search

modelscope / ms-swift

Use PEFT or Full-parameter to finetune 400+ 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
4.38k stars 385 forks source link

【没有llama3.2-11b-vision最佳实践】 #2442

Open LixiangHello opened 1 week ago

LixiangHello commented 1 week ago

自定义数据集

1.视觉多模态数据集格式只有 视觉多模态大模型（DPO/ORPO/SimPO/CPO） 2.最佳实践中没有llama3.2-11/90B的微调demo image

Jintao-Huang commented 1 week ago

https://github.com/modelscope/ms-swift/issues/2133

LixiangHello commented 1 week ago

ms-swift 看样子不太愿意支持llama3.2-v系列模型，建议使用 https://github.com/2U1/Llama3.2-Vision-Finetune 微调👍

Jintao-Huang commented 1 week ago

数据集格式都是通用的，其实看qwen2_vl的就好了