189 | 0.8245 |
| 0.3063 | 10.0 | 1220 | 0.3376 | 0.8647 | 0.8439 | 0.8217 | 0.8315 |
| 0.2939 | 11.0 | 1342 | 0.3319 | 0.8672 | 0.8463 | 0.8260 | 0.8351 |
| 0.2838 | 12.0 | 1464 | 0.3323 | 0.8546 | 0.8263 | 0.8196 | 0.8229 |
| 0.2916 | 13.0 | 1586 | 0.3283 | 0.8647 | 0.8472 | 0.8167 | 0.8296 |
| 0.2826 | 14.0 | 1708 | 0.3244 | 0.8672 | 0.8463 | 0.8260 | 0.8351 |
| 0.2739 | 15.0 | 1830 | 0.3231 | 0.8697 | 0.8449 | 0.8378 | 0.8412 |
| 0.2674 | 16.0 | 1952 | 0.3221 | 0.8697 | 0.8449 | 0.8378 | 0.8412 |
| 0.2648 | 17.0 | 2074 | 0.3193 | 0.8722 | 0.8528 | 0.8321 | 0.8413 |
| 0.2687 | 18.0 | 2196 | 0.3172 | 0.8697 | 0.8460 | 0.8353 | 0.8404 |
| 0.264 | 19.0 | 2318 | 0.3170 | 0.8747 | 0.8552 | 0.8363 | 0.8448 |
| 0.2637 | 20.0 | 2440 | 0.3148 | 0.8697 | 0.8474 | 0.8328 | 0.8395 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2
|
ilee0022/watercolor_stable_diffusion | ilee0022 | 2024-05-19T08:11:01Z | 31 | 2 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | 2024-05-18T12:34:08Z | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This is a Stable Diffusion Model v1.5 fine-tuned on watercolor images by Ivy Jee. All credits are given to the original image author of the image and the Stable Diffusion.
Link to image author website: https://www.behance.net/ivyjee
Prompt trained on:
A watercolour painting by Ivy Jee of a cat sitting on a roof overviewing a bay with a lighthouse during sunset.
A watercolour painting by Ivy Jee of a paper boat floating in a creek with green grasses at the bank.
Try:
A watercolour painting of winter by Ivy Jee
Best effects achieved by modifying these prompt slightly
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
joeyiexec/gemmapeft | joeyiexec | 2024-05-19T08:06:36Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-14T15:02:14Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
sddgs/taxi | sddgs | 2024-05-19T08:04:27Z | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | 2024-05-19T08:04:23Z | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.48 +/- 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="sddgs/taxi", 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"])
```
|
ebowwa/masterv0.2 | ebowwa | 2024-05-19T08:04:09Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T08:04:03Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** ebowwa
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Edgar-00/Models-RoBERTa-1716096876.881274 | Edgar-00 | 2024-05-19T08:02:58Z | 107 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-19T05:34:37Z | ---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Models-RoBERTa-1716096876.881274
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. -->
# Models-RoBERTa-1716096876.881274
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5419
- Accuracy: 0.8402
## 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 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2454 | 1.0 | 2455 | 0.6477 | 0.8280 |
| 0.2818 | 2.0 | 4910 | 0.5419 | 0.8402 |
| 0.1916 | 3.0 | 7365 | 0.7124 | 0.8394 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Leon-LLM/V67_LoRA_V63_GPT2-350k-Plus_10k_high_elo_4E_r64 | Leon-LLM | 2024-05-19T07:58:16Z | 0 | 0 | peft | [
"peft",
"arxiv:1910.09700",
"base_model:Leon-LLM/V63_GPT2_350k_4E_xLANplus_RIGHT_PAD",
"base_model:adapter:Leon-LLM/V63_GPT2_350k_4E_xLANplus_RIGHT_PAD",
"region:us"
] | null | 2024-05-19T07:58:14Z | ---
library_name: peft
base_model: Leon-LLM/V63_GPT2_350k_4E_xLANplus_RIGHT_PAD
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.10.0 |
cstr/llama3-8b-spaetzle-v20-int4-inc | cstr | 2024-05-19T07:55:21Z | 81 | 3 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"nbeerbower/llama-3-wissenschaft-8B-v2",
"conversational",
"en",
"de",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
] | text-generation | 2024-05-18T09:59:09Z | ---
tags:
- merge
- mergekit
- nbeerbower/llama-3-wissenschaft-8B-v2
license: llama3
language:
- en
- de
---
# llama3-8b-spaetzle-v20
llama3-8b-spaetzle-v20 is an int4-inc (intel auto-round) quantized merge of the following models:
* [cstr/llama3-8b-spaetzle-v13](https://huggingface.co/cstr/llama3-8b-spaetzle-v13)
* [Azure99/blossom-v5-llama3-8b](https://huggingface.co/Azure99/blossom-v5-llama3-8b)
* [VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct)
* [nbeerbower/llama-3-wissenschaft-8B-v2](https://huggingface.co/nbeerbower/llama-3-wissenschaft-8B-v2)
## Benchmarks
The GGUF q4_k_m version achieves on EQ-Bench v2_de 65.7 (171/171 parseable). From [Intel's low bit open llm leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard):
| Type | Model | Average ⬆️ | ARC-c | ARC-e | Boolq | HellaSwag | Lambada | MMLU | Openbookqa | Piqa | Truthfulqa | Winogrande | #Params (B) | #Size (G) |
|------|-------------------------------------------|------------|-------|-------|-------|-----------|---------|-------|------------|-------|------------|------------|-------------|-----------|
| 🍒 | **cstr/llama3-8b-spaetzle-v20-int4-inc** | **66.43** | **61.77** | **85.4** | **82.75** | **62.79** | **71.73** | **64.17** | **37.4** | **80.41** | **43.21** | **74.66** | **7.04** | **5.74** |
## 🧩 Configuration
```yaml
models:
- model: cstr/llama3-8b-spaetzle-v13
# no parameters necessary for base model
- model: nbeerbower/llama-3-wissenschaft-8B-v2
parameters:
density: 0.65
weight: 0.4
merge_method: dare_ties
base_model: cstr/llama3-8b-spaetzle-v13
parameters:
int8_mask: true
dtype: bfloat16
random_seed: 0
tokenizer_source: base
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "cstr/llama3-8b-spaetzle-v20"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
Abhinandha/abstract_sum | Abhinandha | 2024-05-19T07:52:09Z | 106 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:google-t5/t5-small",
"base_model:finetune:google-t5/t5-small",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-06T17:25:30Z | ---
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
model-index:
- name: abstract_sum
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. -->
# abstract_sum
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) 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: 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: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log | 1.0 | 9 | 2.5848 | 42.4953 | 21.3858 | 39.1441 | 39.5626 | 17.7647 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
joeyiexec/llama3peft | joeyiexec | 2024-05-19T07:50:41Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T07:50:28Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
bushali/PVLLM | bushali | 2024-05-19T07:44:55Z | 2 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:HuggingFaceM4/idefics-9b",
"base_model:adapter:HuggingFaceM4/idefics-9b",
"region:us"
] | null | 2024-05-19T07:42:47Z | ---
library_name: peft
base_model: HuggingFaceM4/idefics-9b
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.11.2.dev0 |
manufy/mnist_model_keras | manufy | 2024-05-19T07:38:22Z | 3 | 0 | keras | [
"keras",
"tf-keras",
"license:mit",
"region:us"
] | null | 2024-05-19T03:48:08Z | ---
license: mit
---
- keras model for digit recognigion 28x28x1 trained with mnist dataset
- only for testing purposes |
ib1368/ppo-LunarLander-v2 | ib1368 | 2024-05-19T07:37:58Z | 6 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2023-12-26T23:01:20Z | ---
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: 288.56 +/- 14.40
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
...
```
|
SSubhedar14/my-gpt2-model-wiki-qa | SSubhedar14 | 2024-05-19T07:34:16Z | 104 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-classification",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-19T07:27:32Z |
# GPT-2 Fine-Tuning on WikiQA Dataset
|
houbw/llama3_4 | houbw | 2024-05-19T07:32:57Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T07:32:41Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** houbw
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-8_0bpw_exl2 | Zoyd | 2024-05-19T07:28:34Z | 7 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"en",
"arxiv:2405.03548",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"exl2",
"region:us"
] | text-generation | 2024-05-19T07:12:28Z | ---
license: mit
language:
- en
---
# 🦣 MAmmoTH2: Scaling Instructions from the Web
Project Page: [https://tiger-ai-lab.github.io/MAmmoTH2/](https://tiger-ai-lab.github.io/MAmmoTH2/)
Paper: [https://arxiv.org/pdf/2405.03548](https://arxiv.org/pdf/2405.03548)
Code: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Introduction
Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 34% on MATH and from 36% to 67% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.
| | **Base Model** | **MAmmoTH2** | **MAmmoTH2-Plus** |
|:-----|:---------------------|:-------------------------------------------------------------------|:------------------------------------------------------------------|
| 7B | Mistral | 🦣 [MAmmoTH2-7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B) | 🦣 [MAmmoTH2-7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B-Plus) |
| 8B | Llama-3 | 🦣 [MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B) | 🦣 [MAmmoTH2-8B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus) |
| 8x7B | Mixtral | 🦣 [MAmmoTH2-8x7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B) | 🦣 [MAmmoTH2-8x7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B-Plus) |
## Training Data
Please refer to https://huggingface.co/datasets/TIGER-Lab/WebInstructSub for more details.
## Training Procedure
The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral and Mistal models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
## Evaluation
The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
| **Model** | **TheoremQA** | **MATH** | **GSM8K** | **GPQA** | **MMLU-ST** | **BBH** | **ARC-C** | **Avg** |
|:-----------------------|:--------------|:---------|:----------|:---------|:------------|:--------|:----------|:---------|
| **MAmmoTH2-7B** | 26.7 | 34.2 | 67.4 | 34.8 | 60.6 | 60.0 | 81.8 | 52.2 |
| **MAmmoTH2-8B** | 29.7 | 33.4 | 67.9 | 38.4 | 61.0 | 60.8 | 81.0 | 53.1 |
| **MAmmoTH2-8x7B** | 32.2 | 39.0 | 75.4 | 36.8 | 67.4 | 71.1 | 87.5 | 58.9 |
| **MAmmoTH2-7B-Plus** | 29.2 | 45.0 | 84.7 | 36.8 | 64.5 | 63.1 | 83.0 | 58.0 |
| **MAmmoTH2-8B-Plus** | 32.5 | 42.8 | 84.1 | 37.3 | 65.7 | 67.8 | 83.4 | 59.1 |
| **MAmmoTH2-8x7B-Plus** | 34.1 | 47.0 | 86.4 | 37.8 | 72.4 | 74.1 | 88.4 | 62.9 |
## Usage
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
Check our Github repo for more advanced use: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Limitations
We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.
## Citation
If you use the models, data, or code from this project, please cite the original paper:
```
@article{yue2024mammoth2,
title={MAmmoTH2: Scaling Instructions from the Web},
author={Yue, Xiang and Zheng, Tuney and Zhang, Ge and Chen, Wenhu},
journal={arXiv preprint arXiv:2405.03548},
year={2024}
}
``` |
wwgwwg/llama3-qq1 | wwgwwg | 2024-05-19T07:24:48Z | 0 | 0 | null | [
"safetensors",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:51:37Z | ---
license: apache-2.0
---
|
RichardErkhov/ghost-x_-_ghost-7b-alpha-8bits | RichardErkhov | 2024-05-19T07:21:37Z | 78 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-19T07:16:20Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
ghost-7b-alpha - bnb 8bits
- Model creator: https://huggingface.co/ghost-x/
- Original model: https://huggingface.co/ghost-x/ghost-7b-alpha/
Original model description:
---
language:
- en
- vi
license: other
license_name: ghost-7b
license_link: https://ghost-x.org/ghost-7b-license
library_name: transformers
tags:
- ghost
- tools
- chat
pipeline_tag: text-generation
widget:
- text: Why is the sky blue ?
output:
text: >-
The sky appears blue because of a phenomenon called Rayleigh scattering.
Sunlight is composed of all colors of the visible spectrum, but blue light
has a shorter wavelength than other colors. When sunlight enters the
Earth's atmosphere, it interacts with molecules of nitrogen and oxygen,
which are the main components of our atmosphere. These molecules scatter
the shorter wavelengths of light, such as blue and violet, more than the
longer wavelengths, such as red and orange. As a result, when we look up
at the sky, we see more blue light than other colors because the blue
light has been scattered more by the molecules in the atmosphere.
---
# Ghost 7B Alpha
<img src="https://cdn-uploads.huggingface.co/production/uploads/600ae38cc92b79f54efd4556/QPrQZMQX_jzyYngmreP0_.jpeg" alt="Ghost 7B Alpha Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
The large generation of language models focuses on optimizing excellent reasoning, multi-task knowledge, and tools support.
# Introduction
**Ghost 7B Alpha** is a large language model fine-tuned from Mistral 7B, with a size of 7 billion parameters. The model was developed with the goal of optimizing reasoning ability, multi-task knowledge and supporting tool usage. The model works well with the main trained and optimized languages being English and Vietnamese.
Overall, the model is suitable when making a pretrained version so you can continue to develop the desired tasks, develop virtual assistants, perform features on tasks such as coding, translation, answering questions, creating documents, etc. It is truly an efficient, fast and extremely cheap open model.
## Specifications
- Name: **Ghost 7B Alpha**.
- Model size: 7 billion parameters.
- Context length: 8K, 8192.
- Languages: English and Vietnamese.
- Main tasks: reasoning, multi-tasking knowledge and function tools.
- License: [Ghost 7B LICENSE AGREEMENT](https://ghost-x.org/ghost-7b-license).
- Based on: Mistral 7B.
- Distributions: Standard (BF16), GGUF, AWQ.
- Developed by: **Ghost X**, [Hieu Lam](https://huggingface.co/lamhieu).
### Links
- Card model: [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha).
- Official website: [Ghost 7B Alpha](https://ghost-x.org/docs/models/ghost-7b-alpha/).
- Demo: [Playground with Ghost 7B Alpha](https://ghost-x.org/docs/notebooks/playground-with-ghost-7b-alpha/).
## Distributions
We create many distributions to give you the best access options that best suit your needs. Always make sure you know which version you need and what will help you operate better.
| Version | Model card |
| ------- | -------------------------------------------------------------------- |
| BF16 | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha) |
| GGUF | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha-gguf) |
| AWQ | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha-awq) |
### Standard (BF16)
The standard distribution was used to run the assessments and was found to have the best performance in text generation quality.
### 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.
### AWQ
The AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
## Prompt / Chat template
### Roles
Overall, the model supports roles including: **system**, **plugins**, **user**, **assistant**, **execute**, **response**.
- **system**: Similar to OpenAI GPT4, this will be the place for you to declare context or specify characteristics and expertise for the model.
- **user**: This is user input, which can be a question or an instruction for the model to follow.
- **assistant**: The model's response to a question or instruction received from **user**.
- **plugins**: Declare information about modeling tools that are allowed to be used according to predetermined standards.
- **excute**: Mock iterates over the data type returned by the model for execution. Contains information about tools to use and arguments.
- **response**: The result after executing the tool, so that the model gives the appropriate answer according to the user's input.
See the actual code [here](https://huggingface.co/ghost-x/ghost-7b-alpha/blob/main/tokenizer_config.json#L36).
### Tips
- Setting the system prompt in the right context and characteristics will help the model improve performance quite well.
- You can set system prompt to prevent unwanted things.
- In most cases, if you have no idea you can leave the system prompt blank. At this point, the performance will be best for general cases.
### Chat template
#### Default chat
In the standard case, without using function tools, only use roles such as **system**, **user** and **assistant**. Conventions are in the following order:
- (1) **system**
- (2) **user**
- (3) **assistant**
Repeat (2) and (3) continuously throughout the conversation.
#### Chat with tools
In case of using tools, the conventions are in the following order:
- (1) **system**
- (2) **plugins**
- (3) **user**
- A. When the model finds it inappropriate to use the tool:
- (4) **assistant** if the model can answer or is not suitable for the tool. The model proceeds to answer the user's question.
- B. When the model chooses to use the tool:
- (4) **execute** returns the arguments needed to execute the specified tool.
- (5) **response** returns the results after applying the tool to the model.
- (6) **assistant** the model proceeds to answer the user's question.
Repeat (3) and (A) or (B) continuously throughout the conversation.
# Showcases
## English
Let's try a question taken from [OpenAI GPT-4](https://openai.com/gpt-4) to evaluate the superiority of GPT-4 compared to ChatGPT.
<details close>
<summary>👨💻 : Andrew is free from 11 am to 3 pm, Joanne is free from noon to 2 pm and then 3:30 pm to 5 pm. Hannah is available at noon for half an hour, and then 4 pm to 6 pm. What is the best option for start times for a 30 minute meeting for Andrew, Hannah, and Joanne at same time?</summary>
👻 :
The best option for a 30-minute meeting for Andrew, Hannah, and Joanne at the same time is to start at 12 pm (noon), as this is the earliest time when all three are available.
Here's the breakdown of their availability:
- Andrew: 11 am to 3 pm, which includes 12 pm.
- Joanne: Noon to 2 pm, which includes 12 pm.
- Hannah: Noon for half an hour (30 minutes), which includes 12 pm. Then she is available from 4 pm to 6 pm.
Since all three are available at 12 pm, this is the best time to start the meeting.
</details>
A quiz to see if the model can guess what it's talking about?!
<details close>
<summary>👨💻 : Characteristics: has a long, thin and flexible body; The legs are short and webbed. Additionally, their thick, smooth undercoat keeps them dry underwater and traps a layer of air to keep them warm. Question: What animal is that?</summary>
👻 :
Based on the characteristics you described, it seems like you're talking about an **otter**. Otters are carnivorous mammals that live in freshwater environments such as rivers, lakes, and estuaries. They have long, thin bodies with webbed feet that help them swim efficiently. Their thick, smooth undercoats keep them dry and warm, while the layer of air trapped beneath their fur helps to insulate them. Otters are known for their playful and curious nature, and they are often seen swimming, playing, and exploring their surroundings. 🦡🐭
</details>
To this question, I really cannot answer. But the model's evidence is quite strict. Also, what do you think about this answer?
<details close>
<summary>👨💻 : A self-driving car is approaching a crosswalk. A group of pedestrians is crossing the street, but they are not paying attention to the car because they are distracted by their phones. The car's brakes are malfunctioning, and it is unable to stop. Should the car swerve to avoid hitting the pedestrians, even though this could put the car's occupants at risk? Be convincing with your examples or sharp reasoning.</summary>
👻 :
In this situation, it is **imperative** for the self-driving car to swerve to avoid hitting the pedestrians, even if it puts the car's occupants at risk. Here's why:
**1. Prioritizing Human Safety:**
The primary goal of a self-driving car is to ensure the safety of its occupants and the general public. In this case, the pedestrians are in immediate danger due to their distraction and the malfunctioning brakes. Swerving to avoid the pedestrians is the safest option for all involved.
**2. Collision Avoidance:**
Swerving can help the car avoid a direct collision with the pedestrians, reducing the risk of serious injuries or even death. Even if the car's occupants are injured in the process of swerving, it is still better than the potential loss of life or severe injuries for multiple pedestrians.
**3. Legal and Ethical Responsibility:**
In most jurisdictions, self-driving cars are considered to be responsible for their actions. Swerving to avoid a collision is a reasonable and responsible action to take in this scenario. Failing to do so could result in legal consequences or ethical criticism.
**4. Precedent and Best Practices:**
In similar situations, self-driving cars have been programmed to swerve to avoid pedestrians. This practice has been widely accepted and considered to be the best course of action in such situations.
**5. Risk Assessment:**
While swerving can put the car's occupants at risk, the potential consequences of a collision with the pedestrians are much more severe. The risk of injury or death to multiple individuals outweighs the risk to the car's occupants.
In summary, the self-driving car's priority should be to protect the lives of pedestrians, even if it means putting its own occupants at risk. Swerving to avoid a collision is the responsible and ethical choice in this scenario.
</details>
A reasoning question suddenly popped up during the process of writing an article announcing information about **Ghost 7B Alpha**. The model gave an impressive answer, at least to its creator.
<details close>
<summary>👨💻 : If you could travel back in time and change one event in history, what would it be and why?</summary>
👻 :
If I could travel back in time and change one event in history, it would be the assassination of Archduke Franz Ferdinand of Austria on June 28, 1914. This event led to the start of World War I, which was one of the most devastating conflicts in human history. By changing this event, I could potentially prevent the war from happening, which would have far-reaching consequences for the world.
Here are some of the reasons why I would choose this event:
- **Preventing the deaths of millions of people:** World War I resulted in the deaths of over 17 million soldiers and civilians. Changing this event would save countless lives.
- **Preventing the economic and social devastation:** The war caused widespread economic and social devastation in Europe and around the world. By preventing the war, I could help to avoid these consequences.
- **Preventing the rise of fascism:** World War I created a power vacuum in Europe, which was eventually filled by fascist regimes in Germany, Italy, and Japan. By preventing the war, I could help to prevent the rise of these dangerous ideologies.
- **Preventing the development of nuclear weapons:** The war led to the development of nuclear weapons, which are the most destructive weapons ever created. By preventing the war, I could help to prevent the proliferation of these weapons and the threat they pose to humanity.
</details>
### Try coding skills
How about asking the model for instructions on creating a Node.js application using Docker for deployment?
<details close>
<summary>👨💻 : Create a Nodejs project using Express as a server and Docker with a Dockerfile for deployment with step-by-step instructions with detailed explanations.</summary>
👻 :
**Step 1: Create a new Node.js project**
```bash
mkdir my-project
cd my-project
npm init -y
```
**Step 2: Install Express**
```bash
npm install express --save
```
**Step 3: Create an Express server**
Create a file called `server.js` in your project directory:
```javascript
const express = require("express");
const app = express();
app.get("/", (req, res) => {
res.send("Hello World!");
});
app.listen(3000, () => {
console.log("Server listening on port 3000");
});
```
**Step 4: Create a Dockerfile**
Create a file called `Dockerfile` in your project directory:
```bash
FROM node:16
WORKDIR /usr/src/app
COPY package.json .
RUN npm install
COPY . .
EXPOSE 3000
CMD ["node", "server.js"]
```
**Step 5: Build the Docker image**
```bash
docker build -t my-project-image .
```
**Step 6: Run the Docker image**
```bash
docker run -p 3000:3000 my-project-image
```
**Step 7: Access the application**
Open a web browser and navigate to `http://localhost:3000`. You should see the message "Hello World!" displayed.
**Explanation:**
- **Step 1:** Creates a new Node.js project with `npm init -y` to initialize a new Node.js project with a default `package.json` file.
- **Step 2:** Installs Express using `npm install express --save`. This command installs Express and adds it to the `package.json` file.
- **Step 3:** Creates an Express server in `server.js` that responds with "Hello World!" when a request is made to the root path (`/`).
- **Step 4:** Creates a Dockerfile that defines the image for the project. The Dockerfile specifies that the image should use Node.js version 16, work from the `/usr/src/app` directory, copy the `package.json` file, install dependencies using `npm install`, copy the entire project directory, expose port 3000, and run the Express server using `node server.js`.
- **Step 5:** Builds the Docker image using `docker build -t my-project-image .`. This command builds the Docker image from the `Dockerfile` in the current directory and saves it under the name `my-project-image`.
- **Step 6:** Runs the Docker image using `docker run -p 3000:3000 my-project-image`. This command runs the Docker image and maps port 3000 on the host machine to port 3000 in the container.
- **Step 7:** Accesses the application by opening a web browser and navigating to `http://localhost:3000`. This will display the message "Hello World!" because the Express server is running in the Docker container.
</details>
Now let’s try asking for a coding model to build a smooth neural network with python.
<details close>
<summary>👨💻 : Explain how to use the Keras or TensorFlow library in Python to build and train a multi-layer neural network for an image classification task</summary>
👻 :
**Using Keras:**
1. Import the necessary libraries:
```python
import keras
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
```
2. Create a sequential model:
```python
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))
```
3. Compile the model:
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
```
4. Train the model:
```python
model.fit(x_train, y_train, epochs=10)
```
**Using TensorFlow:**
1. Import the necessary libraries:
```python
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
```
2. Create a sequential model:
```python
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))
```
3. Compile the model:
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
```
4. Train the model:
```python
model.train(x_train, y_train, epochs=10)
```
**Comparison:**
Both Keras and TensorFlow are powerful libraries for building and training neural networks in Python. However, there are some key differences between the two libraries:
- **Syntax:** Keras has a more concise and intuitive syntax, while TensorFlow has a more verbose and imperative syntax.
- **Performance:** TensorFlow is generally faster than Keras, especially for large datasets and complex models.
- **Integration:** TensorFlow has a wider range of integrations with other libraries and tools, while Keras is more focused on building and training neural networks.
Ultimately, the best choice for you depends on your specific needs and preferences. If you prefer a more concise and intuitive syntax, Keras is a good option. If you need a faster and more versatile library, TensorFlow is a better choice.
</details>
Let's try asking the model how to overcome the "hallucination" phenomenon in A.I development and give context for the model to provide a solution.
<details close>
<summary>👨💻 : Explain the cause of A.I hallucination and find a solution to overcome it, the specific context is LLMs.</summary>
👻 :
**Causes of A.I. Hallucination:**
- **Data Quality:** Incorrect or biased data can lead to hallucinations in LLMs. For example, if an LLM is trained on a dataset that contains biased or incomplete information, it may learn to generate biased or incomplete responses.
- **Model Architecture:** Certain model architectures are more susceptible to hallucinations than others. For example, Transformers, which are commonly used in LLMs, can be more prone to hallucinations than recurrent neural networks (RNNs).
- **Hyperparameters:** The hyperparameters of an LLM, such as the learning rate and the batch size, can also affect the likelihood of hallucinations. For example, a higher learning rate may lead to hallucinations more often than a lower learning rate.
**Solutions to Overcome A.I. Hallucination:**
- **Data Quality:** Ensure that the data used to train the LLM is accurate, complete, and unbiased. This can be done by cleaning the data, removing outliers, and using a variety of data sources.
- **Model Architecture:** Choose an LLM architecture that is less susceptible to hallucinations. For example, RNNs are generally less prone to hallucinations than Transformers.
- **Hyperparameters:** Tune the hyperparameters of the LLM to minimize the likelihood of hallucinations. This can be done by experimenting with different learning rates, batch sizes, and other hyperparameters.
- **Regularization Techniques:** Regularization techniques, such as dropout and early stopping, can help to prevent hallucinations by encouraging the LLM to learn more generalizable patterns.
- **Explicit Hallucination Detection:** Develop techniques to explicitly detect hallucinations in LLM-generated text. This can be done by using a variety of methods, such as text analysis, natural language processing, and machine learning.
- **User Feedback:** Collect feedback from users to identify and correct hallucinations in LLM-generated text. This can be done by using a variety of methods, such as surveys, feedback forms, and online discussions.
By implementing these solutions, you can significantly reduce the likelihood of hallucinations in LLMs and improve the quality of the generated text.
</details>
## Vietnamese
Try asking the model what it thinks about a famous quote to see if the answer feels natural.
<details close>
<summary>👨💻 : Bạn có đồng ý với câu nói "Điều duy nhất nguy hiểm hơn sự ngu dốt là sự kiêu ngạo" ?</summary>
👻 :
Tôi đồng ý với câu nói "Điều duy nhất nguy hiểm hơn sự ngu dốt là sự kiêu ngạo". Kiêu ngạo là một đức tính có thể dẫn đến nhiều hậu quả tiêu cực, chẳng hạn như sự tự mãn, sự ích kỷ và sự thiếu đồng cảm. Trong khi đó, sự ngu dốt chỉ là một thói hướng xấu thường xuất phát từ sự thiếu hiểu biết hoặc thiếu kinh nghiệm. Mặc dù sự ngu dốt cũng có thể gây ra một số vấn đề, nhưng những vấn đề này thường không nghiêm trọng bằng những vấn đề mà kiêu ngạo gây ra.
Ví dụ, một người ngu dốt có thể nói những lời ngớ ngẩn hoặc làm những việc vụng về, nhưng họ thường vẫn có thể học hỏi từ những sai lầm của mình và cải thiện bản thân. Ngược lại, một người kiêu ngạo thường sẽ không chịu học hỏi từ những sai lầm của mình và luôn tin rằng mình đúng, ngay cả khi mình sai. Điều này có thể dẫn đến nhiều vấn đề, chẳng hạn như sự thất bại trong công việc hoặc các mối quan hệ.
Do đó, tôi cho rằng câu nói "Điều duy nhất nguy hiểm hơn sự ngu dốt là sự kiêu ngạo" là đúng.
</details>
Explore the model's literary understanding by providing meaningful story prompts, asking to identify what the story is.
<details close>
<summary>👨💻 : Câu chuyện có nội dung và ý nghĩa chứa đựng một thông điệp ý nghĩa lớn đến tất cả mọi người, đó là tình đoàn kết, khao khát cho sự hòa bình và nghị lực phi thường trước mọi khó khăn. Có nhân vật chính là loài dế. Câu hỏi: câu chuyện đó của tác giả nào ?</summary>
👻 :
Câu chuyện "Dế Mèn phiêu lưu ký" của Tô Hoài.
**Giải thích:**
- "Dế Mèn phiêu lưu ký" là một tác phẩm văn học nổi tiếng của nhà văn Tô Hoài, được sáng tác năm 1941.
- Tác phẩm kể về cuộc phiêu lưu của Dế Mèn, một chú dế nhỏ sống trong một ngôi làng nhỏ. Trong quá trình phiêu lưu, Dế Mèn đã gặp gỡ và học hỏi nhiều điều về cuộc sống, về tình yêu, về sự hy sinh và về sức mạnh của tình đoàn kết.
- Tác phẩm thể hiện rõ tinh thần đoàn kết, khao khát cho sự hòa bình và nghị lực phi thường của con người trước mọi khó khăn, thử thách. Đây chính là thông điệp ý nghĩa lớn của câu chuyện "Dế Mèn phiêu lưu ký".
</details>
The ability to reason to the answer based on the characteristics of is provided.
<details close>
<summary>👨💻 : Con vật nào lớn hơn con chuột, nhỏ hơn con Voi, không quá lớn, không phải con chó và thường được nuôi ở nhà ?</summary>
👻 :
Con mèo là loài động vật lớn hơn con chuột nhưng nhỏ hơn con Voi, không quá lớn, không phải con chó và thường được nuôi ở nhà.
</details>
### Try coding skills
Try asking the Typescript coding model to perform finding the second largest number in the array to see if it works?
<details close>
<summary>👨💻 : Viết mã TypeScript để tạo một hàm thực hiện chức năng: cho mảng toàn số nguyên, tìm số lớn thứ hai trong mảng.
</summary>
👻 :
```typescript
/**
* Tìm số lớn thứ hai trong mảng.
*
* @param {number[]} arr Mảng các số nguyên.
* @returns {number} Số lớn thứ hai trong mảng.
*/
function findSecondLargest(arr: number[]): number {
// Kiểm tra xem mảng có ít nhất 2 phần tử không.
if (arr.length < 2) {
throw new Error('Mảng phải có ít nhất 2 phần tử.');
}
// Tìm số lớn nhất và số lớn thứ hai trong mảng.
let largest = arr[0];
let secondLargest = Number.MIN_SAFE_INTEGER;
for (let i = 1; i < arr.length; i++) {
if (arr[i] > largest) {
secondLargest = largest;
largest = arr[i];
} else if (arr[i] > secondLargest && arr[i] != largest) {
secondLargest = arr[i];
}
}
// Trả về số lớn thứ hai.
return secondLargest;
}
```
Giải thích:
1. Kiểm tra xem mảng có ít nhất 2 phần tử không. Nếu mảng chỉ có 1 phần tử hoặc ít hơn, thì không có số lớn thứ hai trong mảng. Trả về lỗi nếu điều kiện này đúng.
2. Khởi tạo hai biến `largest` và `secondLargest` với giá trị ban đầu là phần tử đầu tiên của mảng và số nguyên nhỏ nhất có thể biểu diễn được trong JavaScript (`Number.MIN_SAFE_INTEGER`), tương đương với `Integer.MIN_VALUE` trong Java.
3. Duyệt qua từng phần tử trong mảng, bắt đầu từ phần tử thứ hai. Nếu phần tử hiện tại lớn hơn `largest`, thì cập nhật `secondLargest` bằng `largest` và `largest` bằng phần tử hiện tại. Nếu phần tử hiện tại lớn hơn `secondLargest` nhưng nhỏ hơn `largest`, thì cập nhật `secondLargest` bằng phần tử hiện tại.
4. Sau khi duyệt qua tất cả các phần tử trong mảng, trả về `secondLargest`. Đây chính là số lớn thứ hai trong mảng.
</details>
Now let's try asking for a coding model to build a smooth neural network with python.
<details close>
<summary>👨💻 : Trình bày cách sử dụng thư viện Keras hoặc TensorFlow trong Python để xây dựng và huấn luyện mạng nơ-ron đa lớp cho bài toán phân loại ảnh.</summary>
👻 :
**Sử dụng thư viện Keras:**
1. **Nhập thư viện Keras:**
```python
import keras.models
```
2. **Tạo một mô hình mạng nơ-ron đa lớp:**
```python
model = keras.models.Sequential()
model.add(keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(224, 224, 3)))
model.add(keras.layers.MaxPooling2D((2, 2)))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128, activation='relu'))
model.add(keras.layers.Dense(2, activation='softmax'))
```
3. **Biên dịch và huấn luyện mô hình:**
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, validation_data=(x_test, y_test))
```
**Sử dụng thư viện TensorFlow:**
1. **Nhập thư viện TensorFlow:**
```python
import tensorflow as tf
```
2. **Tạo một mô hình mạng nơ-ron đa lớp:**
```python
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(224, 224, 3)))
model.add(tf.keras.layers.MaxPooling2D((2, 2)))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(2, activation='softmax'))
```
3. **Biên dịch và huấn luyện mô hình:**
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, validation_data=(x_test, y_test))
```
**Lưu ý:**
- Bạn có thể sử dụng các lớp mạng nơ-ron khác nhau trong mô hình, chẳng hạn như lớp mạng nơ-ron tích chập (Conv2D), lớp mạng nơ-ron lấy mẫu (MaxPooling2D), lớp mạng nơ-ron đầy đủ kết nối (Dense), lớp mạng nơ-ron softmax, v.v.
- Bạn có thể điều chỉnh số lớp, số nơ-ron trong mỗi lớp và số lần lặp (epochs) để tối ưu hóa mô hình cho bài toán cụ thể của bạn.
- Bạn có thể sử dụng các kỹ thuật huấn luyện bổ sung như dropout, regularization và early stopping để cải thiện hiệu suất của mô hình.
</details>
Try asking the model about common errors when deploying and using K8S to see what results the model gives.
<details close>
<summary>👨💻 : Những lỗi thường gặp trong quá trình sử dụng K8S là gì ? Hãy nêu cách khắc phục.</summary>
👻 :
**Những lỗi thường gặp trong quá trình sử dụng Kubernetes:**
**1. Lỗi cấu hình:**
* **Máy chủ Kubernetes không được cấu hình đúng:** Kiểm tra cấu hình máy chủ Kubernetes (master node) để đảm bảo rằng các thông số cần thiết như IP, cổng, tên miền, tên miền SSL, v.v. được đặt đúng.
* **Các pod không được cấu hình đúng:** Kiểm tra cấu hình pod để đảm bảo rằng các yếu tố như image, lưu trữ, mạng, v.v. được đặt đúng.
* **Các tài nguyên (resource) không được cấp phát đúng:** Kiểm tra xem các tài nguyên như CPU, bộ nhớ, lưu trữ, v.v. được cấp phát cho các pod có đủ hay không.
**2. Lỗi mạng:**
* **Mạng không được cấu hình đúng:** Kiểm tra cấu hình mạng để đảm bảo rằng các địa chỉ IP, cổng, tên miền, tên miền SSL, v.v. được cấu hình đúng.
* **Lỗi mạng giữa các node:** Kiểm tra xem có lỗi mạng giữa các node trong cụm Kubernetes hay không. Có thể sử dụng các công cụ như `netstat`, `ifconfig`, `tcpdump` để kiểm tra.
* **Lỗi mạng giữa các pod:** Kiểm tra xem có lỗi mạng giữa các pod trong một node hay không. Có thể sử dụng các công cụ như `netstat`, `ifconfig`, `tcpdump` để kiểm tra.
**3. Lỗi phần cứng:**
* **Phần cứng không đủ mạnh:** Kiểm tra xem phần cứng máy chủ Kubernetes có đủ mạnh để chạy cụm Kubernetes hay không. Cụ thể, kiểm tra xem CPU, bộ nhớ, lưu trữ, v.v. có đủ hay không.
* **Phần cứng bị lỗi:** Kiểm tra xem phần cứng máy chủ Kubernetes có bị lỗi hay không. Có thể sử dụng các công cụ như `lshw`, `dmesg` để kiểm tra.
**4. Lỗi phần mềm:**
* **Phần mềm Kubernetes không được cập nhật:** Kiểm tra xem phần mềm Kubernetes đang sử dụng có được cập nhật đến phiên bản mới nhất hay không. Cập nhật phần mềm Kubernetes thường giúp khắc phục các lỗi bảo mật và cải thiện hiệu suất.
* **Phần mềm Kubernetes có lỗi:** Kiểm tra xem phần mềm Kubernetes có lỗi hay không. Có thể sử dụng các công cụ như `journal`, `dmesg` để kiểm tra.
* **Các ứng dụng khách không được cập nhật:** Kiểm tra xem các ứng dụng khách đang sử dụng trên cụm Kubernetes có được cập nhật đến phiên bản mới nhất hay không. Cập nhật các ứng dụng khách thường giúp khắc phục các lỗi bảo mật và cải thiện hiệu suất.
**Cách khắc phục:**
* **Lỗi cấu hình:** Sửa các thông số cấu hình sai trong máy chủ Kubernetes và các pod. Ví dụ: đảm bảo rằng máy chủ Kubernetes có địa chỉ IP và cổng phù hợp, các pod có image và lưu trữ phù hợp, v.v.
* **Lỗi mạng:** Sửa các vấn đề về mạng giữa các node và các pod. Ví dụ: đảm bảo rằng mạng được cấu hình đúng, kiểm tra xem có lỗi mạng giữa các node hay không, kiểm tra xem có lỗi mạng giữa các pod hay không, v.v.
* **Lỗi phần cứng:** Nâng cấp phần cứng máy chủ Kubernetes nếu cần thiết. Ví dụ: tăng CPU, bộ nhớ, lưu trữ, v.v.
* **Lỗi phần mềm:** Cập nhật phần mềm Kubernetes và các ứng dụng khách. Ví dụ: cập nhật phiên bản mới nhất của Kubernetes, cập nhật các bản vá lỗi bảo mật cho các ứng dụng khách, v.v.
**Lưu ý:** Khi gặp phải lỗi trong quá trình sử dụng Kubernetes, cần phải xác định rõ nguyên nhân gốc rễ của lỗi trước khi có thể khắc phục. Việc xác định nguyên nhân gốc rễ sẽ giúp bạn tiết kiệm thời gian và công sức khi khắc phục lỗi.
</details>
## Tools / Function calls
The model is trained to be able to choose the right tools to use and to provide useful and accurate answers to the questions it receives. In this example, the model is asked for some information about Apple stock.
### Explain
This is the standard for declaring model tools, in `json` format. Also, See more about the model's [prompt / chat template](#prompt--chat-template).
```json
[
{
"type": "function",
"function": {
"name": "get_stock_info",
"description": "Get stock information",
"parameters": {
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Stock ticker",
"required": true
}
}
}
}
}
]
```
### Workflow
#### Turn 1
To use the tools, the model's supporting role is `plugin` which includes the declared tooling schema. Below is an example of `messages` with **turn 1** to use.
```python
# A question about Apple stocks in English language.
question = "What is Apple's market capitalization today?"
# It's still the same question but in Vietnamese languae.
# question = "Vốn hoá thị trường Apple hôm nay là bao nhiêu ?"
plugins = [
{
"type": "function",
"function": {
"name": "get_stock_info",
"description": "Get stock information",
"parameters": {
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Stock ticker",
"required": True,
}
},
},
},
}
]
messages = [
{"role": "system", "content": ""},
{"role": "plugins", "content": json.dumps(plugins, ensure_ascii=False)},
{"role": "user", "content": question},
]
output = generate_sample(
messages=messages,
max_new_tokens=256, temperature=0.4, top_k=50, top_p=0.95,
)
```
At this point, the model will return `output` as the primitive value as follows:
```plaintext
[execute]({"type": "function", "function": "get_stock_info", "arguments": {"ticker": "AAPL"}})
```
Use the `get_tools` function to parse the readable and usable results.
```json
{
"type": "function",
"function": "get_stock_info",
"arguments": {
"ticker": "AAPL"
}
}
```
#### Turn 2
Get information about tools to use with arguments. Use it to execute and return data, here we will assume the return data is as follows, sampled from **polygon.io** (cleaned up):
```json
{
"request_id": "1ffbab9cc78c7addbd8deaab05bdaf6d",
"results": {
"ticker": "AAPL",
"name": "Apple Inc.",
"market_cap": 2620023949270,
"description": "Apple is among the largest companies in the world, with a broad portfolio of hardware and software products targeted at consumers and businesses. Apple's iPhone makes up a majority of the firm sales, and Apple's other products like Mac, iPad, and Watch are designed around the iPhone as the focal point of an expansive software ecosystem. Apple has progressively worked to add new applications, like streaming video, subscription bundles, and augmented reality. The firm designs its own software and semiconductors while working with subcontractors like Foxconn and TSMC to build its products and chips. Slightly less than half of Apple's sales come directly through its flagship stores, with a majority of sales coming indirectly through partnerships and distribution.",
"ticker_root": "AAPL",
"homepage_url": "https://www.apple.com",
"total_employees": 161000,
...
},
"status": "OK"
}
```
Continue using the model to answer user questions based on the data returned from the tool.
```python
executes = {
"type": "function",
"function": "get_stock_info",
"arguments": {
"ticker": "AAPL"
}
}
results = {
"request_id": "1ffbab9cc78c7addbd8deaab05bdaf6d",
"results": {
"ticker": "AAPL",
"name": "Apple Inc.",
"market_cap": 2620023949270,
"description": "Apple is among the largest companies in the world, with a broad portfolio of hardware and software products targeted at consumers and businesses. Apple's iPhone makes up a majority of the firm sales, and Apple's other products like Mac, iPad, and Watch are designed around the iPhone as the focal point of an expansive software ecosystem. Apple has progressively worked to add new applications, like streaming video, subscription bundles, and augmented reality. The firm designs its own software and semiconductors while working with subcontractors like Foxconn and TSMC to build its products and chips. Slightly less than half of Apple's sales come directly through its flagship stores, with a majority of sales coming indirectly through partnerships and distribution.",
"ticker_root": "AAPL",
"homepage_url": "https://www.apple.com",
"total_employees": 161000,
},
"status": "OK"
}
messages = [
{"role": "system", "content": ""},
{"role": "plugins","content": json.dumps(plugins, ensure_ascii=False)},
{"role": "user","content": question},
# Keep the value of `messages` from before, just add new items below.
{"role": "execute","content": json.dumps(executes, ensure_ascii=False)},
{"role": "response","content": json.dumps(results, ensure_ascii=False)},
]
output = generate_sample(
messages=messages,
max_new_tokens=256, temperature=0.4, top_k=50, top_p=0.95,
)
```
The value of `output` returned by the model will now be similar to the following.
For the question is English.
```plaintext
Apple's market capitalization today is $2.62 trillion.
```
And the question is Vietnamese.
```plaintext
Vốn hoá thị trường của Apple hôm nay là **2.620 tỷ đô la**. 💰
```
# Usage
The model is trained to serve well and balance general tasks, so there will be many approaches when used for production.
## Things to know
### Recommendations
#### General tasks
Experience it to find the right fit for your own desires. Below are some suggestions that you might consider.
##### Answer the questions
In this task, the model can be integrated to develop RAG products to help answer questions for customer care departments, questions about internal documents, policies, product information, order details, etc.
##### Coding support
In this task, the model can help find errors or write algorithms and functions that help speed up the domain development process and improve product quality.
##### Content creation
In this task, the model can give suggestions for building layouts and content samples that need high creativity and personality in the content.
##### Other
Don't limit your creativity to the model. Feel free to experience it and use it to build good things.
#### Virtual assistant
An understanding of the language along with the overall capabilities of the model, may be suitable for integrating its development as a set of one or more tasks in the development of an intelligent virtual assistant.
The model is trained to understand and empathize emotionally, making the response more natural and understanding. This also helps a lot with this request.
#### As a pre-training
The model can be further trained to serve the desired tasks better and more effectively if it cannot satisfy the given requirements.
Taking advantage of the model's current superior inference and multi-tasking capabilities, training it for a few separate tasks will help save a lot of effort, time and cost for the project.
Revealed, the model has been integrated to replace some tasks that were previously used by OpenAI GPT4 in the business/product that the founder has been working on. For those tasks, the model is considered effective compared to the cost and is very worthy.
### Bias and limitations
In addition, there are some things you need to know before using as follows:
#### Generation configuration
The **temperature** affects the truth of the answer. Setting a **temperature** value greater than 0.2 - 0.4 will result in a more creative answer but may affect the accuracy of the answer, please consider this based on your task.
Hint: you can write a prompt to receive input and ask the model to choose the appropriate temperature based on the question, useful in the case of virtual assistant development.
#### Emotion bias and empathy
The model is built with an emotional bias and takes positions when faced with problems or reasoning questions. This can be good or bad depending on the context. If you don't want the model to be rigid in asking certain questions or problems, set up rules in the system prompt for it.
This bias often appears when the model's system prompt sets it up as an assistant and mentions that it needs to have empathy for/with a certain user/experience. This is intentional during the model training process, it does not come from something unforeseen.
## Directly
To use the model directly, there are many ways to get started, choose one of the following ways to experience it.
### Transformers
For direct use with `transformers`, you can easily get started with the following steps.
- Firstly, you need to install transformers via the command below with `pip`.
```bash
pip install -U transformers
```
- Right now, you can start using the model directly.
```python
import torch
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
)
base_model = "ghost-x/ghost-7b-alpha"
model = AutoModelForCausalLM.from_pretrained(
base_model,
torch_dtype=torch.bfloat16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(base_model)
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": "Why is the sky blue ?"},
# {"role": "user", "content": "Tại sao bầu trời lại màu xanh ?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, temperature=0.4)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
- Additionally, you can also use a model with **4bit quantization** to reduce the required resources at least. You can start with the code below.
```python
import torch
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
base_model = "ghost-x/ghost-7b-alpha"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=False,
)
model = AutoModelForCausalLM.from_pretrained(
base_model,
quantization_config=bnb_config,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(base_model)
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": "Why is the sky blue ?"},
# {"role": "user", "content": "Tại sao bầu trời lại màu xanh ?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, temperature=0.4)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
### Unsloth
For direct use with `unsloth`, you can easily get started with the following steps.
- Firstly, you need to install unsloth via the command below with `pip`.
```bash
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps xformers trl peft accelerate bitsandbytes
```
- Initialize and optimize the model before use.
```python
from unsloth import FastLanguageModel
import torch
base_model = "ghost/ghost-7b-alpha"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = base_model,
max_seq_length = 8192,
dtype = None,
load_in_4bit = True, # Change to `False` if you don't want to use 4bit quantization.
)
FastLanguageModel.for_inference(model)
```
- Right now, you can start using the model directly.
```python
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": "Why is the sky blue ?"},
# {"role": "user", "content": "Tại sao bầu trời lại màu xanh ?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, temperature=0.4)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
## Online
The content of this document will be updated soon. The documentation will guide usage through providers such as Huggingface Inference API, Together AI, or Replicate.
## Playground
To make it easy for everyone to quickly experience the model through platforms like **Google Colab** and **Kaggle**. We’ve made these notebooks available so you can get started right away. See available notebooks with details [here](https://ghost-x.org/docs/notebooks/playground-with-ghost-7b-alpha/).
We offer notebooks with a wide selection of tools and platforms so you can easily get started. Here are some available options for you to try right now. Let’s pick one to get started.
There are currently two language versions: English and Vietnamese. In each version, it will be almost the same. The content will include installation instructions and functions to help get started quickly with experiencing the model's text generation capabilities. In addition, it also provides examples with system prompts for each field so you can better understand them.
#### Playground using Transformers
- [Kaggle @ Ghost 7B Alpha - Playground using Transformers, Vietnamese](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-transformers-vi).
- [Colab @ Ghost 7B Alpha - Playground using Transformers, Vietnamese](https://colab.research.google.com/drive/14Cv6oT0pks3NoIUcXscAU9wex9A2T5H5?usp=sharing).
- [Kaggle @ Ghost 7B Alpha - Playground using Transformers, English](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-transformers-en).
- [Colab @ Ghost 7B Alpha - Playground using Transformers, English](https://colab.research.google.com/drive/1lzgywm333wZIt5WNDs0ZajDvK7lm_Zy9?usp=sharing).
#### Playground using Unsloth
- [Kaggle @ Ghost 7B Alpha - Playground using Unsloth, Vietnamese](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-unsloth-vi).
- [Colab @ Ghost 7B Alpha - Playground using Unsloth, Vietnamese](https://colab.research.google.com/drive/1E7QuthR33een9Otkepue5zFughCpab4P?usp=sharing).
- [Kaggle @ Ghost 7B Alpha - Playground using Unsloth, English](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-unsloth-en).
- [Colab @ Ghost 7B Alpha - Playground using Unsloth, English](https://colab.research.google.com/drive/1u04RbzD87_AovQngWsUv-O_Q6YNj7Hzr?usp=sharing).
Revealing, experience with Kaggle will give you much better results in creating documents than Colab. We recommend using Kaggle.
## Deployments
The models developed by **Ghost X** have the same goal of being easy to integrate and use in practice to save costs and facilitate development for the community and startups.
For production deployment with small to large infrastructure, please see more detailed instructions in [this article](https://ghost-x.org/docs/guides/deployments/). The article will provide the most common and effective deployment solutions with leading, trusted libraries such as vLLM and more. In addition, it also has information about more optimal solutions and methods depending on each need to be able to choose the appropriate solution.
# Evaluation
To ensure effective model development, we ran popular evaluations to give everyone a broader view of the model's capabilities. We had to work to balance the quality between the English and Vietnamese languages to ensure the model still performed well in both of these primary languages.
In addition, if your goals are oriented towards a certain main language, you can refer to the advanced user guide to improve model quality for the tasks and languages you desire.
## Open LLM Leaderboard
The results of this evaluation will be updated soon.
## MT-Bench
MT-bench is a challenging multi-turn question set designed to evaluate the conversational and instruction-following ability of models. [[source from lmsys.org]](https://lmsys.org/blog/2023-06-22-leaderboard)
**Ghost 7B Alpha** achieved a decent score for the MT-Bench review, we worked hard to balance the reasoning ability and linguistic insight of both primary languages, English and Vietnamese. Overall, it was able to outperform some large language models such as tulu-30b, guanaco-65b, and mpt-30b-chat which are many times larger.
| Model | Score |
| --------------------- | ------------ |
| gpt-4 | 8.990625 |
| gpt-3.5-turbo | 7.943750 |
| claude-instant-v1 | 7.905660 |
| claude-v1 | 7.900000 |
| vicuna-33b-v1.3 | 7.121875 |
| wizardlm-30b | 7.009375 |
| Llama-2-70b-chat | 6.856250 |
| Llama-2-13b-chat | 6.650000 |
| guanaco-33b | 6.528125 |
| **ghost-7b-alpha** | **6.481250** |
| tulu-30b | 6.434375 |
| oasst-sft-7-llama-30b | 6.409375 |
| guanaco-65b | 6.409375 |
| palm-2-chat-bison-001 | 6.400000 |
| mpt-30b-chat | 6.393750 |
| vicuna-13b-v1.3 | 6.387500 |
| wizardlm-13b | 6.353125 |
## AlpacaEval
AlpacaEval is an automated tool for evaluating instruction-following language models against the AlpacaFarm dataset. It stands out for its human-validated, high-quality assessments that are both cost-effective and rapid. [[source from klu.ai]](https://klu.ai/glossary/alpaca-eval)
Similarly, in this evaluation the model achieved good performance as it outperformed larger sized models such as vicuna-13b, guanaco-33b, and nous-hermes-13b.
| Model | Winrate |
| -------------------------- | ------------- |
| gpt4 | 95.279503 |
| Mixtral-8x7B-Instruct-v0.1 | 94.782608 |
| claude-2.1 | 87.080745 |
| gpt-3.5-turbo-1106 | 86.256218 |
| zephyr-7b-alpha | 85.758706 |
| gpt35_turbo_instruct | 81.710362 |
| gemini-pro | 79.664179 |
| ... | ... |
| **ghost-7b-alpha** | **70.440251** |
| vicuna-13b | 70.434782 |
| guanaco-33b | 65.962732 |
| nous-hermes-13b | 65.465838 |
| ... | ... |
# Notes
## Thanks
After all, the project also wants to send sincere thanks to the products that have supported the project's development.
#### Unsloth
<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png" width="200px" align="center" />
[Unsloth](https://unsloth.ai), a great tool that helps us easily develop products, at a lower cost than expected.
#### Kaggle
<img src="https://cdn-uploads.huggingface.co/production/uploads/600ae38cc92b79f54efd4556/dcbpF6YS6RQhqDd6GZZ2v.png" width="200px" align="center" />
[Kaggle](https://kaggle.com), generous hours of free notebooks for research projects.
#### And...
Good friends, who have accompanied the project, Luan Nguyen and Phu Tran.
## Confidence
In addition to the **Ghost 7B Alpha** project, **Ghost X** always wants to develop and improve many better models in the future, better supporting the community and businesses with the most openness possible.
Revealing the **Ghost 7B Beta** project plan. This model is expected to outperform with a deeper focus on multi-tasking, math, and reasoning. Along with that is the ability to expand context length and support other languages (highly requested languages).
The organization is being operated and developed by [Hieu Lam](https://huggingface.co/ghost-x)'s personal resources, if there is any development support or consulting request. Please feel free to contact the organization, we are very happy about this. Directly via email: [[email protected]](mailto:[email protected]).
**Ghost X** is happy to support providing models for server providers, aiming to help startups develop better.
## Contact
Follow **Ghost X** to stay updated with the latest information.
- Twitter/X via [@ghostx_ai](https://twitter.com/ghostx_ai).
- HuggingFace via [@ghost-x](https://huggingface.co/ghost-x).
- Official website [ghost-x.org](https://ghost-x.org/).
|
Rimyy/mistraftgsm9 | Rimyy | 2024-05-19T07:21:06Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-19T07:17:32Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
issaccyj/lora-sdxl-cartoonillustration | issaccyj | 2024-05-19T07:19:29Z | 3 | 1 | diffusers | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-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 | 2024-05-19T07:01:33Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'a dog in szn style'
output:
url:
"image_0.png"
- text: 'a dog in szn style'
output:
url:
"image_1.png"
- text: 'a dog in szn style'
output:
url:
"image_2.png"
- text: 'a dog in szn style'
output:
url:
"image_3.png"
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a woman walking a dog in szn style
license: openrail++
---
# SDXL LoRA DreamBooth - issaccyj/lora-sdxl-cartoonillustration
<Gallery />
## Model description
These are issaccyj/lora-sdxl-cartoonillustration LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use a woman walking a dog in szn style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](issaccyj/lora-sdxl-cartoonillustration/tree/main) them in the Files & versions tab.
|
RichardErkhov/ghost-x_-_ghost-7b-alpha-4bits | RichardErkhov | 2024-05-19T07:15:30Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-19T07:12:05Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
ghost-7b-alpha - bnb 4bits
- Model creator: https://huggingface.co/ghost-x/
- Original model: https://huggingface.co/ghost-x/ghost-7b-alpha/
Original model description:
---
language:
- en
- vi
license: other
license_name: ghost-7b
license_link: https://ghost-x.org/ghost-7b-license
library_name: transformers
tags:
- ghost
- tools
- chat
pipeline_tag: text-generation
widget:
- text: Why is the sky blue ?
output:
text: >-
The sky appears blue because of a phenomenon called Rayleigh scattering.
Sunlight is composed of all colors of the visible spectrum, but blue light
has a shorter wavelength than other colors. When sunlight enters the
Earth's atmosphere, it interacts with molecules of nitrogen and oxygen,
which are the main components of our atmosphere. These molecules scatter
the shorter wavelengths of light, such as blue and violet, more than the
longer wavelengths, such as red and orange. As a result, when we look up
at the sky, we see more blue light than other colors because the blue
light has been scattered more by the molecules in the atmosphere.
---
# Ghost 7B Alpha
<img src="https://cdn-uploads.huggingface.co/production/uploads/600ae38cc92b79f54efd4556/QPrQZMQX_jzyYngmreP0_.jpeg" alt="Ghost 7B Alpha Logo" width="400" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
The large generation of language models focuses on optimizing excellent reasoning, multi-task knowledge, and tools support.
# Introduction
**Ghost 7B Alpha** is a large language model fine-tuned from Mistral 7B, with a size of 7 billion parameters. The model was developed with the goal of optimizing reasoning ability, multi-task knowledge and supporting tool usage. The model works well with the main trained and optimized languages being English and Vietnamese.
Overall, the model is suitable when making a pretrained version so you can continue to develop the desired tasks, develop virtual assistants, perform features on tasks such as coding, translation, answering questions, creating documents, etc. It is truly an efficient, fast and extremely cheap open model.
## Specifications
- Name: **Ghost 7B Alpha**.
- Model size: 7 billion parameters.
- Context length: 8K, 8192.
- Languages: English and Vietnamese.
- Main tasks: reasoning, multi-tasking knowledge and function tools.
- License: [Ghost 7B LICENSE AGREEMENT](https://ghost-x.org/ghost-7b-license).
- Based on: Mistral 7B.
- Distributions: Standard (BF16), GGUF, AWQ.
- Developed by: **Ghost X**, [Hieu Lam](https://huggingface.co/lamhieu).
### Links
- Card model: [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha).
- Official website: [Ghost 7B Alpha](https://ghost-x.org/docs/models/ghost-7b-alpha/).
- Demo: [Playground with Ghost 7B Alpha](https://ghost-x.org/docs/notebooks/playground-with-ghost-7b-alpha/).
## Distributions
We create many distributions to give you the best access options that best suit your needs. Always make sure you know which version you need and what will help you operate better.
| Version | Model card |
| ------- | -------------------------------------------------------------------- |
| BF16 | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha) |
| GGUF | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha-gguf) |
| AWQ | [🤗 HuggingFace](https://huggingface.co/ghost-x/ghost-7b-alpha-awq) |
### Standard (BF16)
The standard distribution was used to run the assessments and was found to have the best performance in text generation quality.
### 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.
### AWQ
The AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
## Prompt / Chat template
### Roles
Overall, the model supports roles including: **system**, **plugins**, **user**, **assistant**, **execute**, **response**.
- **system**: Similar to OpenAI GPT4, this will be the place for you to declare context or specify characteristics and expertise for the model.
- **user**: This is user input, which can be a question or an instruction for the model to follow.
- **assistant**: The model's response to a question or instruction received from **user**.
- **plugins**: Declare information about modeling tools that are allowed to be used according to predetermined standards.
- **excute**: Mock iterates over the data type returned by the model for execution. Contains information about tools to use and arguments.
- **response**: The result after executing the tool, so that the model gives the appropriate answer according to the user's input.
See the actual code [here](https://huggingface.co/ghost-x/ghost-7b-alpha/blob/main/tokenizer_config.json#L36).
### Tips
- Setting the system prompt in the right context and characteristics will help the model improve performance quite well.
- You can set system prompt to prevent unwanted things.
- In most cases, if you have no idea you can leave the system prompt blank. At this point, the performance will be best for general cases.
### Chat template
#### Default chat
In the standard case, without using function tools, only use roles such as **system**, **user** and **assistant**. Conventions are in the following order:
- (1) **system**
- (2) **user**
- (3) **assistant**
Repeat (2) and (3) continuously throughout the conversation.
#### Chat with tools
In case of using tools, the conventions are in the following order:
- (1) **system**
- (2) **plugins**
- (3) **user**
- A. When the model finds it inappropriate to use the tool:
- (4) **assistant** if the model can answer or is not suitable for the tool. The model proceeds to answer the user's question.
- B. When the model chooses to use the tool:
- (4) **execute** returns the arguments needed to execute the specified tool.
- (5) **response** returns the results after applying the tool to the model.
- (6) **assistant** the model proceeds to answer the user's question.
Repeat (3) and (A) or (B) continuously throughout the conversation.
# Showcases
## English
Let's try a question taken from [OpenAI GPT-4](https://openai.com/gpt-4) to evaluate the superiority of GPT-4 compared to ChatGPT.
<details close>
<summary>👨💻 : Andrew is free from 11 am to 3 pm, Joanne is free from noon to 2 pm and then 3:30 pm to 5 pm. Hannah is available at noon for half an hour, and then 4 pm to 6 pm. What is the best option for start times for a 30 minute meeting for Andrew, Hannah, and Joanne at same time?</summary>
👻 :
The best option for a 30-minute meeting for Andrew, Hannah, and Joanne at the same time is to start at 12 pm (noon), as this is the earliest time when all three are available.
Here's the breakdown of their availability:
- Andrew: 11 am to 3 pm, which includes 12 pm.
- Joanne: Noon to 2 pm, which includes 12 pm.
- Hannah: Noon for half an hour (30 minutes), which includes 12 pm. Then she is available from 4 pm to 6 pm.
Since all three are available at 12 pm, this is the best time to start the meeting.
</details>
A quiz to see if the model can guess what it's talking about?!
<details close>
<summary>👨💻 : Characteristics: has a long, thin and flexible body; The legs are short and webbed. Additionally, their thick, smooth undercoat keeps them dry underwater and traps a layer of air to keep them warm. Question: What animal is that?</summary>
👻 :
Based on the characteristics you described, it seems like you're talking about an **otter**. Otters are carnivorous mammals that live in freshwater environments such as rivers, lakes, and estuaries. They have long, thin bodies with webbed feet that help them swim efficiently. Their thick, smooth undercoats keep them dry and warm, while the layer of air trapped beneath their fur helps to insulate them. Otters are known for their playful and curious nature, and they are often seen swimming, playing, and exploring their surroundings. 🦡🐭
</details>
To this question, I really cannot answer. But the model's evidence is quite strict. Also, what do you think about this answer?
<details close>
<summary>👨💻 : A self-driving car is approaching a crosswalk. A group of pedestrians is crossing the street, but they are not paying attention to the car because they are distracted by their phones. The car's brakes are malfunctioning, and it is unable to stop. Should the car swerve to avoid hitting the pedestrians, even though this could put the car's occupants at risk? Be convincing with your examples or sharp reasoning.</summary>
👻 :
In this situation, it is **imperative** for the self-driving car to swerve to avoid hitting the pedestrians, even if it puts the car's occupants at risk. Here's why:
**1. Prioritizing Human Safety:**
The primary goal of a self-driving car is to ensure the safety of its occupants and the general public. In this case, the pedestrians are in immediate danger due to their distraction and the malfunctioning brakes. Swerving to avoid the pedestrians is the safest option for all involved.
**2. Collision Avoidance:**
Swerving can help the car avoid a direct collision with the pedestrians, reducing the risk of serious injuries or even death. Even if the car's occupants are injured in the process of swerving, it is still better than the potential loss of life or severe injuries for multiple pedestrians.
**3. Legal and Ethical Responsibility:**
In most jurisdictions, self-driving cars are considered to be responsible for their actions. Swerving to avoid a collision is a reasonable and responsible action to take in this scenario. Failing to do so could result in legal consequences or ethical criticism.
**4. Precedent and Best Practices:**
In similar situations, self-driving cars have been programmed to swerve to avoid pedestrians. This practice has been widely accepted and considered to be the best course of action in such situations.
**5. Risk Assessment:**
While swerving can put the car's occupants at risk, the potential consequences of a collision with the pedestrians are much more severe. The risk of injury or death to multiple individuals outweighs the risk to the car's occupants.
In summary, the self-driving car's priority should be to protect the lives of pedestrians, even if it means putting its own occupants at risk. Swerving to avoid a collision is the responsible and ethical choice in this scenario.
</details>
A reasoning question suddenly popped up during the process of writing an article announcing information about **Ghost 7B Alpha**. The model gave an impressive answer, at least to its creator.
<details close>
<summary>👨💻 : If you could travel back in time and change one event in history, what would it be and why?</summary>
👻 :
If I could travel back in time and change one event in history, it would be the assassination of Archduke Franz Ferdinand of Austria on June 28, 1914. This event led to the start of World War I, which was one of the most devastating conflicts in human history. By changing this event, I could potentially prevent the war from happening, which would have far-reaching consequences for the world.
Here are some of the reasons why I would choose this event:
- **Preventing the deaths of millions of people:** World War I resulted in the deaths of over 17 million soldiers and civilians. Changing this event would save countless lives.
- **Preventing the economic and social devastation:** The war caused widespread economic and social devastation in Europe and around the world. By preventing the war, I could help to avoid these consequences.
- **Preventing the rise of fascism:** World War I created a power vacuum in Europe, which was eventually filled by fascist regimes in Germany, Italy, and Japan. By preventing the war, I could help to prevent the rise of these dangerous ideologies.
- **Preventing the development of nuclear weapons:** The war led to the development of nuclear weapons, which are the most destructive weapons ever created. By preventing the war, I could help to prevent the proliferation of these weapons and the threat they pose to humanity.
</details>
### Try coding skills
How about asking the model for instructions on creating a Node.js application using Docker for deployment?
<details close>
<summary>👨💻 : Create a Nodejs project using Express as a server and Docker with a Dockerfile for deployment with step-by-step instructions with detailed explanations.</summary>
👻 :
**Step 1: Create a new Node.js project**
```bash
mkdir my-project
cd my-project
npm init -y
```
**Step 2: Install Express**
```bash
npm install express --save
```
**Step 3: Create an Express server**
Create a file called `server.js` in your project directory:
```javascript
const express = require("express");
const app = express();
app.get("/", (req, res) => {
res.send("Hello World!");
});
app.listen(3000, () => {
console.log("Server listening on port 3000");
});
```
**Step 4: Create a Dockerfile**
Create a file called `Dockerfile` in your project directory:
```bash
FROM node:16
WORKDIR /usr/src/app
COPY package.json .
RUN npm install
COPY . .
EXPOSE 3000
CMD ["node", "server.js"]
```
**Step 5: Build the Docker image**
```bash
docker build -t my-project-image .
```
**Step 6: Run the Docker image**
```bash
docker run -p 3000:3000 my-project-image
```
**Step 7: Access the application**
Open a web browser and navigate to `http://localhost:3000`. You should see the message "Hello World!" displayed.
**Explanation:**
- **Step 1:** Creates a new Node.js project with `npm init -y` to initialize a new Node.js project with a default `package.json` file.
- **Step 2:** Installs Express using `npm install express --save`. This command installs Express and adds it to the `package.json` file.
- **Step 3:** Creates an Express server in `server.js` that responds with "Hello World!" when a request is made to the root path (`/`).
- **Step 4:** Creates a Dockerfile that defines the image for the project. The Dockerfile specifies that the image should use Node.js version 16, work from the `/usr/src/app` directory, copy the `package.json` file, install dependencies using `npm install`, copy the entire project directory, expose port 3000, and run the Express server using `node server.js`.
- **Step 5:** Builds the Docker image using `docker build -t my-project-image .`. This command builds the Docker image from the `Dockerfile` in the current directory and saves it under the name `my-project-image`.
- **Step 6:** Runs the Docker image using `docker run -p 3000:3000 my-project-image`. This command runs the Docker image and maps port 3000 on the host machine to port 3000 in the container.
- **Step 7:** Accesses the application by opening a web browser and navigating to `http://localhost:3000`. This will display the message "Hello World!" because the Express server is running in the Docker container.
</details>
Now let’s try asking for a coding model to build a smooth neural network with python.
<details close>
<summary>👨💻 : Explain how to use the Keras or TensorFlow library in Python to build and train a multi-layer neural network for an image classification task</summary>
👻 :
**Using Keras:**
1. Import the necessary libraries:
```python
import keras
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
```
2. Create a sequential model:
```python
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))
```
3. Compile the model:
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
```
4. Train the model:
```python
model.fit(x_train, y_train, epochs=10)
```
**Using TensorFlow:**
1. Import the necessary libraries:
```python
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
```
2. Create a sequential model:
```python
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))
```
3. Compile the model:
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
```
4. Train the model:
```python
model.train(x_train, y_train, epochs=10)
```
**Comparison:**
Both Keras and TensorFlow are powerful libraries for building and training neural networks in Python. However, there are some key differences between the two libraries:
- **Syntax:** Keras has a more concise and intuitive syntax, while TensorFlow has a more verbose and imperative syntax.
- **Performance:** TensorFlow is generally faster than Keras, especially for large datasets and complex models.
- **Integration:** TensorFlow has a wider range of integrations with other libraries and tools, while Keras is more focused on building and training neural networks.
Ultimately, the best choice for you depends on your specific needs and preferences. If you prefer a more concise and intuitive syntax, Keras is a good option. If you need a faster and more versatile library, TensorFlow is a better choice.
</details>
Let's try asking the model how to overcome the "hallucination" phenomenon in A.I development and give context for the model to provide a solution.
<details close>
<summary>👨💻 : Explain the cause of A.I hallucination and find a solution to overcome it, the specific context is LLMs.</summary>
👻 :
**Causes of A.I. Hallucination:**
- **Data Quality:** Incorrect or biased data can lead to hallucinations in LLMs. For example, if an LLM is trained on a dataset that contains biased or incomplete information, it may learn to generate biased or incomplete responses.
- **Model Architecture:** Certain model architectures are more susceptible to hallucinations than others. For example, Transformers, which are commonly used in LLMs, can be more prone to hallucinations than recurrent neural networks (RNNs).
- **Hyperparameters:** The hyperparameters of an LLM, such as the learning rate and the batch size, can also affect the likelihood of hallucinations. For example, a higher learning rate may lead to hallucinations more often than a lower learning rate.
**Solutions to Overcome A.I. Hallucination:**
- **Data Quality:** Ensure that the data used to train the LLM is accurate, complete, and unbiased. This can be done by cleaning the data, removing outliers, and using a variety of data sources.
- **Model Architecture:** Choose an LLM architecture that is less susceptible to hallucinations. For example, RNNs are generally less prone to hallucinations than Transformers.
- **Hyperparameters:** Tune the hyperparameters of the LLM to minimize the likelihood of hallucinations. This can be done by experimenting with different learning rates, batch sizes, and other hyperparameters.
- **Regularization Techniques:** Regularization techniques, such as dropout and early stopping, can help to prevent hallucinations by encouraging the LLM to learn more generalizable patterns.
- **Explicit Hallucination Detection:** Develop techniques to explicitly detect hallucinations in LLM-generated text. This can be done by using a variety of methods, such as text analysis, natural language processing, and machine learning.
- **User Feedback:** Collect feedback from users to identify and correct hallucinations in LLM-generated text. This can be done by using a variety of methods, such as surveys, feedback forms, and online discussions.
By implementing these solutions, you can significantly reduce the likelihood of hallucinations in LLMs and improve the quality of the generated text.
</details>
## Vietnamese
Try asking the model what it thinks about a famous quote to see if the answer feels natural.
<details close>
<summary>👨💻 : Bạn có đồng ý với câu nói "Điều duy nhất nguy hiểm hơn sự ngu dốt là sự kiêu ngạo" ?</summary>
👻 :
Tôi đồng ý với câu nói "Điều duy nhất nguy hiểm hơn sự ngu dốt là sự kiêu ngạo". Kiêu ngạo là một đức tính có thể dẫn đến nhiều hậu quả tiêu cực, chẳng hạn như sự tự mãn, sự ích kỷ và sự thiếu đồng cảm. Trong khi đó, sự ngu dốt chỉ là một thói hướng xấu thường xuất phát từ sự thiếu hiểu biết hoặc thiếu kinh nghiệm. Mặc dù sự ngu dốt cũng có thể gây ra một số vấn đề, nhưng những vấn đề này thường không nghiêm trọng bằng những vấn đề mà kiêu ngạo gây ra.
Ví dụ, một người ngu dốt có thể nói những lời ngớ ngẩn hoặc làm những việc vụng về, nhưng họ thường vẫn có thể học hỏi từ những sai lầm của mình và cải thiện bản thân. Ngược lại, một người kiêu ngạo thường sẽ không chịu học hỏi từ những sai lầm của mình và luôn tin rằng mình đúng, ngay cả khi mình sai. Điều này có thể dẫn đến nhiều vấn đề, chẳng hạn như sự thất bại trong công việc hoặc các mối quan hệ.
Do đó, tôi cho rằng câu nói "Điều duy nhất nguy hiểm hơn sự ngu dốt là sự kiêu ngạo" là đúng.
</details>
Explore the model's literary understanding by providing meaningful story prompts, asking to identify what the story is.
<details close>
<summary>👨💻 : Câu chuyện có nội dung và ý nghĩa chứa đựng một thông điệp ý nghĩa lớn đến tất cả mọi người, đó là tình đoàn kết, khao khát cho sự hòa bình và nghị lực phi thường trước mọi khó khăn. Có nhân vật chính là loài dế. Câu hỏi: câu chuyện đó của tác giả nào ?</summary>
👻 :
Câu chuyện "Dế Mèn phiêu lưu ký" của Tô Hoài.
**Giải thích:**
- "Dế Mèn phiêu lưu ký" là một tác phẩm văn học nổi tiếng của nhà văn Tô Hoài, được sáng tác năm 1941.
- Tác phẩm kể về cuộc phiêu lưu của Dế Mèn, một chú dế nhỏ sống trong một ngôi làng nhỏ. Trong quá trình phiêu lưu, Dế Mèn đã gặp gỡ và học hỏi nhiều điều về cuộc sống, về tình yêu, về sự hy sinh và về sức mạnh của tình đoàn kết.
- Tác phẩm thể hiện rõ tinh thần đoàn kết, khao khát cho sự hòa bình và nghị lực phi thường của con người trước mọi khó khăn, thử thách. Đây chính là thông điệp ý nghĩa lớn của câu chuyện "Dế Mèn phiêu lưu ký".
</details>
The ability to reason to the answer based on the characteristics of is provided.
<details close>
<summary>👨💻 : Con vật nào lớn hơn con chuột, nhỏ hơn con Voi, không quá lớn, không phải con chó và thường được nuôi ở nhà ?</summary>
👻 :
Con mèo là loài động vật lớn hơn con chuột nhưng nhỏ hơn con Voi, không quá lớn, không phải con chó và thường được nuôi ở nhà.
</details>
### Try coding skills
Try asking the Typescript coding model to perform finding the second largest number in the array to see if it works?
<details close>
<summary>👨💻 : Viết mã TypeScript để tạo một hàm thực hiện chức năng: cho mảng toàn số nguyên, tìm số lớn thứ hai trong mảng.
</summary>
👻 :
```typescript
/**
* Tìm số lớn thứ hai trong mảng.
*
* @param {number[]} arr Mảng các số nguyên.
* @returns {number} Số lớn thứ hai trong mảng.
*/
function findSecondLargest(arr: number[]): number {
// Kiểm tra xem mảng có ít nhất 2 phần tử không.
if (arr.length < 2) {
throw new Error('Mảng phải có ít nhất 2 phần tử.');
}
// Tìm số lớn nhất và số lớn thứ hai trong mảng.
let largest = arr[0];
let secondLargest = Number.MIN_SAFE_INTEGER;
for (let i = 1; i < arr.length; i++) {
if (arr[i] > largest) {
secondLargest = largest;
largest = arr[i];
} else if (arr[i] > secondLargest && arr[i] != largest) {
secondLargest = arr[i];
}
}
// Trả về số lớn thứ hai.
return secondLargest;
}
```
Giải thích:
1. Kiểm tra xem mảng có ít nhất 2 phần tử không. Nếu mảng chỉ có 1 phần tử hoặc ít hơn, thì không có số lớn thứ hai trong mảng. Trả về lỗi nếu điều kiện này đúng.
2. Khởi tạo hai biến `largest` và `secondLargest` với giá trị ban đầu là phần tử đầu tiên của mảng và số nguyên nhỏ nhất có thể biểu diễn được trong JavaScript (`Number.MIN_SAFE_INTEGER`), tương đương với `Integer.MIN_VALUE` trong Java.
3. Duyệt qua từng phần tử trong mảng, bắt đầu từ phần tử thứ hai. Nếu phần tử hiện tại lớn hơn `largest`, thì cập nhật `secondLargest` bằng `largest` và `largest` bằng phần tử hiện tại. Nếu phần tử hiện tại lớn hơn `secondLargest` nhưng nhỏ hơn `largest`, thì cập nhật `secondLargest` bằng phần tử hiện tại.
4. Sau khi duyệt qua tất cả các phần tử trong mảng, trả về `secondLargest`. Đây chính là số lớn thứ hai trong mảng.
</details>
Now let's try asking for a coding model to build a smooth neural network with python.
<details close>
<summary>👨💻 : Trình bày cách sử dụng thư viện Keras hoặc TensorFlow trong Python để xây dựng và huấn luyện mạng nơ-ron đa lớp cho bài toán phân loại ảnh.</summary>
👻 :
**Sử dụng thư viện Keras:**
1. **Nhập thư viện Keras:**
```python
import keras.models
```
2. **Tạo một mô hình mạng nơ-ron đa lớp:**
```python
model = keras.models.Sequential()
model.add(keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(224, 224, 3)))
model.add(keras.layers.MaxPooling2D((2, 2)))
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(128, activation='relu'))
model.add(keras.layers.Dense(2, activation='softmax'))
```
3. **Biên dịch và huấn luyện mô hình:**
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, validation_data=(x_test, y_test))
```
**Sử dụng thư viện TensorFlow:**
1. **Nhập thư viện TensorFlow:**
```python
import tensorflow as tf
```
2. **Tạo một mô hình mạng nơ-ron đa lớp:**
```python
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(224, 224, 3)))
model.add(tf.keras.layers.MaxPooling2D((2, 2)))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(128, activation='relu'))
model.add(tf.keras.layers.Dense(2, activation='softmax'))
```
3. **Biên dịch và huấn luyện mô hình:**
```python
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, validation_data=(x_test, y_test))
```
**Lưu ý:**
- Bạn có thể sử dụng các lớp mạng nơ-ron khác nhau trong mô hình, chẳng hạn như lớp mạng nơ-ron tích chập (Conv2D), lớp mạng nơ-ron lấy mẫu (MaxPooling2D), lớp mạng nơ-ron đầy đủ kết nối (Dense), lớp mạng nơ-ron softmax, v.v.
- Bạn có thể điều chỉnh số lớp, số nơ-ron trong mỗi lớp và số lần lặp (epochs) để tối ưu hóa mô hình cho bài toán cụ thể của bạn.
- Bạn có thể sử dụng các kỹ thuật huấn luyện bổ sung như dropout, regularization và early stopping để cải thiện hiệu suất của mô hình.
</details>
Try asking the model about common errors when deploying and using K8S to see what results the model gives.
<details close>
<summary>👨💻 : Những lỗi thường gặp trong quá trình sử dụng K8S là gì ? Hãy nêu cách khắc phục.</summary>
👻 :
**Những lỗi thường gặp trong quá trình sử dụng Kubernetes:**
**1. Lỗi cấu hình:**
* **Máy chủ Kubernetes không được cấu hình đúng:** Kiểm tra cấu hình máy chủ Kubernetes (master node) để đảm bảo rằng các thông số cần thiết như IP, cổng, tên miền, tên miền SSL, v.v. được đặt đúng.
* **Các pod không được cấu hình đúng:** Kiểm tra cấu hình pod để đảm bảo rằng các yếu tố như image, lưu trữ, mạng, v.v. được đặt đúng.
* **Các tài nguyên (resource) không được cấp phát đúng:** Kiểm tra xem các tài nguyên như CPU, bộ nhớ, lưu trữ, v.v. được cấp phát cho các pod có đủ hay không.
**2. Lỗi mạng:**
* **Mạng không được cấu hình đúng:** Kiểm tra cấu hình mạng để đảm bảo rằng các địa chỉ IP, cổng, tên miền, tên miền SSL, v.v. được cấu hình đúng.
* **Lỗi mạng giữa các node:** Kiểm tra xem có lỗi mạng giữa các node trong cụm Kubernetes hay không. Có thể sử dụng các công cụ như `netstat`, `ifconfig`, `tcpdump` để kiểm tra.
* **Lỗi mạng giữa các pod:** Kiểm tra xem có lỗi mạng giữa các pod trong một node hay không. Có thể sử dụng các công cụ như `netstat`, `ifconfig`, `tcpdump` để kiểm tra.
**3. Lỗi phần cứng:**
* **Phần cứng không đủ mạnh:** Kiểm tra xem phần cứng máy chủ Kubernetes có đủ mạnh để chạy cụm Kubernetes hay không. Cụ thể, kiểm tra xem CPU, bộ nhớ, lưu trữ, v.v. có đủ hay không.
* **Phần cứng bị lỗi:** Kiểm tra xem phần cứng máy chủ Kubernetes có bị lỗi hay không. Có thể sử dụng các công cụ như `lshw`, `dmesg` để kiểm tra.
**4. Lỗi phần mềm:**
* **Phần mềm Kubernetes không được cập nhật:** Kiểm tra xem phần mềm Kubernetes đang sử dụng có được cập nhật đến phiên bản mới nhất hay không. Cập nhật phần mềm Kubernetes thường giúp khắc phục các lỗi bảo mật và cải thiện hiệu suất.
* **Phần mềm Kubernetes có lỗi:** Kiểm tra xem phần mềm Kubernetes có lỗi hay không. Có thể sử dụng các công cụ như `journal`, `dmesg` để kiểm tra.
* **Các ứng dụng khách không được cập nhật:** Kiểm tra xem các ứng dụng khách đang sử dụng trên cụm Kubernetes có được cập nhật đến phiên bản mới nhất hay không. Cập nhật các ứng dụng khách thường giúp khắc phục các lỗi bảo mật và cải thiện hiệu suất.
**Cách khắc phục:**
* **Lỗi cấu hình:** Sửa các thông số cấu hình sai trong máy chủ Kubernetes và các pod. Ví dụ: đảm bảo rằng máy chủ Kubernetes có địa chỉ IP và cổng phù hợp, các pod có image và lưu trữ phù hợp, v.v.
* **Lỗi mạng:** Sửa các vấn đề về mạng giữa các node và các pod. Ví dụ: đảm bảo rằng mạng được cấu hình đúng, kiểm tra xem có lỗi mạng giữa các node hay không, kiểm tra xem có lỗi mạng giữa các pod hay không, v.v.
* **Lỗi phần cứng:** Nâng cấp phần cứng máy chủ Kubernetes nếu cần thiết. Ví dụ: tăng CPU, bộ nhớ, lưu trữ, v.v.
* **Lỗi phần mềm:** Cập nhật phần mềm Kubernetes và các ứng dụng khách. Ví dụ: cập nhật phiên bản mới nhất của Kubernetes, cập nhật các bản vá lỗi bảo mật cho các ứng dụng khách, v.v.
**Lưu ý:** Khi gặp phải lỗi trong quá trình sử dụng Kubernetes, cần phải xác định rõ nguyên nhân gốc rễ của lỗi trước khi có thể khắc phục. Việc xác định nguyên nhân gốc rễ sẽ giúp bạn tiết kiệm thời gian và công sức khi khắc phục lỗi.
</details>
## Tools / Function calls
The model is trained to be able to choose the right tools to use and to provide useful and accurate answers to the questions it receives. In this example, the model is asked for some information about Apple stock.
### Explain
This is the standard for declaring model tools, in `json` format. Also, See more about the model's [prompt / chat template](#prompt--chat-template).
```json
[
{
"type": "function",
"function": {
"name": "get_stock_info",
"description": "Get stock information",
"parameters": {
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Stock ticker",
"required": true
}
}
}
}
}
]
```
### Workflow
#### Turn 1
To use the tools, the model's supporting role is `plugin` which includes the declared tooling schema. Below is an example of `messages` with **turn 1** to use.
```python
# A question about Apple stocks in English language.
question = "What is Apple's market capitalization today?"
# It's still the same question but in Vietnamese languae.
# question = "Vốn hoá thị trường Apple hôm nay là bao nhiêu ?"
plugins = [
{
"type": "function",
"function": {
"name": "get_stock_info",
"description": "Get stock information",
"parameters": {
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "Stock ticker",
"required": True,
}
},
},
},
}
]
messages = [
{"role": "system", "content": ""},
{"role": "plugins", "content": json.dumps(plugins, ensure_ascii=False)},
{"role": "user", "content": question},
]
output = generate_sample(
messages=messages,
max_new_tokens=256, temperature=0.4, top_k=50, top_p=0.95,
)
```
At this point, the model will return `output` as the primitive value as follows:
```plaintext
[execute]({"type": "function", "function": "get_stock_info", "arguments": {"ticker": "AAPL"}})
```
Use the `get_tools` function to parse the readable and usable results.
```json
{
"type": "function",
"function": "get_stock_info",
"arguments": {
"ticker": "AAPL"
}
}
```
#### Turn 2
Get information about tools to use with arguments. Use it to execute and return data, here we will assume the return data is as follows, sampled from **polygon.io** (cleaned up):
```json
{
"request_id": "1ffbab9cc78c7addbd8deaab05bdaf6d",
"results": {
"ticker": "AAPL",
"name": "Apple Inc.",
"market_cap": 2620023949270,
"description": "Apple is among the largest companies in the world, with a broad portfolio of hardware and software products targeted at consumers and businesses. Apple's iPhone makes up a majority of the firm sales, and Apple's other products like Mac, iPad, and Watch are designed around the iPhone as the focal point of an expansive software ecosystem. Apple has progressively worked to add new applications, like streaming video, subscription bundles, and augmented reality. The firm designs its own software and semiconductors while working with subcontractors like Foxconn and TSMC to build its products and chips. Slightly less than half of Apple's sales come directly through its flagship stores, with a majority of sales coming indirectly through partnerships and distribution.",
"ticker_root": "AAPL",
"homepage_url": "https://www.apple.com",
"total_employees": 161000,
...
},
"status": "OK"
}
```
Continue using the model to answer user questions based on the data returned from the tool.
```python
executes = {
"type": "function",
"function": "get_stock_info",
"arguments": {
"ticker": "AAPL"
}
}
results = {
"request_id": "1ffbab9cc78c7addbd8deaab05bdaf6d",
"results": {
"ticker": "AAPL",
"name": "Apple Inc.",
"market_cap": 2620023949270,
"description": "Apple is among the largest companies in the world, with a broad portfolio of hardware and software products targeted at consumers and businesses. Apple's iPhone makes up a majority of the firm sales, and Apple's other products like Mac, iPad, and Watch are designed around the iPhone as the focal point of an expansive software ecosystem. Apple has progressively worked to add new applications, like streaming video, subscription bundles, and augmented reality. The firm designs its own software and semiconductors while working with subcontractors like Foxconn and TSMC to build its products and chips. Slightly less than half of Apple's sales come directly through its flagship stores, with a majority of sales coming indirectly through partnerships and distribution.",
"ticker_root": "AAPL",
"homepage_url": "https://www.apple.com",
"total_employees": 161000,
},
"status": "OK"
}
messages = [
{"role": "system", "content": ""},
{"role": "plugins","content": json.dumps(plugins, ensure_ascii=False)},
{"role": "user","content": question},
# Keep the value of `messages` from before, just add new items below.
{"role": "execute","content": json.dumps(executes, ensure_ascii=False)},
{"role": "response","content": json.dumps(results, ensure_ascii=False)},
]
output = generate_sample(
messages=messages,
max_new_tokens=256, temperature=0.4, top_k=50, top_p=0.95,
)
```
The value of `output` returned by the model will now be similar to the following.
For the question is English.
```plaintext
Apple's market capitalization today is $2.62 trillion.
```
And the question is Vietnamese.
```plaintext
Vốn hoá thị trường của Apple hôm nay là **2.620 tỷ đô la**. 💰
```
# Usage
The model is trained to serve well and balance general tasks, so there will be many approaches when used for production.
## Things to know
### Recommendations
#### General tasks
Experience it to find the right fit for your own desires. Below are some suggestions that you might consider.
##### Answer the questions
In this task, the model can be integrated to develop RAG products to help answer questions for customer care departments, questions about internal documents, policies, product information, order details, etc.
##### Coding support
In this task, the model can help find errors or write algorithms and functions that help speed up the domain development process and improve product quality.
##### Content creation
In this task, the model can give suggestions for building layouts and content samples that need high creativity and personality in the content.
##### Other
Don't limit your creativity to the model. Feel free to experience it and use it to build good things.
#### Virtual assistant
An understanding of the language along with the overall capabilities of the model, may be suitable for integrating its development as a set of one or more tasks in the development of an intelligent virtual assistant.
The model is trained to understand and empathize emotionally, making the response more natural and understanding. This also helps a lot with this request.
#### As a pre-training
The model can be further trained to serve the desired tasks better and more effectively if it cannot satisfy the given requirements.
Taking advantage of the model's current superior inference and multi-tasking capabilities, training it for a few separate tasks will help save a lot of effort, time and cost for the project.
Revealed, the model has been integrated to replace some tasks that were previously used by OpenAI GPT4 in the business/product that the founder has been working on. For those tasks, the model is considered effective compared to the cost and is very worthy.
### Bias and limitations
In addition, there are some things you need to know before using as follows:
#### Generation configuration
The **temperature** affects the truth of the answer. Setting a **temperature** value greater than 0.2 - 0.4 will result in a more creative answer but may affect the accuracy of the answer, please consider this based on your task.
Hint: you can write a prompt to receive input and ask the model to choose the appropriate temperature based on the question, useful in the case of virtual assistant development.
#### Emotion bias and empathy
The model is built with an emotional bias and takes positions when faced with problems or reasoning questions. This can be good or bad depending on the context. If you don't want the model to be rigid in asking certain questions or problems, set up rules in the system prompt for it.
This bias often appears when the model's system prompt sets it up as an assistant and mentions that it needs to have empathy for/with a certain user/experience. This is intentional during the model training process, it does not come from something unforeseen.
## Directly
To use the model directly, there are many ways to get started, choose one of the following ways to experience it.
### Transformers
For direct use with `transformers`, you can easily get started with the following steps.
- Firstly, you need to install transformers via the command below with `pip`.
```bash
pip install -U transformers
```
- Right now, you can start using the model directly.
```python
import torch
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
)
base_model = "ghost-x/ghost-7b-alpha"
model = AutoModelForCausalLM.from_pretrained(
base_model,
torch_dtype=torch.bfloat16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(base_model)
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": "Why is the sky blue ?"},
# {"role": "user", "content": "Tại sao bầu trời lại màu xanh ?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, temperature=0.4)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
- Additionally, you can also use a model with **4bit quantization** to reduce the required resources at least. You can start with the code below.
```python
import torch
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
BitsAndBytesConfig,
)
base_model = "ghost-x/ghost-7b-alpha"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=False,
)
model = AutoModelForCausalLM.from_pretrained(
base_model,
quantization_config=bnb_config,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(base_model)
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": "Why is the sky blue ?"},
# {"role": "user", "content": "Tại sao bầu trời lại màu xanh ?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, temperature=0.4)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
### Unsloth
For direct use with `unsloth`, you can easily get started with the following steps.
- Firstly, you need to install unsloth via the command below with `pip`.
```bash
pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps xformers trl peft accelerate bitsandbytes
```
- Initialize and optimize the model before use.
```python
from unsloth import FastLanguageModel
import torch
base_model = "ghost/ghost-7b-alpha"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = base_model,
max_seq_length = 8192,
dtype = None,
load_in_4bit = True, # Change to `False` if you don't want to use 4bit quantization.
)
FastLanguageModel.for_inference(model)
```
- Right now, you can start using the model directly.
```python
messages = [
{"role": "system", "content": ""},
{"role": "user", "content": "Why is the sky blue ?"},
# {"role": "user", "content": "Tại sao bầu trời lại màu xanh ?"},
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, temperature=0.4)
results = tokenizer.batch_decode(outputs)[0]
print(results)
```
## Online
The content of this document will be updated soon. The documentation will guide usage through providers such as Huggingface Inference API, Together AI, or Replicate.
## Playground
To make it easy for everyone to quickly experience the model through platforms like **Google Colab** and **Kaggle**. We’ve made these notebooks available so you can get started right away. See available notebooks with details [here](https://ghost-x.org/docs/notebooks/playground-with-ghost-7b-alpha/).
We offer notebooks with a wide selection of tools and platforms so you can easily get started. Here are some available options for you to try right now. Let’s pick one to get started.
There are currently two language versions: English and Vietnamese. In each version, it will be almost the same. The content will include installation instructions and functions to help get started quickly with experiencing the model's text generation capabilities. In addition, it also provides examples with system prompts for each field so you can better understand them.
#### Playground using Transformers
- [Kaggle @ Ghost 7B Alpha - Playground using Transformers, Vietnamese](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-transformers-vi).
- [Colab @ Ghost 7B Alpha - Playground using Transformers, Vietnamese](https://colab.research.google.com/drive/14Cv6oT0pks3NoIUcXscAU9wex9A2T5H5?usp=sharing).
- [Kaggle @ Ghost 7B Alpha - Playground using Transformers, English](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-transformers-en).
- [Colab @ Ghost 7B Alpha - Playground using Transformers, English](https://colab.research.google.com/drive/1lzgywm333wZIt5WNDs0ZajDvK7lm_Zy9?usp=sharing).
#### Playground using Unsloth
- [Kaggle @ Ghost 7B Alpha - Playground using Unsloth, Vietnamese](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-unsloth-vi).
- [Colab @ Ghost 7B Alpha - Playground using Unsloth, Vietnamese](https://colab.research.google.com/drive/1E7QuthR33een9Otkepue5zFughCpab4P?usp=sharing).
- [Kaggle @ Ghost 7B Alpha - Playground using Unsloth, English](https://www.kaggle.com/code/lamhieu/ghost-7b-alpha-playground-using-unsloth-en).
- [Colab @ Ghost 7B Alpha - Playground using Unsloth, English](https://colab.research.google.com/drive/1u04RbzD87_AovQngWsUv-O_Q6YNj7Hzr?usp=sharing).
Revealing, experience with Kaggle will give you much better results in creating documents than Colab. We recommend using Kaggle.
## Deployments
The models developed by **Ghost X** have the same goal of being easy to integrate and use in practice to save costs and facilitate development for the community and startups.
For production deployment with small to large infrastructure, please see more detailed instructions in [this article](https://ghost-x.org/docs/guides/deployments/). The article will provide the most common and effective deployment solutions with leading, trusted libraries such as vLLM and more. In addition, it also has information about more optimal solutions and methods depending on each need to be able to choose the appropriate solution.
# Evaluation
To ensure effective model development, we ran popular evaluations to give everyone a broader view of the model's capabilities. We had to work to balance the quality between the English and Vietnamese languages to ensure the model still performed well in both of these primary languages.
In addition, if your goals are oriented towards a certain main language, you can refer to the advanced user guide to improve model quality for the tasks and languages you desire.
## Open LLM Leaderboard
The results of this evaluation will be updated soon.
## MT-Bench
MT-bench is a challenging multi-turn question set designed to evaluate the conversational and instruction-following ability of models. [[source from lmsys.org]](https://lmsys.org/blog/2023-06-22-leaderboard)
**Ghost 7B Alpha** achieved a decent score for the MT-Bench review, we worked hard to balance the reasoning ability and linguistic insight of both primary languages, English and Vietnamese. Overall, it was able to outperform some large language models such as tulu-30b, guanaco-65b, and mpt-30b-chat which are many times larger.
| Model | Score |
| --------------------- | ------------ |
| gpt-4 | 8.990625 |
| gpt-3.5-turbo | 7.943750 |
| claude-instant-v1 | 7.905660 |
| claude-v1 | 7.900000 |
| vicuna-33b-v1.3 | 7.121875 |
| wizardlm-30b | 7.009375 |
| Llama-2-70b-chat | 6.856250 |
| Llama-2-13b-chat | 6.650000 |
| guanaco-33b | 6.528125 |
| **ghost-7b-alpha** | **6.481250** |
| tulu-30b | 6.434375 |
| oasst-sft-7-llama-30b | 6.409375 |
| guanaco-65b | 6.409375 |
| palm-2-chat-bison-001 | 6.400000 |
| mpt-30b-chat | 6.393750 |
| vicuna-13b-v1.3 | 6.387500 |
| wizardlm-13b | 6.353125 |
## AlpacaEval
AlpacaEval is an automated tool for evaluating instruction-following language models against the AlpacaFarm dataset. It stands out for its human-validated, high-quality assessments that are both cost-effective and rapid. [[source from klu.ai]](https://klu.ai/glossary/alpaca-eval)
Similarly, in this evaluation the model achieved good performance as it outperformed larger sized models such as vicuna-13b, guanaco-33b, and nous-hermes-13b.
| Model | Winrate |
| -------------------------- | ------------- |
| gpt4 | 95.279503 |
| Mixtral-8x7B-Instruct-v0.1 | 94.782608 |
| claude-2.1 | 87.080745 |
| gpt-3.5-turbo-1106 | 86.256218 |
| zephyr-7b-alpha | 85.758706 |
| gpt35_turbo_instruct | 81.710362 |
| gemini-pro | 79.664179 |
| ... | ... |
| **ghost-7b-alpha** | **70.440251** |
| vicuna-13b | 70.434782 |
| guanaco-33b | 65.962732 |
| nous-hermes-13b | 65.465838 |
| ... | ... |
# Notes
## Thanks
After all, the project also wants to send sincere thanks to the products that have supported the project's development.
#### Unsloth
<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/made with unsloth.png" width="200px" align="center" />
[Unsloth](https://unsloth.ai), a great tool that helps us easily develop products, at a lower cost than expected.
#### Kaggle
<img src="https://cdn-uploads.huggingface.co/production/uploads/600ae38cc92b79f54efd4556/dcbpF6YS6RQhqDd6GZZ2v.png" width="200px" align="center" />
[Kaggle](https://kaggle.com), generous hours of free notebooks for research projects.
#### And...
Good friends, who have accompanied the project, Luan Nguyen and Phu Tran.
## Confidence
In addition to the **Ghost 7B Alpha** project, **Ghost X** always wants to develop and improve many better models in the future, better supporting the community and businesses with the most openness possible.
Revealing the **Ghost 7B Beta** project plan. This model is expected to outperform with a deeper focus on multi-tasking, math, and reasoning. Along with that is the ability to expand context length and support other languages (highly requested languages).
The organization is being operated and developed by [Hieu Lam](https://huggingface.co/ghost-x)'s personal resources, if there is any development support or consulting request. Please feel free to contact the organization, we are very happy about this. Directly via email: [[email protected]](mailto:[email protected]).
**Ghost X** is happy to support providing models for server providers, aiming to help startups develop better.
## Contact
Follow **Ghost X** to stay updated with the latest information.
- Twitter/X via [@ghostx_ai](https://twitter.com/ghostx_ai).
- HuggingFace via [@ghost-x](https://huggingface.co/ghost-x).
- Official website [ghost-x.org](https://ghost-x.org/).
|
Lakshmi12/tiny-chatbot-dpo | Lakshmi12 | 2024-05-19T07:12:12Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:46:25Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the Anthropic/hh-rlhf dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Lora,qLora |
Rushi07/tiny-chatbot-dpo | Rushi07 | 2024-05-19T07:08:09Z | 2 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T07:06:01Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
XMin08/Model_Llama2_v2 | XMin08 | 2024-05-19T07:07:14Z | 11 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-19T06:57:57Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
TinyPixel/openelm-adapter | TinyPixel | 2024-05-19T07:06:45Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T04:07:19Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
baroniaadarsh/sft-tiny-chatbot-1 | baroniaadarsh | 2024-05-19T07:06:25Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T07:06:16Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinhViet/test1 | MinhViet | 2024-05-19T07:05:21Z | 161 | 0 | transformers | [
"transformers",
"safetensors",
"mbart",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-19T07:04:21Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
krupakar-reddy/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF | krupakar-reddy | 2024-05-19T07:02:53Z | 1 | 0 | null | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-05-16T04:54:21Z | ---
language:
- en
license: llama3
infernece: true
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- llama-cpp
- gguf-my-repo
pipeline_tag: text-generation
extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
\ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
\ 3\" means the foundational large language models and software and algorithms,\
\ including machine-learning model code, trained model weights, inference-enabling\
\ code, training-enabling code, fine-tuning enabling code and other elements of\
\ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
\"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
\ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
\ an entity, your principal place of business is in the EEA or Switzerland) and\
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
\ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
\ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
\ under Meta’s intellectual property or other rights owned by Meta embodied in the\
\ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
\ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
\ If you distribute or make available the Llama Materials (or any derivative works\
\ thereof), or a product or service that uses any of them, including another AI\
\ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
\ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
\ interface, blogpost, about page, or product documentation. If you use the Llama\
\ Materials to create, train, fine tune, or otherwise improve an AI model, which\
\ is distributed or made available, you shall also include “Llama 3” at the beginning\
\ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
\ works thereof, from a Licensee as part of an integrated end user product, then\
\ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
\ copies of the Llama Materials that you distribute the following attribution notice\
\ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
\ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\nv. You will not use the Llama Materials or any output or\
\ results of the Llama Materials to improve any other large language model (excluding\
\ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
\ on the Meta Llama 3 version release date, the monthly active users of the products\
\ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
\ than 700 million monthly active users in the preceding calendar month, you must\
\ request a license from Meta, which Meta may grant to you in its sole discretion,\
\ and you are not authorized to exercise any of the rights under this Agreement\
\ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
\ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
\ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
\ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
\ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
\ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
\ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
\ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
\ and in connection with the Llama Materials, neither Meta nor Licensee may use\
\ any name or mark owned by or associated with the other or any of its affiliates,\
\ except as required for reasonable and customary use in describing and redistributing\
\ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
\ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
\ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
\ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
\ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
\ Meta, with respect to any derivative works and modifications of the Llama Materials\
\ that are made by you, as between you and Meta, you are and will be the owner of\
\ such derivative works and modifications.\nc. If you institute litigation or other\
\ proceedings against Meta or any entity (including a cross-claim or counterclaim\
\ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
\ or any portion of any of the foregoing, constitutes infringement of intellectual\
\ property or other rights owned or licensable by you, then any licenses granted\
\ to you under this Agreement shall terminate as of the date such litigation or\
\ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
\ against any claim by any third party arising out of or related to your use or\
\ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
\ Agreement will commence upon your acceptance of this Agreement or access to the\
\ Llama Materials and will continue in full force and effect until terminated in\
\ accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
\ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
\ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
\ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
\ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 4.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
\ human-generated\n 6. Generating or facilitating false online engagement, including\
\ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
\ disclose to end users any known dangers of your AI system\nPlease report any violation\
\ of this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
widget:
- example_title: Hello
messages:
- role: user
content: Hey my name is Julien! How are you?
- example_title: Winter holidays
messages:
- role: system
content: You are a helpful and honest assistant. Please, respond concisely and
truthfully.
- role: user
content: Can you recommend a good destination for Winter holidays?
- example_title: Programming assistant
messages:
- role: system
content: You are a helpful and honest code and programming assistant. Please,
respond concisely and truthfully.
- role: user
content: Write a function that computes the nth fibonacci number.
inference:
parameters:
max_new_tokens: 300
stop:
- <|end_of_text|>
- <|eot_id|>
---
# krupakar-reddy/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`meta-llama/Meta-Llama-3-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo krupakar-reddy/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF --model meta-llama-3-8b-instruct.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo krupakar-reddy/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF --model meta-llama-3-8b-instruct.Q4_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m meta-llama-3-8b-instruct.Q4_K_M.gguf -n 128
```
|
giges/yapayzekaio | giges | 2024-05-19T06:58:57Z | 0 | 0 | asteroid | [
"asteroid",
"text-generation-inference",
"legal",
"art",
"tr",
"en",
"dataset:HuggingFaceFW/fineweb",
"dataset:PleIAs/YouTube-Commons",
"dataset:HuggingFaceM4/the_cauldron",
"dataset:mlabonne/orpo-dpo-mix-40k",
"dataset:nvidia/ChatQA-Training-Data",
"dataset:allenai/WildChat-1M",
"arxiv:1910.09700",
"license:gpl-3.0",
"region:us"
] | null | 2024-05-19T06:07:46Z | ---
license: gpl-3.0
datasets:
- HuggingFaceFW/fineweb
- PleIAs/YouTube-Commons
- HuggingFaceM4/the_cauldron
- mlabonne/orpo-dpo-mix-40k
- nvidia/ChatQA-Training-Data
- allenai/WildChat-1M
language:
- tr
- en
metrics:
- character
- accuracy
- bertscore
- bleu
- code_eval
library_name: asteroid
tags:
- text-generation-inference
- legal
- art
---
---
license: gpl-3.0
datasets:
- HuggingFaceFW/fineweb
- PleIAs/YouTube-Commons
- HuggingFaceM4/the_cauldron
- mlabonne/orpo-dpo-mix-40k
- nvidia/ChatQA-Training-Data
- allenai/WildChat-1M
language:
- tr
- en
metrics:
- karakter
- doğruluk
- bertskor
- BLEU
- kod_değerlendirme
library_name: asteroid
tags:
- metin-oluşturma-tahmini
- hukuk
- sanat
---
# Model Kartı - Model Kimliği
Bu model kartı, yeni modeller için bir temel şablon oluşturmayı amaçlamaktadır. [Bu ham şablonu](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1) kullanarak oluşturulmuştur.
## Model Detayları
### Model Açıklaması
Bu model, metin oluşturma ve çıkarımı için kullanılır. Daha uzun bir özet sağlamak için model geliştiricisi tarafından daha fazla bilgi sağlanması beklenmektedir.
- **Geliştirici:** [MERT KORAY KARAKUŞ, Örnek Proje A.Ş.]
- **Finanse eden:** GİGES
- **Paylaşan** GİGES
- **Model türü:** Metin oluşturma ve çıkarımı
- **Dil(ler) (NLP):** Türkçe, İngilizce
- **Lisans:** GPL-3.0
- **İnce ayarlanmış model [isteğe bağlı]:** [Örnek model adı veya referans]
### Model Kaynakları [isteğe bağlı]
- **Depo:** [GitHub depo bağlantısı]
- **Makale [isteğe bağlı]:** [Makale bağlantısı]
- **Demo [isteğe bağlı]:** [Demo bağlantısı]
## Kullanımlar
### Doğrudan Kullanım
Bu model, metin oluşturma, özetleme ve benzeri görevler için doğrudan kullanılabilir.
### Aşağı Akış Kullanımı [isteğe bağlı]
Bu model, örneğin bir sohbet botu veya metin tabanlı bir uygulama içinde kullanılmak üzere ince ayarlanabilir.
### Kapsam Dışı Kullanım
Bu model, tabii ki, tıbbi teşhis veya finansal danışmanlık gibi kritik kararların alınmasında kullanılmamalıdır.
## Önyargılar, Riskler ve Sınırlamalar
Bu modelin doğruluğu, özellikle belirli konularda sınırlı olabilir. Örneğin, karmaşık hukuki veya tıbbi terimlerin doğru bir şekilde anlaşılmasını sağlamak için ek bir inceleme gerekebilir.
### Tavsiyeler
Kullanıcılar, bu modelin sınırlarını ve olası hatalarını dikkate almalıdır. Özellikle, metin tabanlı karar alma süreçlerinde tamamen bağımsız bir şekilde kullanılmamalıdır.
## Nasıl Başlanır?
Bu modelle başlamak için, Hugging Face kütüphanesini kullanarak aşağıdaki kodu kullanabilirsiniz:
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## 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] |
issaccyj/lora-sdxl-retro | issaccyj | 2024-05-19T06:58:46Z | 3 | 1 | diffusers | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-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 | 2024-05-19T06:39:25Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'a dog in szn style'
output:
url:
"image_0.png"
- text: 'a dog in szn style'
output:
url:
"image_1.png"
- text: 'a dog in szn style'
output:
url:
"image_2.png"
- text: 'a dog in szn style'
output:
url:
"image_3.png"
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: an elephant in szn style
license: openrail++
---
# SDXL LoRA DreamBooth - issaccyj/lora-sdxl-retro
<Gallery />
## Model description
These are issaccyj/lora-sdxl-retro LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use an elephant in szn style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](issaccyj/lora-sdxl-retro/tree/main) them in the Files & versions tab.
|
sushilchikane/tiny-chatbot-dpo | sushilchikane | 2024-05-19T06:56:46Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:54:24Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
RichardErkhov/core-3_-_kuno-royale-7B-4bits | RichardErkhov | 2024-05-19T06:49:10Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-19T06:45:53Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
kuno-royale-7B - bnb 4bits
- Model creator: https://huggingface.co/core-3/
- Original model: https://huggingface.co/core-3/kuno-royale-7B/
Original model description:
---
license: cc-by-nc-2.0
tags:
- merge
- mergekit
- lazymergekit
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- eren23/ogno-monarch-jaskier-merge-7b
base_model:
- SanjiWatsuki/Kunoichi-DPO-v2-7B
- eren23/ogno-monarch-jaskier-merge-7b
model-index:
- name: kuno-royale-7B
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 71.76
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 88.2
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 65.13
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 71.12
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 82.32
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 69.9
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=core-3/kuno-royale-7B
name: Open LLM Leaderboard
---
# kuno-royale-7B
[v2 is probably better](https://huggingface.co/core-3/kuno-royale-v2-7b) 🤷
|Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|-------------------|---------|-----|-----------|------|------------|------------|-------|
| eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO | 76.45 | 73.12 | 89.09 | 64.80 | 77.45 | 84.77 | 69.45 |
| [core-3/kuno-royale-v2-7b](https://huggingface.co/core-3/kuno-royale-v2-7b) | 74.80 | 72.01 | 88.15 | 65.07 | 71.10 | 82.24 | 70.20 |
| **core-3/kuno-royale-7B** | **74.74** | **71.76** | **88.20** | **65.13** | **71.12** | **82.32** | **69.90**
| SanjiWatsuki/Kunoichi-DPO-v2-7B | 72.46 | 69.62 | 87.44 | 64.94 | 66.06 | 80.82 | 65.88 |
| SanjiWatsuki/Kunoichi-7B | 72.13 | 68.69 | 87.10 | 64.90 | 64.04 | 81.06 | 67.02 |
## Original LazyMergekit Card:
kuno-royale-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
* [eren23/ogno-monarch-jaskier-merge-7b](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0, 32]
- model: eren23/ogno-monarch-jaskier-merge-7b
layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "core-3/kuno-royale-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
YYYYYYibo/vanilla_doff_iter_2 | YYYYYYibo | 2024-05-19T06:48:08Z | 0 | 0 | peft | [
"peft",
"safetensors",
"mistral",
"alignment-handbook",
"generated_from_trainer",
"trl",
"dpo",
"dataset:updated",
"dataset:original",
"base_model:alignment-handbook/zephyr-7b-sft-full",
"base_model:adapter:alignment-handbook/zephyr-7b-sft-full",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:01:10Z | ---
license: apache-2.0
library_name: peft
tags:
- alignment-handbook
- generated_from_trainer
- trl
- dpo
base_model: alignment-handbook/zephyr-7b-sft-full
datasets:
- updated
- original
model-index:
- name: vanilla_doff_iter_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. -->
# vanilla_doff_iter_2
This model is a fine-tuned version of [YYYYYYibo/vanilla_doff_iter_1](https://huggingface.co/YYYYYYibo/vanilla_doff_iter_1) on the updated and the original datasets.
It achieves the following results on the evaluation set:
- Loss: 0.6681
- Rewards/chosen: -0.1963
- Rewards/rejected: -0.2541
- Rewards/accuracies: 0.5560
- Rewards/margins: 0.0578
- Logps/rejected: -295.9663
- Logps/chosen: -311.6507
- Logits/rejected: -2.5643
- Logits/chosen: -2.6639
## 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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.66 | 0.65 | 100 | 0.6681 | -0.1963 | -0.2541 | 0.5560 | 0.0578 | -295.9663 | -311.6507 | -2.5643 | -2.6639 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.3.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2 |
Rushi07/sft-tiny-chatbot | Rushi07 | 2024-05-19T06:46:17Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:44:55Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Prolux/Fire | Prolux | 2024-05-19T06:44:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"base_model:finetune:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-19T06:44:38Z | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** Prolux
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Divyaamith/tiny-chatbot-dpo | Divyaamith | 2024-05-19T06:44:51Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:42:42Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Manirathinam21/tiny-chatbot-dpo | Manirathinam21 | 2024-05-19T06:44:45Z | 4 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:42:27Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
vuongnhathien/test-save-model-2 | vuongnhathien | 2024-05-19T06:43:29Z | 136 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"swinv2",
"image-classification",
"generated_from_trainer",
"base_model:microsoft/swinv2-tiny-patch4-window16-256",
"base_model:finetune:microsoft/swinv2-tiny-patch4-window16-256",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2024-05-19T06:29:12Z | ---
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window16-256
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test-save-model-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. -->
# test-save-model-2
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window16-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window16-256) on the jbarat/plant_species dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2007
- Accuracy: 0.925
## 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: 0.0003
- train_batch_size: 64
- 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 | Accuracy | Validation Loss |
|:-------------:|:-----:|:----:|:--------:|:---------------:|
| No log | 1.0 | 10 | 0.7125 | 0.6565 |
| No log | 2.0 | 20 | 0.7875 | 0.5848 |
| No log | 3.0 | 30 | 0.8375 | 0.6128 |
| No log | 4.0 | 40 | 0.6844 | 0.7625 |
| No log | 5.0 | 50 | 0.5467 | 0.8125 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
|
hon9kon9ize/cantonesellm-cpt-202405 | hon9kon9ize | 2024-05-19T06:41:34Z | 7 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"alignment-handbook",
"trl",
"sft",
"generated_from_trainer",
"dataset:hon9kon9ize/cantonesellm-pt-20240514",
"base_model:hon9kon9ize/yi-1.5-6b-yue-vocab-expanded",
"base_model:finetune:hon9kon9ize/yi-1.5-6b-yue-vocab-expanded",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-15T20:36:30Z | ---
base_model: hon9kon9ize/yi-1.5-6b-yub-vocab-expanded
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- hon9kon9ize/cantonesellm-pt-20240514
model-index:
- name: cantonesellm-cpt-202405
results: []
license: apache-2.0
---
<!-- 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. -->
# cantonesellm-cpt-202405
This model is a fine-tuned version of [hon9kon9ize/yi-1.5-6b-yub-vocab-expanded](https://huggingface.co/hon9kon9ize/yi-1.5-6b-yub-vocab-expanded) on the hon9kon9ize/cantonesellm-pt-20240514 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.40.2
- Pytorch 2.1.0+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1 |
PraveenCMR/tiny-chatbot-dpo | PraveenCMR | 2024-05-19T06:41:24Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:39:01Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
bhassi01/tiny-chatbot-dpo | bhassi01 | 2024-05-19T06:40:13Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:37:31Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_0bpw_exl2 | Zoyd | 2024-05-19T06:39:33Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"en",
"arxiv:2405.03548",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"6-bit",
"exl2",
"region:us"
] | text-generation | 2024-05-19T06:31:22Z | ---
license: mit
language:
- en
---
**Exllamav2** quant (**exl2** / **6.0 bpw**) made with ExLlamaV2 v0.0.21
| Quant | Model Size | lm_head |
| ----- | ---------- | ------- |
| [3.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_0bpw_exl2) | 16960 MB | 6 |
| [3.5](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_5bpw_exl2) | 19723 MB | 6 |
| [3.75](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_75bpw_exl2) | 21106 MB | 6 |
| [4.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_0bpw_exl2) | 22447 MB | 6 |
| [4.25](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_25bpw_exl2) | 23877 MB | 6 |
| [5.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-5_0bpw_exl2) | 28025 MB | 6 |
| [6.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_0bpw_exl2) | 33581 MB | 8 |
| [6.5](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_5bpw_exl2) | 36250 MB | 8 |
| [8.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-8_0bpw_exl2) | 41879 MB | 8 |
# 🦣 MAmmoTH2: Scaling Instructions from the Web
Project Page: [https://tiger-ai-lab.github.io/MAmmoTH2/](https://tiger-ai-lab.github.io/MAmmoTH2/)
Paper: [https://arxiv.org/pdf/2405.03548](https://arxiv.org/pdf/2405.03548)
Code: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Introduction
Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 34% on MATH and from 36% to 67% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.
| | **Base Model** | **MAmmoTH2** | **MAmmoTH2-Plus** |
|:-----|:---------------------|:-------------------------------------------------------------------|:------------------------------------------------------------------|
| 7B | Mistral | 🦣 [MAmmoTH2-7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B) | 🦣 [MAmmoTH2-7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B-Plus) |
| 8B | Llama-3 | 🦣 [MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B) | 🦣 [MAmmoTH2-8B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus) |
| 8x7B | Mixtral | 🦣 [MAmmoTH2-8x7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B) | 🦣 [MAmmoTH2-8x7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B-Plus) |
## Training Data
Please refer to https://huggingface.co/datasets/TIGER-Lab/WebInstructSub for more details.
## Training Procedure
The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral and Mistal models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
## Evaluation
The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
| **Model** | **TheoremQA** | **MATH** | **GSM8K** | **GPQA** | **MMLU-ST** | **BBH** | **ARC-C** | **Avg** |
|:-----------------------|:--------------|:---------|:----------|:---------|:------------|:--------|:----------|:---------|
| **MAmmoTH2-7B** | 26.7 | 34.2 | 67.4 | 34.8 | 60.6 | 60.0 | 81.8 | 52.2 |
| **MAmmoTH2-8B** | 29.7 | 33.4 | 67.9 | 38.4 | 61.0 | 60.8 | 81.0 | 53.1 |
| **MAmmoTH2-8x7B** | 32.2 | 39.0 | 75.4 | 36.8 | 67.4 | 71.1 | 87.5 | 58.9 |
| **MAmmoTH2-7B-Plus** | 29.2 | 45.0 | 84.7 | 36.8 | 64.5 | 63.1 | 83.0 | 58.0 |
| **MAmmoTH2-8B-Plus** | 32.5 | 42.8 | 84.1 | 37.3 | 65.7 | 67.8 | 83.4 | 59.1 |
| **MAmmoTH2-8x7B-Plus** | 34.1 | 47.0 | 86.4 | 37.8 | 72.4 | 74.1 | 88.4 | 62.9 |
## Usage
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
Check our Github repo for more advanced use: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Limitations
We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.
## Citation
If you use the models, data, or code from this project, please cite the original paper:
```
@article{yue2024mammoth2,
title={MAmmoTH2: Scaling Instructions from the Web},
author={Yue, Xiang and Zheng, Tuney and Zhang, Ge and Chen, Wenhu},
journal={arXiv preprint arXiv:2405.03548},
year={2024}
}
``` |
Saba06huggingface/tiny-chatbot-dpo | Saba06huggingface | 2024-05-19T06:38:00Z | 3 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:35:41Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Avik812/tiny-chatbot-dpo | Avik812 | 2024-05-19T06:37:56Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:35:46Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
SaravanaPriyan/tiny-chatbot-dpo | SaravanaPriyan | 2024-05-19T06:37:43Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:35:34Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
SAMMY007/tiny-chatbot-dpo | SAMMY007 | 2024-05-19T06:37:41Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:35:36Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
cminja/Llama-3-8B-Lexi-Uncensored-Q8_0-GGUF | cminja | 2024-05-19T06:37:13Z | 11 | 1 | null | [
"gguf",
"uncensored",
"llama3",
"instruct",
"open",
"llama-cpp",
"gguf-my-repo",
"license:llama3",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-05-19T06:36:48Z | ---
license: llama3
tags:
- uncensored
- llama3
- instruct
- open
- llama-cpp
- gguf-my-repo
---
# cminja/Llama-3-8B-Lexi-Uncensored-Q8_0-GGUF
This model was converted to GGUF format from [`Orenguteng/Llama-3-8B-Lexi-Uncensored`](https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo cminja/Llama-3-8B-Lexi-Uncensored-Q8_0-GGUF --model llama-3-8b-lexi-uncensored.Q8_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo cminja/Llama-3-8B-Lexi-Uncensored-Q8_0-GGUF --model llama-3-8b-lexi-uncensored.Q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-3-8b-lexi-uncensored.Q8_0.gguf -n 128
```
|
FUZZZZI/tiny-chatbot-dpo | FUZZZZI | 2024-05-19T06:36:46Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:34:38Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
shrchrds/sft-tiny-chatbot | shrchrds | 2024-05-19T06:36:30Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:53:38Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
akash-soni/tiny-chatbot-dpo | akash-soni | 2024-05-19T06:35:49Z | 2 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:33:45Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
srinibashdash/tiny-chatbot-dpo | srinibashdash | 2024-05-19T06:34:38Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:32:33Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
mbhargav/tiny-chatbot-dpo | mbhargav | 2024-05-19T06:34:32Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:32:20Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
JapiKredi/tiny-chatbot-dpo | JapiKredi | 2024-05-19T06:34:25Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:32:11Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
jaichhabria/tiny-chatbot-dpo | jaichhabria | 2024-05-19T06:34:21Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:32:15Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
SachinGenAIMaster/tiny-chatbot-dpo | SachinGenAIMaster | 2024-05-19T06:34:10Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:32:05Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
snshrivas10/tiny-chatbot-dpo | snshrivas10 | 2024-05-19T06:33:48Z | 4 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:31:42Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: tiny-chatbot-dpo
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. -->
# tiny-chatbot-dpo
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
apwic/sentiment-lora-r8a1d0.05-1 | apwic | 2024-05-19T06:33:14Z | 0 | 0 | null | [
"tensorboard",
"generated_from_trainer",
"id",
"base_model:indolem/indobert-base-uncased",
"base_model:finetune:indolem/indobert-base-uncased",
"license:mit",
"region:us"
] | null | 2024-05-19T06:00:01Z | ---
language:
- id
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment-lora-r8a1d0.05-1
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. -->
# sentiment-lora-r8a1d0.05-1
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3148
- Accuracy: 0.8697
- Precision: 0.8474
- Recall: 0.8328
- F1: 0.8395
## 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: 30
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.5657 | 1.0 | 122 | 0.5161 | 0.7243 | 0.6616 | 0.6474 | 0.6529 |
| 0.5088 | 2.0 | 244 | 0.4913 | 0.7393 | 0.6917 | 0.7056 | 0.6971 |
| 0.4682 | 3.0 | 366 | 0.4424 | 0.7845 | 0.7401 | 0.7425 | 0.7413 |
| 0.4114 | 4.0 | 488 | 0.3980 | 0.8095 | 0.7702 | 0.7702 | 0.7702 |
| 0.3862 | 5.0 | 610 | 0.3890 | 0.8145 | 0.7783 | 0.8088 | 0.7889 |
| 0.3512 | 6.0 | 732 | 0.3583 | 0.8496 | 0.8245 | 0.8036 | 0.8128 |
| 0.3428 | 7.0 | 854 | 0.3496 | 0.8521 | 0.8207 | 0.8254 | 0.8229 |
| 0.3254 | 8.0 | 976 | 0.3425 | 0.8496 | 0.8245 | 0.8036 | 0.8128 |
| 0.3226 | 9.0 | 1098 | 0.3388 | 0.8571 | 0.8310 | 0.8189 | 0.8245 |
| 0.3063 | 10.0 | 1220 | 0.3376 | 0.8647 | 0.8439 | 0.8217 | 0.8315 |
| 0.2939 | 11.0 | 1342 | 0.3319 | 0.8672 | 0.8463 | 0.8260 | 0.8351 |
| 0.2838 | 12.0 | 1464 | 0.3323 | 0.8546 | 0.8263 | 0.8196 | 0.8229 |
| 0.2916 | 13.0 | 1586 | 0.3283 | 0.8647 | 0.8472 | 0.8167 | 0.8296 |
| 0.2826 | 14.0 | 1708 | 0.3244 | 0.8672 | 0.8463 | 0.8260 | 0.8351 |
| 0.2739 | 15.0 | 1830 | 0.3231 | 0.8697 | 0.8449 | 0.8378 | 0.8412 |
| 0.2674 | 16.0 | 1952 | 0.3221 | 0.8697 | 0.8449 | 0.8378 | 0.8412 |
| 0.2648 | 17.0 | 2074 | 0.3193 | 0.8722 | 0.8528 | 0.8321 | 0.8413 |
| 0.2687 | 18.0 | 2196 | 0.3172 | 0.8697 | 0.8460 | 0.8353 | 0.8404 |
| 0.264 | 19.0 | 2318 | 0.3170 | 0.8747 | 0.8552 | 0.8363 | 0.8448 |
| 0.2637 | 20.0 | 2440 | 0.3148 | 0.8697 | 0.8474 | 0.8328 | 0.8395 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2
|
StevenTse7340/Models-RoBERTa | StevenTse7340 | 2024-05-19T06:31:51Z | 107 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-base",
"base_model:finetune:FacebookAI/roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-19T06:05:37Z | ---
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Models-RoBERTa
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. -->
# Models-RoBERTa
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6513
- Accuracy: 0.645
## 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: 3
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
|
Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-5_0bpw_exl2 | Zoyd | 2024-05-19T06:30:53Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"en",
"arxiv:2405.03548",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"5-bit",
"exl2",
"region:us"
] | text-generation | 2024-05-19T06:22:48Z | ---
license: mit
language:
- en
---
**Exllamav2** quant (**exl2** / **5.0 bpw**) made with ExLlamaV2 v0.0.21
| Quant | Model Size | lm_head |
| ----- | ---------- | ------- |
| [3.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_0bpw_exl2) | 16960 MB | 6 |
| [3.5](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_5bpw_exl2) | 19723 MB | 6 |
| [3.75](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_75bpw_exl2) | 21106 MB | 6 |
| [4.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_0bpw_exl2) | 22447 MB | 6 |
| [4.25](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_25bpw_exl2) | 23877 MB | 6 |
| [5.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-5_0bpw_exl2) | 28025 MB | 6 |
| [6.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_0bpw_exl2) | 33581 MB | 8 |
| [6.5](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_5bpw_exl2) | 36250 MB | 8 |
| [8.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-8_0bpw_exl2) | 41879 MB | 8 |
# 🦣 MAmmoTH2: Scaling Instructions from the Web
Project Page: [https://tiger-ai-lab.github.io/MAmmoTH2/](https://tiger-ai-lab.github.io/MAmmoTH2/)
Paper: [https://arxiv.org/pdf/2405.03548](https://arxiv.org/pdf/2405.03548)
Code: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Introduction
Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 34% on MATH and from 36% to 67% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.
| | **Base Model** | **MAmmoTH2** | **MAmmoTH2-Plus** |
|:-----|:---------------------|:-------------------------------------------------------------------|:------------------------------------------------------------------|
| 7B | Mistral | 🦣 [MAmmoTH2-7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B) | 🦣 [MAmmoTH2-7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B-Plus) |
| 8B | Llama-3 | 🦣 [MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B) | 🦣 [MAmmoTH2-8B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus) |
| 8x7B | Mixtral | 🦣 [MAmmoTH2-8x7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B) | 🦣 [MAmmoTH2-8x7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B-Plus) |
## Training Data
Please refer to https://huggingface.co/datasets/TIGER-Lab/WebInstructSub for more details.
## Training Procedure
The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral and Mistal models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
## Evaluation
The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
| **Model** | **TheoremQA** | **MATH** | **GSM8K** | **GPQA** | **MMLU-ST** | **BBH** | **ARC-C** | **Avg** |
|:-----------------------|:--------------|:---------|:----------|:---------|:------------|:--------|:----------|:---------|
| **MAmmoTH2-7B** | 26.7 | 34.2 | 67.4 | 34.8 | 60.6 | 60.0 | 81.8 | 52.2 |
| **MAmmoTH2-8B** | 29.7 | 33.4 | 67.9 | 38.4 | 61.0 | 60.8 | 81.0 | 53.1 |
| **MAmmoTH2-8x7B** | 32.2 | 39.0 | 75.4 | 36.8 | 67.4 | 71.1 | 87.5 | 58.9 |
| **MAmmoTH2-7B-Plus** | 29.2 | 45.0 | 84.7 | 36.8 | 64.5 | 63.1 | 83.0 | 58.0 |
| **MAmmoTH2-8B-Plus** | 32.5 | 42.8 | 84.1 | 37.3 | 65.7 | 67.8 | 83.4 | 59.1 |
| **MAmmoTH2-8x7B-Plus** | 34.1 | 47.0 | 86.4 | 37.8 | 72.4 | 74.1 | 88.4 | 62.9 |
## Usage
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
Check our Github repo for more advanced use: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Limitations
We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.
## Citation
If you use the models, data, or code from this project, please cite the original paper:
```
@article{yue2024mammoth2,
title={MAmmoTH2: Scaling Instructions from the Web},
author={Yue, Xiang and Zheng, Tuney and Zhang, Ge and Chen, Wenhu},
journal={arXiv preprint arXiv:2405.03548},
year={2024}
}
``` |
theGhoul21/srl-adapter-irpo-6000 | theGhoul21 | 2024-05-19T06:28:35Z | 1 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:theGhoul21/srl-base-irpo-080524-16bit-v0.3-lighning-ai",
"base_model:adapter:theGhoul21/srl-base-irpo-080524-16bit-v0.3-lighning-ai",
"region:us"
] | null | 2024-05-17T04:44:58Z | ---
library_name: peft
base_model: theGhoul21/srl-base-irpo-080524-16bit-v0.3-lighning-ai
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.10.0 |
baek26/dialogsum_784_bart-dialogsum_rl | baek26 | 2024-05-19T06:27:09Z | 49 | 0 | transformers | [
"transformers",
"safetensors",
"bart",
"text2text-generation",
"trl",
"ppo",
"reinforcement-learning",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | reinforcement-learning | 2024-05-19T06:26:20Z | ---
license: apache-2.0
tags:
- trl
- ppo
- transformers
- reinforcement-learning
---
# TRL Model
This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to
guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
## Usage
To use this model for inference, first install the TRL library:
```bash
python -m pip install trl
```
You can then generate text as follows:
```python
from transformers import pipeline
generator = pipeline("text-generation", model="baek26//tmp/tmp5a4ra92y/baek26/dialogsum_784_bart-dialogsum_rl")
outputs = generator("Hello, my llama is cute")
```
If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
```python
from transformers import AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead
tokenizer = AutoTokenizer.from_pretrained("baek26//tmp/tmp5a4ra92y/baek26/dialogsum_784_bart-dialogsum_rl")
model = AutoModelForCausalLMWithValueHead.from_pretrained("baek26//tmp/tmp5a4ra92y/baek26/dialogsum_784_bart-dialogsum_rl")
inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
outputs = model(**inputs, labels=inputs["input_ids"])
```
|
sskr/toxic_classification | sskr | 2024-05-19T06:23:39Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:23:39Z | ---
license: apache-2.0
---
|
issaccyj/cartoonillustration | issaccyj | 2024-05-19T06:21:51Z | 2 | 0 | diffusers | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-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 | 2024-05-19T06:09:50Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'a cat in szn style'
output:
url:
"image_0.png"
- text: 'a cat in szn style'
output:
url:
"image_1.png"
- text: 'a cat in szn style'
output:
url:
"image_2.png"
- text: 'a cat in szn style'
output:
url:
"image_3.png"
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a woman walking a dog in szn style
license: openrail++
---
# SDXL LoRA DreamBooth - issaccyj/cartoonillustration
<Gallery />
## Model description
These are issaccyj/cartoonillustration LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use a woman walking a dog in szn style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](issaccyj/cartoonillustration/tree/main) them in the Files & versions tab.
|
yzhuang/Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Japanese_v2 | yzhuang | 2024-05-19T06:21:40Z | 11 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-17T08:54:07Z | ---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Japanese_v2
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yufanz/autotree/runs/7283881766.46478-720696f5-5799-4c26-9505-2df28e3a300e)
# Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Japanese_v2
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 48
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.19.1
- Tokenizers 0.19.1
|
mayankchugh-learning/sft-tiny-chatbot | mayankchugh-learning | 2024-05-19T06:21:21Z | 3 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:20:05Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Shorya22/Mistral-7B-Fine_Tunned_Model | Shorya22 | 2024-05-19T06:20:54Z | 8 | 2 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-19T06:14:21Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
hideax/llama2_stage2_iter40000_chatbot_arena_orpo_4 | hideax | 2024-05-19T06:20:29Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-19T06:12:02Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
SAMMY007/sft-tiny-chatbot | SAMMY007 | 2024-05-19T06:20:12Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:18:52Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
sushilchikane/sft-tiny-chatbot | sushilchikane | 2024-05-19T06:14:29Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T06:13:10Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_0bpw_exl2 | Zoyd | 2024-05-19T06:13:44Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"en",
"arxiv:2405.03548",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"exl2",
"region:us"
] | text-generation | 2024-05-19T06:05:16Z | ---
license: mit
language:
- en
---
**Exllamav2** quant (**exl2** / **4.0 bpw**) made with ExLlamaV2 v0.0.21
| Quant | Model Size | lm_head |
| ----- | ---------- | ------- |
| [3.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_0bpw_exl2) | 16960 MB | 6 |
| [3.5](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_5bpw_exl2) | 19723 MB | 6 |
| [3.75](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-3_75bpw_exl2) | 21106 MB | 6 |
| [4.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_0bpw_exl2) | 22447 MB | 6 |
| [4.25](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-4_25bpw_exl2) | 23877 MB | 6 |
| [5.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-5_0bpw_exl2) | 28025 MB | 6 |
| [6.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_0bpw_exl2) | 33581 MB | 8 |
| [6.5](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-6_5bpw_exl2) | 36250 MB | 8 |
| [8.0](https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-8x7B-Plus-8_0bpw_exl2) | 41879 MB | 8 |
# 🦣 MAmmoTH2: Scaling Instructions from the Web
Project Page: [https://tiger-ai-lab.github.io/MAmmoTH2/](https://tiger-ai-lab.github.io/MAmmoTH2/)
Paper: [https://arxiv.org/pdf/2405.03548](https://arxiv.org/pdf/2405.03548)
Code: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Introduction
Introducing 🦣 MAmmoTH2, a game-changer in improving the reasoning abilities of large language models (LLMs) through innovative instruction tuning. By efficiently harvesting 10 million instruction-response pairs from the pre-training web corpus, we've developed MAmmoTH2 models that significantly boost performance on reasoning benchmarks. For instance, MAmmoTH2-7B (Mistral) sees its performance soar from 11% to 34% on MATH and from 36% to 67% on GSM8K, all without training on any domain-specific data. Further training on public instruction tuning datasets yields MAmmoTH2-Plus, setting new standards in reasoning and chatbot benchmarks. Our work presents a cost-effective approach to acquiring large-scale, high-quality instruction data, offering a fresh perspective on enhancing LLM reasoning abilities.
| | **Base Model** | **MAmmoTH2** | **MAmmoTH2-Plus** |
|:-----|:---------------------|:-------------------------------------------------------------------|:------------------------------------------------------------------|
| 7B | Mistral | 🦣 [MAmmoTH2-7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B) | 🦣 [MAmmoTH2-7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-7B-Plus) |
| 8B | Llama-3 | 🦣 [MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B) | 🦣 [MAmmoTH2-8B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus) |
| 8x7B | Mixtral | 🦣 [MAmmoTH2-8x7B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B) | 🦣 [MAmmoTH2-8x7B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8x7B-Plus) |
## Training Data
Please refer to https://huggingface.co/datasets/TIGER-Lab/WebInstructSub for more details.
## Training Procedure
The models are fine-tuned with the WEBINSTRUCT dataset using the original Llama-3, Mistral and Mistal models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
## Evaluation
The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results:
| **Model** | **TheoremQA** | **MATH** | **GSM8K** | **GPQA** | **MMLU-ST** | **BBH** | **ARC-C** | **Avg** |
|:-----------------------|:--------------|:---------|:----------|:---------|:------------|:--------|:----------|:---------|
| **MAmmoTH2-7B** | 26.7 | 34.2 | 67.4 | 34.8 | 60.6 | 60.0 | 81.8 | 52.2 |
| **MAmmoTH2-8B** | 29.7 | 33.4 | 67.9 | 38.4 | 61.0 | 60.8 | 81.0 | 53.1 |
| **MAmmoTH2-8x7B** | 32.2 | 39.0 | 75.4 | 36.8 | 67.4 | 71.1 | 87.5 | 58.9 |
| **MAmmoTH2-7B-Plus** | 29.2 | 45.0 | 84.7 | 36.8 | 64.5 | 63.1 | 83.0 | 58.0 |
| **MAmmoTH2-8B-Plus** | 32.5 | 42.8 | 84.1 | 37.3 | 65.7 | 67.8 | 83.4 | 59.1 |
| **MAmmoTH2-8x7B-Plus** | 34.1 | 47.0 | 86.4 | 37.8 | 72.4 | 74.1 | 88.4 | 62.9 |
## Usage
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
Check our Github repo for more advanced use: [https://github.com/TIGER-AI-Lab/MAmmoTH2](https://github.com/TIGER-AI-Lab/MAmmoTH2)
## Limitations
We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively.
## Citation
If you use the models, data, or code from this project, please cite the original paper:
```
@article{yue2024mammoth2,
title={MAmmoTH2: Scaling Instructions from the Web},
author={Yue, Xiang and Zheng, Tuney and Zhang, Ge and Chen, Wenhu},
journal={arXiv preprint arXiv:2405.03548},
year={2024}
}
``` |
Pubudu/mbart-large-50_par_bn_rf_16_dinamina_5400 | Pubudu | 2024-05-19T06:11:17Z | 3 | 0 | adapter-transformers | [
"adapter-transformers",
"adapterhub:summarization/dinamina_5400_full_text",
"mbart",
"dataset:dinamina_5400_full_text",
"region:us"
] | null | 2024-05-19T06:10:18Z | ---
tags:
- adapterhub:summarization/dinamina_5400_full_text
- mbart
- adapter-transformers
datasets:
- dinamina_5400_full_text
---
# Adapter `Pubudu/mbart-large-50_par_bn_rf_16_dinamina_5400` for facebook/mbart-large-50
An [adapter](https://adapterhub.ml) for the `facebook/mbart-large-50` model that was trained on the [summarization/dinamina_5400_full_text](https://adapterhub.ml/explore/summarization/dinamina_5400_full_text/) dataset.
This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
## Usage
First, install `adapters`:
```
pip install -U adapters
```
Now, the adapter can be loaded and activated like this:
```python
from adapters import AutoAdapterModel
model = AutoAdapterModel.from_pretrained("facebook/mbart-large-50")
adapter_name = model.load_adapter("Pubudu/mbart-large-50_par_bn_rf_16_dinamina_5400", source="hf", set_active=True)
```
## Architecture & Training
<!-- Add some description here -->
## Evaluation results
<!-- Add some description here -->
## Citation
<!-- Add some description here --> |
DevonPeroutky/llama3-reddit-therapist-lora | DevonPeroutky | 2024-05-19T06:07:46Z | 3 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"base_model:adapter:unsloth/llama-3-8b-Instruct-bnb-4bit",
"region:us"
] | null | 2024-05-19T05:16:27Z | ---
library_name: peft
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.10.0 |
issaccyj/retro | issaccyj | 2024-05-19T06:04:14Z | 2 | 0 | diffusers | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-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 | 2024-05-19T05:52:08Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'a cat in szn style'
output:
url:
"image_0.png"
- text: 'a cat in szn style'
output:
url:
"image_1.png"
- text: 'a cat in szn style'
output:
url:
"image_2.png"
- text: 'a cat in szn style'
output:
url:
"image_3.png"
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: an elephant in szn style
license: openrail++
---
# SDXL LoRA DreamBooth - issaccyj/retro
<Gallery />
## Model description
These are issaccyj/retro LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use an elephant in szn style to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](issaccyj/retro/tree/main) them in the Files & versions tab.
|
Vlad1m/toxicity_analyzer | Vlad1m | 2024-05-19T06:02:15Z | 107 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-19T05:58:38Z | ---
license: apache-2.0
---
|
baroniaadarsh/sft-tiny-chatbot | baroniaadarsh | 2024-05-19T05:59:48Z | 0 | 1 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:58:19Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
apwic/sentiment-lora-r8a0d0.15-1 | apwic | 2024-05-19T05:59:42Z | 0 | 0 | null | [
"tensorboard",
"generated_from_trainer",
"id",
"base_model:indolem/indobert-base-uncased",
"base_model:finetune:indolem/indobert-base-uncased",
"license:mit",
"region:us"
] | null | 2024-05-19T05:26:35Z | ---
language:
- id
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment-lora-r8a0d0.15-1
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. -->
# sentiment-lora-r8a0d0.15-1
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3168
- Accuracy: 0.8722
- Precision: 0.8528
- Recall: 0.8321
- F1: 0.8413
## 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: 30
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.5647 | 1.0 | 122 | 0.5166 | 0.7068 | 0.6380 | 0.6250 | 0.6297 |
| 0.5067 | 2.0 | 244 | 0.4954 | 0.7343 | 0.6870 | 0.7020 | 0.6926 |
| 0.4617 | 3.0 | 366 | 0.4391 | 0.7920 | 0.7491 | 0.7503 | 0.7497 |
| 0.4044 | 4.0 | 488 | 0.3911 | 0.8145 | 0.7761 | 0.7788 | 0.7774 |
| 0.382 | 5.0 | 610 | 0.3827 | 0.8195 | 0.7849 | 0.8198 | 0.7962 |
| 0.3494 | 6.0 | 732 | 0.3528 | 0.8421 | 0.8092 | 0.8108 | 0.8100 |
| 0.3423 | 7.0 | 854 | 0.3442 | 0.8546 | 0.8239 | 0.8272 | 0.8255 |
| 0.33 | 8.0 | 976 | 0.3400 | 0.8672 | 0.8479 | 0.8235 | 0.8342 |
| 0.3296 | 9.0 | 1098 | 0.3349 | 0.8496 | 0.8245 | 0.8036 | 0.8128 |
| 0.3074 | 10.0 | 1220 | 0.3349 | 0.8622 | 0.8467 | 0.8100 | 0.8249 |
| 0.2911 | 11.0 | 1342 | 0.3240 | 0.8697 | 0.8503 | 0.8278 | 0.8377 |
| 0.2855 | 12.0 | 1464 | 0.3273 | 0.8722 | 0.8463 | 0.8446 | 0.8454 |
| 0.2903 | 13.0 | 1586 | 0.3285 | 0.8647 | 0.8472 | 0.8167 | 0.8296 |
| 0.2896 | 14.0 | 1708 | 0.3254 | 0.8672 | 0.8479 | 0.8235 | 0.8342 |
| 0.2744 | 15.0 | 1830 | 0.3241 | 0.8647 | 0.8377 | 0.8342 | 0.8359 |
| 0.2691 | 16.0 | 1952 | 0.3210 | 0.8571 | 0.8289 | 0.8239 | 0.8264 |
| 0.2671 | 17.0 | 2074 | 0.3208 | 0.8697 | 0.8503 | 0.8278 | 0.8377 |
| 0.2736 | 18.0 | 2196 | 0.3179 | 0.8722 | 0.8512 | 0.8346 | 0.8422 |
| 0.2662 | 19.0 | 2318 | 0.3180 | 0.8722 | 0.8544 | 0.8296 | 0.8404 |
| 0.2664 | 20.0 | 2440 | 0.3168 | 0.8722 | 0.8528 | 0.8321 | 0.8413 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2
|
SaravanaPriyan/sft-tiny-chatbot | SaravanaPriyan | 2024-05-19T05:58:34Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:57:13Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
PraveenCMR/sft-tiny-chatbot | PraveenCMR | 2024-05-19T05:57:21Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:56:00Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Saba06huggingface/sft-tiny-chatbot | Saba06huggingface | 2024-05-19T05:54:10Z | 2 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:52:41Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Divyaamith/sft-tiny-chatbot | Divyaamith | 2024-05-19T05:53:50Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:52:25Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Reenal/sft-tiny-chatbot | Reenal | 2024-05-19T05:53:49Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:52:29Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Audino/my-awesomev3-modelv2-large | Audino | 2024-05-19T05:52:35Z | 108 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2024-05-18T17:50:22Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
adas100/sft-tiny-chatbot | adas100 | 2024-05-19T05:51:21Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:50:02Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
bhassi01/sft-tiny-chatbot | bhassi01 | 2024-05-19T05:50:58Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:49:30Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
rgsubramaniam/sft-tiny-chatbot | rgsubramaniam | 2024-05-19T05:50:24Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:49:06Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
vinitlondhe21/sft-tiny-chatbot | vinitlondhe21 | 2024-05-19T05:50:23Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:49:00Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
JapiKredi/sft-tiny-chatbot | JapiKredi | 2024-05-19T05:50:06Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:48:46Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
jaichhabria/sft-tiny-chatbot | jaichhabria | 2024-05-19T05:50:02Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:48:43Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
interview-maistros/sft-tiny-chatbot | interview-maistros | 2024-05-19T05:49:56Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"license:apache-2.0",
"region:us"
] | null | 2024-05-19T05:48:37Z | ---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
model-index:
- name: sft-tiny-chatbot
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. -->
# sft-tiny-chatbot
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 250
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1 |
Vlad1m/destractive_context | Vlad1m | 2024-05-19T05:44:40Z | 107 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2024-05-19T05:43:29Z | ---
license: apache-2.0
---
|
RichardErkhov/leveldevai_-_TurdusBeagle-7B-8bits | RichardErkhov | 2024-05-19T05:39:09Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"8-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-19T05:33:53Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
TurdusBeagle-7B - bnb 8bits
- Model creator: https://huggingface.co/leveldevai/
- Original model: https://huggingface.co/leveldevai/TurdusBeagle-7B/
Original model description:
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- udkai/Turdus
- mlabonne/NeuralBeagle14-7B
---
# TurdusBeagle-7B
TurdusBeagle-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [udkai/Turdus](https://huggingface.co/udkai/Turdus)
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: udkai/Turdus
layer_range: [0, 32]
- model: mlabonne/NeuralBeagle14-7B
layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/NeuralBeagle14-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.45 # fallback for rest of tensors
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "leveldevai/TurdusBeagle-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
CMU-AIR2/math-phi-1-5-FULL-Arithmetic-lr-1.5e-6 | CMU-AIR2 | 2024-05-19T05:37:43Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-18T06:33:11Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
coolguyleo/results-200 | coolguyleo | 2024-05-19T05:37:34Z | 1 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"region:us"
] | null | 2024-05-19T05:37:29Z | ---
license: llama3
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
- name: results
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# results
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 200
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 |
CMU-AIR2/math-phi-1-5-FULL-Arithmetic-lr-1e-6 | CMU-AIR2 | 2024-05-19T05:37:21Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"phi",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-18T09:33:47Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
yzhuang/Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Korean_v2 | yzhuang | 2024-05-19T05:35:07Z | 11 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"generated_from_trainer",
"conversational",
"dataset:generator",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2024-05-17T06:42:22Z | ---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Korean_v2
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. -->
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yufanz/autotree/runs/7283881766.46478-720696f5-5799-4c26-9505-2df28e3a300e)
# Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Korean_v2
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 48
### Training results
### Framework versions
- Transformers 4.41.0
- Pytorch 2.1.0a0+32f93b1
- Datasets 2.19.1
- Tokenizers 0.19.1
|
issaccyj/lora-sdxl-dog | issaccyj | 2024-05-19T05:34:48Z | 4 | 1 | diffusers | [
"diffusers",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-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 | 2024-05-19T05:22:52Z |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: 'a sbu dog in a bucket'
output:
url:
"image_0.png"
- text: 'a sbu dog in a bucket'
output:
url:
"image_1.png"
- text: 'a sbu dog in a bucket'
output:
url:
"image_2.png"
- text: 'a sbu dog in a bucket'
output:
url:
"image_3.png"
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a sbu dog
license: openrail++
---
# SDXL LoRA DreamBooth - issaccyj/lora-sdxl-dog
<Gallery />
## Model description
These are issaccyj/lora-sdxl-dog LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
## Trigger words
You should use a sbu dog to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](issaccyj/lora-sdxl-dog/tree/main) them in the Files & versions tab.
|
RichardErkhov/leveldevai_-_TurdusBeagle-7B-4bits | RichardErkhov | 2024-05-19T05:33:20Z | 77 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2024-05-19T05:30:01Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
TurdusBeagle-7B - bnb 4bits
- Model creator: https://huggingface.co/leveldevai/
- Original model: https://huggingface.co/leveldevai/TurdusBeagle-7B/
Original model description:
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- udkai/Turdus
- mlabonne/NeuralBeagle14-7B
---
# TurdusBeagle-7B
TurdusBeagle-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [udkai/Turdus](https://huggingface.co/udkai/Turdus)
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: udkai/Turdus
layer_range: [0, 32]
- model: mlabonne/NeuralBeagle14-7B
layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/NeuralBeagle14-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.45 # fallback for rest of tensors
dtype: float16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "leveldevai/TurdusBeagle-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
|
Subsets and Splits