huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: ''.

[WildLight]

hi, I meet the error following:

Traceback (most recent call last):
  File "blip2_instructed_generation.py", line 30, in <module>
    model, vis_processors, _ = load_model_and_preprocess(
  File "/public/xx/tvqa_test/LAVIS-main/lavis/models/__init__.py", line 205, in load_model_and_preprocess
    model = model_cls.from_pretrained(model_type=model_type)
  File "/public/xx/tvqa_test/LAVIS-main/lavis/models/base_model.py", line 70, in from_pretrained
    model = cls.from_config(model_cfg)
  File "/public/xx/tvqa_test/LAVIS-main/lavis/models/blip2_models/blip2_vicuna_instruct.py", line 715, in from_config
    model = cls(
  File "/public/xx/tvqa_test/LAVIS-main/lavis/models/blip2_models/blip2_vicuna_instruct.py", line 90, in __init__
    self.llm_tokenizer = LlamaTokenizer.from_pretrained(llm_model, use_fast=False, truncation_side="left")
  File "/root/anaconda/envs/instructblip/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1813, in from_pretrained
    resolved_vocab_files[file_id] = cached_file(
  File "/root/anaconda/envs/instructblip/lib/python3.8/site-packages/transformers/utils/hub.py", line 429, in cached_file
    resolved_file = hf_hub_download(
  File "/root/anaconda/envs/instructblip/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 111, in _inner_fn
    validate_repo_id(arg_value)
  File "/root/anaconda/envs/instructblip/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 165, in validate_repo_id
    raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: ''.

I use the code following from here: https://github.com/salesforce/LAVIS/tree/main/projects/instructblip

import torch
from PIL import Image
# setup device to use
device = torch.device("cuda") if torch.cuda.is_available() else "cpu"
# load sample image
raw_image = Image.open("../../docs/_static/Confusing-Pictures.jpg").convert("RGB")
display(raw_image.resize((596, 437)))
from lavis.models import load_model_and_preprocess
# loads InstructBLIP model
model, vis_processors, _ = load_model_and_preprocess(name="blip2_vicuna_instruct", model_type="vicuna7b", is_eval=True, device=device)
# prepare the image
image = vis_processors["eval"](raw_image).unsqueeze(0).to(device)

the version of me conda following:

torch                     2.0.1
salesforce-lavis          1.0.1
transformers              4.33.2

so how can I solve it? please help me, thank you!