OSError: Missing model files in the Llama directory

[Cafarli]

Describe the bug

I installed the llama 2-7b model from the official Llama website and followed the instruction. But I encountered an error when trying to load the Llama model from the directory C:\Users\Admin\checkpoints\Llama-2-7b. The error message indicates that the necessary model files (pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index, or flax_model.msgpack) are not found in the specified directory.

Output

<OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory C:\Users\Admin\.llama\checkpoints\Llama-2-7b.>

Runtime Environment

• Model: llama-2-7b-chat
• Using via huggingface?: no
• OS: Windows

[PrinceAlmeida]

Even I faced the same problem when I downloaded official Llama(Meta) website llama 2-7b I got consolidated.00.pth

If you are looking for solution,
You can covert the code from .pth to .bin using the following transformer code at line 39 they have mention the steps how to load

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