microsoft

/

llava-med-v1.5-mistral-7b

like 83

Follow

Microsoft 11.2k

Every time I run this code:
tokenizer, model, image_processor, context_len = load_pretrained_model(
model_path="path/to/your/model",
model_base=None,
model_name="llava-mistral",
load_4bit=True
)

I get an error that says:
raise ValueError(f"{tensor_name} is on the meta device, we need a value to put in on {device}.")
ValueError: weight is on the meta device, we need a value to put in on 0.