Error no file named pytorch_model.bin, model.safetensors

[morbidod]

Hello,

I successfully downloaded the model to this directory /root/.llama/checkpoints/Llama3.2-1B-Instruct
When I launch the AutoModelForCausalLM.from_pretrained passing the path above I got the following error:

OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /root/.llama/checkpoints/Llama3.2-1B-Instruct.

(AutomodelForCasualLM is from latest transformers library (pip install -U transformers).

Thanks in advance for any suggestion.

[LennyxDxDxD]

metoo

[ShanthiniMichael]

Have you found any solution? I am also facing the same issue

[Brandonio-c]

You need to convert the model to a huggingface-appropriate format.

See:
https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py