TheBloke/Llama-2-70B-Chat-GGUF does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

#6
by senthilknzanz - opened

llama_model = pipeline("text-generation", model="TheBloke/Llama-2-70B-Chat-GGUF", token=access_token)

for the above code, I get the following error:

OSError: TheBloke/Llama-2-70B-Chat-GGUF does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.

Facing same error using Pipeline

@swathiKonakanchi this does not work with huggingface transformers pipeline since it doesnt support gguf quanted models
use llama cpp python or ctransformers as it supports gguf models.

Sign up or log in to comment