This guide provides instructions on how to use the conversion scripts to convert models between Community model and NVIDIA’s NeMo format.
Conversion |
From |
To |
Github Link |
---|---|---|---|
Baichuan | Hugging Face | NeMo | Link |
Baichuan | NeMo | Hugging Face | Link |
BERT | Hugging Face | NeMo | Link |
BERT | NeMo | Hugging Face | Link |
Falcon | Hugging Face | NeMo | Link |
Falcon | NeMo | Hugging Face | Link |
Gemma | Hugging Face | NeMo | Link |
Gemma | JAX | NeMo | Link |
Gemma | PyTorch | NeMo | Link |
GPT/LLaMA | NeMo (Legacy) | NeMo (Megatron-Core) | Link |
LLaMA | Hugging Face | NeMo | Link |
LLaMA | NeMo | Hugging Face | Link |
Mistral 7B | Hugging Face | NeMo | Link |
Mistral 7B | NeMo | Hugging Face | Link |
Mixtral | Hugging Face | NeMo | Link |
Mixtral | NeMo | Hugging Face | Link |
MPT | Hugging Face | NeMo | Link |
Starcoder | Hugging Face | NeMo | Link |
To convert a Hugging Face LLaMA checkpoint into a NeMo checkpoint, use the following command:
python convert_llama_hf_to_nemo.py>`_ \
--input_name_or_path <path_to_hf_checkpoints_folder> \
--output_path <path_to_output_nemo_file>
To convert a NeMo checkpoint into a Hugging Face LLaMA checkpoint, you have two options:
Generate only the Hugging Face weights:
python convert_<model>_nemo_to_hf.py>`_ \
--input_name_or_path /path/to/file.nemo or /path/to/extracted_folder \
--output_path /path/to/pytorch_model.bin
Generate the full Hugging Face model folder:
python convert_<model>_nemo_to_hf.py>`_ \
--input_name_or_path /path/to/file.nemo or /path/to/extracted_folder \
--output_path /path/to/model_folder \
--hf_input_path /path/to/input_hf_folder \
--hf_output_path /path/to/output_hf_folder
Replace <model> with the specific model you are converting.
Use the --cpu-only
flag if the model cannot fit in the GPU, such as for Llama2 70b models. Note that using this option will significantly slow down the conversion process.
--input_name_or_path
: Path to the input .nemo file or the Hugging Face model folder.--output_path
: Path to the output file or folder, depending on the conversion direction.--hf_input_path
: (Optional) Path to the input Hugging Face model folder.--hf_output_path
: (Optional) Path to the output Hugging Face model folder.