search

modelscope / ms-swift

Use PEFT or Full-parameter to finetune 350+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)
https://swift.readthedocs.io/zh-cn/latest/Instruction/index.html
Apache License 2.0
4.01k stars 355 forks source link

sft_args.json中system #2314

Closed CASIA-YOUTONG closed 4 days ago

CASIA-YOUTONG commented 6 days ago

我构建的数据是{"system":..,"query":...,"response":...} 进行训练，但是sft_args.json中system为 "system": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.", 并不是我训练数据的system. 我感觉这是一个显示错误，并不影响我的训练效果。请问是这样吗？

Jintao-Huang commented 5 days ago

fixed https://github.com/modelscope/ms-swift/pull/2307