Files
firefly-llama-13b/README.md
ModelHub XC 26a2940b84 初始化项目,由ModelHub XC社区提供模型
Model: YeungNLP/firefly-llama-13b
Source: Original Platform
2026-06-08 21:09:19 +08:00

22 lines
1.8 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

该模型使用llama-13b使用UltraChat数据集进行指令微调约140万多轮对话数据。仅需一张显卡即可完成训练。
firefly-llama-13b在🤗Hugging Face的Open LLM榜单上进行了客观的评测。
在榜单上firefly-llama-13b取得了不错的效果比vicuna-13b-1.1略高0.2分比llama-2-13b-chat略低0.5分比vicuna-13b-v1.3略低0.6分。从评测分数来看firefly-llama-13b与vicuna-13b、llama-2-13b-chat的水平非常接近😎。
| 模型 | Average | ARC | HellaSwag | MMLU | TruthfulQA (MC) |
|--------------------------------------------------------------------------------|-------|----------------------|------------|------------|------|
| Llama-2-70b-chat-hf | 66.8 | 64.6 | 85.9 | 63.9 | 52.8 |
| vicuna-13b-v1.3 | 60 | 54.6 | 80.4 | 52.9 | 52.1 |
| Llama-2-13b-chat-hf | 59.9 | 59 | 81.9 | 54.6 | 44.1 |
| firefly-llama-13b |59.4 | 59 | 79.7 | 49.1 | 49.6 |
| vicuna-13b-1.1 | 59.2 | 52.7 | 80.1 |51.9 | 52.1 |
| guanaco-13B-HF | 59.1 | 57.8 | 83.8 |48.3 | 46.7|
值得注意的是vicuna-13b模型采用的是全量参数微调对训练资源的要求十分高。而firefly-llama-13b采用的则是QLoRA微调最少仅需16G显存即可对13B的模型进行微调。
详细介绍见文章:[Firefly单卡复刻Vicuna-13BOpen LLM榜单🤗略高0.2分](https://mp.weixin.qq.com/s/QG2YMo_QxaxS_Rr2yJrIeA)
更多详情见[Firefly项目](https://github.com/yangjianxin1/Firefly)
[Open LLM排行榜](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)