Trying to install MiniGPT-4 locally->

[Peter Swinkels]

Hello,

After installing Python 3.11.3 (64-bit) I downloaded the code for MiniGPT-4 at https://github.com/Vision-CAIR/MiniGPT-4.

After that I ran the following commands to install all dependencies I am aware of:

C:\Users\...\AppData\Local\Programs\Python\Python311\python.exe -m pip install --upgrade pip
pip install decord
pip install gradio
pip install iopath
pip install numpy
pip install omegaconf
pip install opencv-python
pip install sentencepiece
pip install timm
pip install torch
pip install torchvision
pip install transformers
pip install webdataset

When all that has been done I get the folllowing error when trying to launch MiniGPT-4 using "C:\Users\...\AppData\Local\Programs\Python\Python311\python demo.py --cfg-path eval_configs/minigpt4_eval.yaml --gpu-id 0":

Initializing Chat
Loading VIT
Loading VIT Done
Loading Q-Former
Loading Q-Former Done
Loading LLAMA
Traceback (most recent call last):
  File "D:\Other\MiniGPT-4-main\demo.py", line 60, in <module>
    model = model_cls.from_config(model_config).to('cuda:{}'.format(args.gpu_id))
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Other\MiniGPT-4-main\minigpt4\models\mini_gpt4.py", line 243, in from_config
    model = cls(
            ^^^^
  File "D:\Other\MiniGPT-4-main\minigpt4\models\mini_gpt4.py", line 86, in __init__
    self.llama_tokenizer = LlamaTokenizer.from_pretrained(llama_model, use_fast=False)
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\peter\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\tokenization_utils_base.py", line 1771, in from_pretrained
    resolved_vocab_files[file_id] = cached_file(
                                    ^^^^^^^^^^^^
  File "C:\Users\peter\AppData\Local\Programs\Python\Python311\Lib\site-packages\transformers\utils\hub.py", line 417, in cached_file
    resolved_file = hf_hub_download(
                    ^^^^^^^^^^^^^^^^
  File "C:\Users\peter\AppData\Local\Programs\Python\Python311\Lib\site-packages\huggingface_hub\utils\_validators.py", line 112, in _inner_fn
    validate_repo_id(arg_value)
  File "C:\Users\peter\AppData\Local\Programs\Python\Python311\Lib\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': '/path/to/vicuna/weights/'. Use `repo_type` argument if needed.
D:\Other\MiniGPT-4-main>

Searching MiniGPT-4.pdf for the term "LLAMA" leads me to this paragraph:

[30] Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang,
and Tatsunori B. Hashimoto. Stanford alpaca: An instruction-following llama model. https://github.
com/tatsu-lab/stanford_alpaca, 2023.

Does anyone know whether this "stanford-alpaca" is what is missing or whether it is what "LLAMA" is based on?

In short what dependency is missing and how do I install it?

Thanks in advance. :-)