运行generate.py报错：huggingface_hub.utils._validators.HFValidationError

[Harpsichord1207]

python generate.py，输出如下：

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 117
CUDA SETUP: Loading binary /home/ubuntu/CIGVicuna/venv/lib/python3.8/site-packages/bitsandbytes/libbitsandbytes_cuda117.so...
Traceback (most recent call last):
  File "generate.py", line 331, in <module>
    tokenizer = LlamaTokenizer.from_pretrained(args.model_path)
  File "/home/ubuntu/CIGVicuna/venv/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1770, in from_pretrained
    resolved_vocab_files[file_id] = cached_file(
  File "/home/ubuntu/CIGVicuna/venv/lib/python3.8/site-packages/transformers/utils/hub.py", line 409, in cached_file
    resolved_file = hf_hub_download(
  File "/home/ubuntu/CIGVicuna/venv/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 112, in _inner_fn
    validate_repo_id(arg_value)
  File "/home/ubuntu/CIGVicuna/venv/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 160, in validate_repo_id
    raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/model/13B_hf'. Use `repo_type` argument if needed.

[Facico]

@Harpsichord1207 你可以使用下面命令，将model_path 和lora_path 指定一下： python generate.py --model_path decapoda-research/llama-7b-hf --lora_path Facico/Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco --use_local 0

[Harpsichord1207]

@Facico OK了，谢谢，我以为里面默认的参数也可以运行。 另外请问一下：

1. 您给的示例命令里的Facico/Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco和lora-Vicuna/checkpoint-final是一样的吗？如果不是，哪个效果好呢？
2. 我用lora-Vicuna/checkpoint-final，上游模型选择13B来运行，会报错，目前的checkpoint都是只能在7B下运行是吗
3. generate.py和interaction.py有什么区别

谢谢~

[Facico]

里面默认参数在开发的过程中可能会换成一些本地路径，可能有时候没注意修改就传上来了，也许有时候不能直接用

• 1、是一样的，之前为了方便就直接把模型传在github上了
• 2、对，现在除了标明是13b的是用3090跑的，其他的base model都是7b然后用2080跑的
• 3、generate是单轮指令对话，interaction是多轮对话（里面的全局指令不一样），你也可以使用chat.py(chat.sh)，有更方便的接口，因为周末刚开发完还没写对应的文档。