Missing pytorch_model.bin?
Am I using this model incorrectly? I try downloading it using a call from AutoModel and get the following error:
Traceback (most recent call last):
File "/home/winson/projects/gpt/redpajama.cpp/examples/redpajama/scripts/./convert_gptneox_to_ggml.py", line 62, in
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16 if ftype == 1 else torch.float32,
File "/home/winson/miniconda3/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 471, in from_pretrained
return model_class.from_pretrained(
File "/home/winson/miniconda3/lib/python3.10/site-packages/transformers/modeling_utils.py", line 2511, in from_pretrained
raise EnvironmentError(
OSError: keldenl/RedPajama-INCITE-Chat-3B-v1-GGML does not appear to have a file named pytorch_model.bin, tf_model.h5, model.ckpt or flax_model.msgpack.
This model is supposed to be used with a llama.cpp like implementation. Not with transformers library, but a C++ implementation. You can try redpajama.cpp?