Kwok Wai Lok comments

Repositories
Issues
Comments

Results 2 comments of


                                            Kwok Wai Lok

Lora微调后要怎么加载测试呢？

from peft import AutoPeftModelForCausalLM import torch from chat import MiniCPMVChat, img2base64 import json path_to_adapter="xxxxxx/output_minicpmv2_lora/checkpoint-200" model = AutoPeftModelForCausalLM.from_pretrained( # path to the output directory path_to_adapter, device_map="cuda:0", trust_remote_code=True ).eval() vpm_resampler_embedtokens_weight = torch.load(f"{path_to_adapter}/vpm_resampler_embedtokens.pt")...

[BUG] <title> finetune/dataset.py 有bug

same problem, does this problem have a solution?