Sciphi Mistral 7B 32k

🚀 SciPhi-Mistral-7B-32k模型卡片

SciPhi-Mistral-7B-32k是一个基于Mistral-7B-v0.1微调的大语言模型（LLM）。该模型使用超过10亿个标记进行了四个周期的微调，这些标记包括常规的指令调优数据和合成教科书。这项工作的目标是提高模型的科学推理和教育能力。为获得最佳效果，请遵循Alpaca提示指南。

SciPhi-AI可通过免费的托管API使用，不过暴露的模型可能会有所不同。目前，可使用SciPhi-Self-RAG-Mistral-7B-32k。更多详细信息可在文档中找到。

✨ 主要特性

• 模型架构：基于Mistral-7B-v0.1，具有Transformer架构、分组查询注意力、滑动窗口注意力和字节回退BPE分词器等特性。
• 微调优化：使用超过10亿个标记进行四个周期的微调，提升科学推理和教育能力。
• API支持：可通过免费的托管API使用。

📦 安装指南

文档未提及安装步骤，跳过该章节。

💻 使用示例

基础用法

# 推荐的聊天格式示例
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]

# 转换为以下格式
# 系统提示
print("### System:")
print("You are a friendly chatbot who always responds in the style of a pirate")
# 指令
print("### Instruction:")
print("How many helicopters can a human eat in one sitting?")
# 响应
print("### Response:")
print("...")

📚 详细文档

模型架构

推荐的聊天格式

我们推荐将以下格式：

messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]

转换为：

### System:
You are a friendly chatbot who always responds in the style of a pirate

### Instruction:
How many helicopters can a human eat in one sitting?

### Response:
...

参考文献

1. Lian, W., Goodson, B., Wang, G., Pentland, E., Cook, A., Vong, C., & Teknium. (2023). MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset. HuggingFace repository. 链接
2. Mukherjee, S., Mitra, A., Jawahar, G., Agarwal, S., Palangi, H., & Awadallah, A. (2023). Orca: Progressive Learning from Complex Explanation Traces of GPT-4. arXiv预印本 arXiv:2306.02707.
3. Longpre, S., Hou, L., Vu, T., Webson, A., Chung, H. W., Tay, Y., Zhou, D., Le, Q. V., Zoph, B., Wei, J., & Roberts, A. (2023). The Flan Collection: Designing Data and Methods for Effective Instruction Tuning. arXiv预印本 arXiv:2301.13688.
4. Mistral AI. (2023). Model Card for Mistral-7B-v0.1. The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks tested. For full details, please refer to the paper and release blog post. Model Architecture: Transformer with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer. 链接

致谢

感谢AI Alignment Lab、vikp、jph00以及其他为这项工作做出贡献的人。

📄 许可证

本项目采用MIT许可证。