ChatGLM2-6B:https://github.com/THUDM/ChatGLM2-6B
模型地址:https://huggingface.co/THUDM/chatglm2-6b
详细步骤同:ChatGLM-6B的P-Tuning微调详细步骤及结果验证
环境可复用ChatGLM-6B(上述部署教程),即
Python 3.8.10
CUDA Version: 12.0
torch 2.0.1
transformers 4.27.1
注:ChatGLM2-6B官网给的环境P-Tuning微调报错
AttributeError: ‘Seq2SeqTrainer’ object has no attribute 'is_deepspeed_enabl
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: