When converting fine-tuned weights from GPTNeoX format back to HF Llama, the --architecture llama flag seems to be required (otherwise the default value "neox" would be selected.) While specified for RM conversion, this flag is not included in the command for converting GPTNeoX SFT/DPO weights back to HF in this documentation.
Quick documentation fix.
In the documentation post-training/README.md, the base weights were converted from HF Llama:
https://github.com/EleutherAI/gpt-neox/blob/59a5236ddaf721890e3d6ef98fb8ca66c2266ce0/post-training/README.md?plain=1#L6
When converting fine-tuned weights from GPTNeoX format back to HF Llama, the
--architecture llamaflag seems to be required (otherwise the default value"neox"would be selected.) While specified for RM conversion, this flag is not included in the command for converting GPTNeoX SFT/DPO weights back to HF in this documentation.https://github.com/EleutherAI/gpt-neox/blob/59a5236ddaf721890e3d6ef98fb8ca66c2266ce0/post-training/README.md?plain=1#L53-56
https://github.com/EleutherAI/gpt-neox/blob/59a5236ddaf721890e3d6ef98fb8ca66c2266ce0/tools/ckpts/convert_neox_to_hf.py#L469-L478
Fixes #1317