convert huggingface model to megatron. "Only llama v2 available using huggingface"

[uygnef]

Hi @AleHD

When I run this script:

python weights2megatron/weights2megatron.py llama --size=7

--out=/path/to/megatron/weights/ --cache-dir=/path/to/llama-7b/

It says:

assert version == 2, "Only llama v2 available using huggingface" Does this script not support Llama v1?

[AleHD]

At the moment you need to specify the cache directory to the weights given officialy by meta. We are working on using decapoda-research llama implementation to retrieve the weights automatically with huggingface.