README.md

---
language:
- en
tags:
- causal-lm
license: cc-by-nc-4.0
datasets:
- dmayhem93/ChatCombined
- tatsu-lab/alpaca
- nomic-ai/gpt4all_prompt_generations
- Dahoas/full-hh-rlhf
- jeffwan/sharegpt_vicuna
- HuggingFaceH4/databricks_dolly_15k
---

# StableLM-Tuned-Alpha

## Model Description

`StableLM-Tuned-Alpha` is a suite of 3B and 7B parameter decoder-only language models built on top of the `StableLM-Base-Alpha` models and further fine-tuned on various chat and instruction-following datasets.

## Usage

Get started chatting with `StableLM-Tuned-Alpha` by using the following code snippet:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("StabilityAI/stablelm-tuned-alpha-3b")
model = AutoModelForCausalLM.from_pretrained("StabilityAI/stablelm-tuned-alpha-3b")
model.half().cuda()

inputs = tokenizer("What's your mood today?", return_tensors="pt").to("cuda")
tokens = model.generate(
  **inputs,
  max_new_tokens=64,
  temperature=0.7,
  do_sample=True,
)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))
```

## Model Details

* **Developed by**: [Stability AI](https://stability.ai/)
* **Model type**: StableLM-Tuned-Alpha models are auto-regressive language models based on the NeoX transformer architecture.
* **Language(s)**: English
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
* **License**: [CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/)
* **Contact**: For questions and comments about the model, please email {TODO: email address}

## Training

| Parameters | Hidden Size | Layers | Heads | Sequence Length |
|------------|-------------|--------|-------|-----------------|
| 3B         | 4096        | 16     | 32    | 4096            |
| 7B         | 6144        | 16     | 48    | 4096            |

### Training Dataset

`StableLM-Tuned-Alpha` models are fine-tuned on a combination of five datasets:
[Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), a dataset of 52,000 instructions and demonstrations generated by OpenAI's `text-davinci-003` engine.
[GPT4All Prompt Generations](https://huggingface.co/datasets/nomic-ai/gpt4all_prompt_generations), which consists of 400k prompts and responses generated by GPT-4;
[Anthropic HH](https://huggingface.co/datasets/Dahoas/full-hh-rlhf), made up of preferences about AI assistant helpfulness and harmlessness;
[DataBricks Dolly](https://github.com/databrickslabs/dolly), comprising 15k instruction/responses generated by Databricks employees in capability domains from the InstructGPT paper, including brainstorming, classification, closed QA, generation, information extraction, open QA and summarization;
and [ShareGPT Vicuna (English subset)](https://huggingface.co/datasets/jeffwan/sharegpt_vicuna), a dataset of conversations retrieved from [ShareGPT](https://sharegpt.com/).

### Training Procedure

Models are learned via supervised fine-tuning on the aforementioned datasets, trained in mixed-precision (FP16), and optimized with AdamW. We outline the following hyperparameters:

| Parameters | Batch Size | Learning Rate | Warm-up | Weight Decay | Betas       |
|------------|------------|---------------|---------|--------------|-------------|
| 3B         | 256        | 2e-5          | 50      | 0.01         | (0.9, 0.99) |
| 7B         | 128        | 2e-5          | 100     | 0.01         | (0.9, 0.99) |

## Use and Limitations

### Intended Use

These models are intended to be used by the open-source community chat-like applications in adherence with the [CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.

### Limitations and bias

Although the aforementioned datasets help to steer the base language models into "safer" distributions of text, not all biases and toxicity can be mitigated through fine-tuning. We ask that users be mindful of such potential issues that can arise in generated responses. Do not treat model outputs as substitutes for human judgment or as sources of truth. Please use responsibly.

## Acknowledgements

This work would not have been possible without the helpful hand of Dakota Mahan ([@dmayhem93](https://huggingface.co/dmayhem93)).

## Citations

```bibtex
@misc{alpaca,
  author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
  title = {Stanford Alpaca: An Instruction-following LLaMA model},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}
```

```bibtext
@misc{vicuna2023,
    title = {Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality},
    url = {https://vicuna.lmsys.org},
    author = {Chiang, Wei-Lin and Li, Zhuohan and Lin, Zi and Sheng, Ying and Wu, Zhanghao and Zhang, Hao and Zheng, Lianmin and Zhuang, Siyuan and Zhuang, Yonghao and Gonzalez, Joseph E. and Stoica, Ion and Xing, Eric P.},
    month = {March},
    year = {2023}
}
```

```bibtex
@misc{gpt4all,
  author = {Yuvanesh Anand and Zach Nussbaum and Brandon Duderstadt and Benjamin Schmidt and Andriy Mulyar},
  title = {GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/nomic-ai/gpt4all}},
}
```