OSError: TheBloke/Llama-2-7B-Chat-GGML does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.
#39
by
SJay747
- opened
I run the following code and am getting the error in title:
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML")
I am new to HuggingFace so please go easy. What am I doing wrong and how do I fix it?
@SJay747 well ggml is an Outdated format that doesn’t work and you should use gguf format instead. you have to use llama.cpp or ctransformers or llama cpp python to run it.