LLM-Pruner
LLM-Pruner copied to clipboard
horseee
[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.
if it has, how can we convert? wait for your reply. thanks
How to fix this error for custom model pruning? The pruning was done but some layers weren't pruned properly. I got this error at the time of inference ` key_states...
Hi! While loading the pruned model (using this llm pruner) how do we load the model which will result in equivalent loading like AutoModelforCausalLlm as in hugging face transformers?
