LLM-Pruner

LLM-Pruner copied to clipboard

recover training

1

when I start recover training Baichuan-7B, I meet the bug. Exception has occurred: RuntimeError Caught RuntimeError in replica 1 on device 1. Original Traceback (most recent call last): File "/opt/miniconda3/envs/flash/lib/python3.9/site-packages/torch/nn/parallel/parallel_apply.py",...

xcg940123

Can prune model convert to llama.cpp ggml？

1

shaonianyr

hi, Does post_training support full parameter fine-tuning of the pruned model？

1

StevensPrime

When would the code for ChatGLM be released?

1

Thanks a lot for your work on compression on LLMs, and looking forward for the code for ChatGLM. When would it be available for GLMs?

moonlightian

There are no random seed settings in post_training.py. Did the results in the paper use a random seed setting? I look forward to your reply. Thank you very much!

JunKong5

Adaptation of GQA

7

Thank you for your solid work. I would like to ask if the current version is suitable for GQA architecture models, such as LLaMA-2-70B and LLaMA-3.

junzhang-zj

Update hf_prune.py

1

Added Model on CUDA.

aritralegndery

I would like to ask if the current version is suitable for qwen.

3

I would like to ask if the current version is suitable for qwen.

wangxiaoxue

No pytorch_model.bin file in the tune_log/llama_0.2/checkpoint-200 folder

3

Hi, I run the code successfully but find that there does not exist the pytorch_model.bin in the tune_log/llama_0.2/checkpoint-200 folder. May I ask the possible reasons or have you encountered this...

hebowei2000

SKY072410