Creating custom configuration files in hgging face format

horseee / LLM-Pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

https://arxiv.org/abs/2305.11627

Apache License 2.0

876 stars 104 forks source link

Creating custom configuration files in hgging face format #75

Open sriyachakravarthy opened 2 months ago

sriyachakravarthy commented 2 months ago

Hi! Is it possible to save the model and create custom configuration files so that we can push to hugging face and load? Also, can PEFT be used directly from transformers library, or should we load peft.from_pretrained from this LLM-Pruner repo?