单卡评价时候出错

[LiZhangMing]

CUDA_VISIBLE_DEVICES=0 python src/train_sft.py --do_eval --dataset example --checkpoint_dir path_to_checkpoint --output_dir path_to_eval_result --per_device_eval_batch_size 8 --max_samples 50 --predict_with_generate

报错为： 06/25/2023 09:10:02 - INFO - utils.common - Fine-tuning method: LoRA Traceback (most recent call last): File "/home/lizhangming/anaconda3/envs/chatglm_etuning/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 259, in hf_raise_for_status response.raise_for_status() File "/home/lizhangming/anaconda3/envs/chatglm_etuning/lib/python3.10/site-packages/requests/models.py", line 1021, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/path_to_checkpoint/resolve/main/adapter_config.json

[hiyouga]

检查一下保存 lora 权重文件夹的路径是否正确提供到 --checkpoint_dir 参数

[LiZhangMing]

检查一下保存 lora 权重文件夹的路径是否正确提供到 --checkpoint_dir 参数 谢谢您， 还有个小问题哈，就是执行完这个的时候 python src/cli_demo.py --checkpoint_dir path_to_checkpoint 在终端测试的时候，用户输入能不能长一点，我发现他会把我的一些内容截断。