qresearch

/

llama-3-vision-alpha

like 60

Tried on both python 3.11 and 3.12

Run:

pip install torch transformers bitsandbytes accelerate
pip install pillow
python __main__.py -I file.png

results in:

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
  File "/Users/mikolajboronski/github/minecraft/llama-3-vision-alpha/__main__.py", line 209, in <module>
    tokenizer, model, vision_model, processor = initialize_models()
                                                ^^^^^^^^^^^^^^^^^^^
  File "/Users/mikolajboronski/github/minecraft/llama-3-vision-alpha/__main__.py", line 64, in initialize_models
    model = LlamaForCausalLM.from_pretrained(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/mikolajboronski/miniconda3/envs/mc/lib/python3.11/site-packages/transformers/modeling_utils.py", line 3165, in from_pretrained
    hf_quantizer.validate_environment(
  File "/Users/mikolajboronski/miniconda3/envs/mc/lib/python3.11/site-packages/transformers/quantizers/quantizer_bnb_4bit.py", line 62, in validate_environment
    raise ImportError(
ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes: `pip install -i https://pypi.org/simple/ bitsandbytes`

Tried reinstalling both accelerate and bitsandbytes -- didnt help. Can you please provide a requirements.txt so I can try with hardcoded versions?