search

sshh12 / multi_token

Embed arbitrary modalities (images, audio, documents, etc) into large language models.
Apache License 2.0
158 stars 8 forks source link

No module named 'imagebind' #21

Closed kuki2008 closed 2 weeks ago

kuki2008 commented 2 weeks ago 
Traceback (most recent call last):
  File "/content/multi_token/scripts/serve_model.py", line 31, in <module>
    model, tokenizer = load_trained_lora_model(
  File "/content/multi_token/multi_token/inference.py", line 49, in load_trained_lora_model
    modalities = MODALITY_BUILDERS[cfg.modality_builder]()
  File "/content/multi_token/multi_token/modalities/__init__.py", line 23, in <lambda>
    "imagebind": lambda: [ImageBindModality()],
  File "/content/multi_token/multi_token/modalities/imagebind.py", line 45, in __init__
    self.module = ImageBindModule()
  File "/content/multi_token/multi_token/modalities/imagebind.py", line 18, in __init__
    from imagebind.models import imagebind_model
ModuleNotFoundError: No module named 'imagebind'

Here is the full log, i was trying to run

python /content/multi_token/scripts/serve_model.py \
    --model_name_or_path mistralai/Mistral-7B-Instruct-v0.1 \
    --model_lora_path sshh12/Mistral-7B-LoRA-ImageBind-LLAVA \
    --port 7860