I’ve read the model repo community you referred to, and it seems like there’s a real possibility that they’re missing some files.
just wait. I assume they’re US based - so depending on their loc their work week just starts or is going to start. And probably over the weekend there is a number of requests gathering up to be checked.
And there’s always possibility that the responsible person isn’t around on day
You could do it by making the code look like this.
hi @sanchitamore
This should work. In fact, if you log in, you don’t even need token parameter.
from transformers import pipeline
class LLM:
def __init__(self, model_name, auth_token=None):
self.model = pipeline('text2text-generation', model=model_name)
def predict(self, prompt, **kwargs):
return self.model(text_inputs=prompt, **kwargs)[0]["generated_text"]
model = LLM(model_name="mistralai/Mistral-7B-Instruct-v0.3")
Can you please run huggingface-cli whoami and do…
In that case, there is nothing we can do.