Spaces:

nielsr

/

comparing-captioning-models

like 445

Running

I would like to know how to use this app locally on Windows. I have made and installed the Venv folder according to requirements.txt, but it did not install the gradio (I did that), but then I get this error when I start it:

100%|████████████████████████████████████████| 169k/169k [00:00<00:00, 512kB/s]
100%|███████████████████████████████████████| 283k/283k [00:00<00:00, 7.41MB/s]
100%|███████████████████████████████████████| 110k/110k [00:00<00:00, 5.83MB/s]
Loading the tokenizer from the `special_tokens_map.json` and the `added_tokens.json` will be removed in `transformers 5`,  it is kept for forward compatibility, but it is recommended to update your `tokenizer_config.json` by uploading it again. You will see the new `added_tokens_decoder` attribute that will store the relevant information.
Traceback (most recent call last):
  File "I:\Stable-Diffusion-Automatic\comparing-captioning-models\app.py", line 21, in <module>
    blip2_model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-opt-6.7b-coco", device_map="auto", load_in_4bit=True, torch_dtype=torch.float16)
  File "I:\Stable-Diffusion-Automatic\comparing-captioning-models\transformers\src\transformers\modeling_utils.py", line 2596, in from_pretrained
    raise ImportError(
ImportError: Using `load_in_8bit=True` requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes `pip install -i https://test.pypi.org/simple/ bitsandbytes` or pip install bitsandbytes`