preprocessor_config.json Not Found for Model liuhaotian/llava-v1.6-mistral-7b

[Safdari10]

Describe the issue

Issue: I am trying to load the LLaVA model liuhaotian/llava-v1.6-mistral-7b using the LlavaProcessor from the transformers library. However, I am encountering a 404 Client Error because the file preprocessor_config.json is not found at the specified URL.

Command:

import torch
from PIL import Image
from transformers import LlavaProcessor, LlavaForConditionalGeneration

model_name = "liuhaotian/llava-v1.6-mistral-7b"

try:
    processor = LlavaProcessor.from_pretrained(model_name, trust_remote_code=True)
    model = LlavaForConditionalGeneration.from_pretrained(model_name, trust_remote_code=True)
    print("Model loaded successfully.")
except Exception as e:
    print(f"Error loading model: {e}")

Log:

Traceback (most recent call last):
  File "C:\Users\safda\AppData\Local\Programs\Python\Python313\Lib\site-packages\huggingface_hub\utils\_http.py", line 406, in hf_raise_for_status
    response.raise_for_status()
  File "C:\Users\safda\AppData\Local\Programs\Python\Python313\Lib\site-packages\requests\models.py", line 1024, in raise_for_status
    raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b/resolve/main/preprocessor_config.json

...

OSError: liuhaotian/llava-v1.6-mistral-7b does not appear to have a file named preprocessor_config.json. Checkout 'https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b/tree/main' for available files.

Steps to Reproduce:

Install the necessary libraries:

pip install torch sentencepiece accelerate
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/haotian-liu/LLaVA.git

Run the provided code snippet.

Expected Behavior: The model should load successfully without any errors.

Actual Behavior: A 404 Client Error is raised because the file preprocessor_config.json is not found.

Additional Context: I have verified that the model name and URL are correct. Any guidance on resolving this issue would be greatly appreciated.