How to prune the embedding and lm_head?

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

880 stars 106 forks source link

How to prune the embedding and lm_head? #55

Open L-hongbin opened 8 months ago