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, ...)
4.01k
stars
355
forks
source link
求助微调glm4v9b的OCR功能时,自定义数据集无法正常训练 #2333
Open
meng0423 opened 3 days ago
自定义数据集格式如上,训练时loss迅速变成0,如下图,求帮助,谢谢!