---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
inference: false
thumbnail: >-
  https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
---
# Model Card



## Training Dataset

` mamba-gpt-7b ` is trained on multiple datasets:
  - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca)
  - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1)
  - [LIMA (en)](https://huggingface.co/datasets/GAIR/lima)
  - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k)
  - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM)
  - [UltraChat (en)](https://github.com/thunlp/UltraChat)


## Summary

We have fine-tuned the OpenLLaMA model and surpassed the original model in multiple evaluation subtasks, making it currently one of the best performing 3B model, with comparable performance to llama-7b.
- Base model: [openlm-research/open_llama_7b_v2](https://huggingface.co/openlm-research/open_llama_7b_v2)


## Usage

To use the model with the `transformers` library on a machine with GPU(s), first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.

Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.

Then, run the following Python snippet:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CobraMamba/mamba-gpt-7b-v1")
model = AutoModelForCausalLM.from_pretrained("CobraMamba/mamba-gpt-7b-v1", trust_remote_code=True, torch_dtype=torch.float16)

input_content = "Your text here"
input_ids = tokenizer.encode(input_content, return_tensors="pt")
output = model.generate(input_ids, max_length=128, temperature=0.7)
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(output_text)

```


## Citation

If this work is helpful, please kindly cite as:

```bibtex
@Misc{mamba-gpt-7b-v1,
  title = {Mamba-GPT-7b-v1},
  author = {chiliu},
  howpublished = {\url{https://huggingface.co/CobraMamba/mamba-gpt-7b-v1}},
  year = {2023}
}
```


## Disclaimer

Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.

- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.

---
license: apache-2.0
---

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_CobraMamba__mamba-gpt-7b-v1)

| Metric                | Value                     |
|-----------------------|---------------------------|
| Avg.                  | 54.77   |
| ARC (25-shot)         | 61.26          |
| HellaSwag (10-shot)   | 84.1    |
| MMLU (5-shot)         | 63.46         |
| TruthfulQA (0-shot)   | 46.34   |
| Winogrande (5-shot)   | 79.16   |
| GSM8K (5-shot)        | 17.36        |
| DROP (3-shot)         | 31.67         |