It would ease the model usage if the weights of large (>1B) models were available in .safetensors.
Motivation
As for now, it takes ~1 hour to download unbabel/*-xxl models on A100. It can be resolved with other formats for model weights.
The safetensors format is faster than the Pytorch ones, as stated here: https://huggingface.co/docs/safetensors/en/speed.
Additional context
It seems that safetensors support would require:
converting the weights for published models (i.e. save_model from safetensors.torch)
support within the classes, for example, new function for loading safetensors in class CometModel
🚀 Feature
It would ease the model usage if the weights of large (>1B) models were available in
.safetensors
.Motivation
As for now, it takes ~1 hour to download
unbabel/*-xxl
models on A100. It can be resolved with other formats for model weights. The safetensors format is faster than the Pytorch ones, as stated here: https://huggingface.co/docs/safetensors/en/speed.Additional context
It seems that
safetensors
support would require:save_model
fromsafetensors.torch
)class CometModel
load_from_checkpoint