horseee/LLM-Pruner

Issues

• Llama3 reports shape error after pruning

  #69 opened a month ago by WentaoTan
  5

• evaluate PPL with the post-training model

  #79 opened 11 days ago by VincentZ-2020
  0

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

  #66 opened 2 months ago by wangxiaoxue
  3

• No such file or directory: pytorch_model.bin

  #74 opened a month ago by yaolu-zjut
  2

• 关于consecutive_groups

  #78 opened 16 days ago by VincentZ-2020
  0

• UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1

  #77 opened 20 days ago by BrownTan
  4

• 延迟评估

  #50 opened 8 months ago by qxpBlog
  4

• OSError: Can't load tokenizer for 'baffo32/decapoda-research-llama-7B-hf'.

  #47 opened 8 months ago by qxpBlog
  2

• I tired Mistral 7b model, but I got this issue

  #56 opened 6 months ago by TejasLidhure
  0

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

  #63 opened 3 months ago by hebowei2000
  3

• RecursionError: maximum recursion depth exceeded

  #53 opened 6 months ago by Zhenyu001225
  2

• Evaluation：UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte

  #58 opened 5 months ago by manlenzzz
  1

• Taylor pruner under-utilizing resources

  #76 opened a month ago by marianbasti
  0

• Creating custom configuration files in hgging face format

  #75 opened a month ago by sriyachakravarthy
  0

• Does it support qwen2?

  #71 opened a month ago by yangxue-1
  1

• Issue: Missing Generation of `pytorch_model.bin` File During Model Tuning

  #45 opened 9 months ago by WilliamYi96
  5

• Can the pruned model be converted into a gguf file？

  #73 opened a month ago by pxrgod
  0

• Custom Model pruning

  #72 opened a month ago by saidineshpola
  0

• ConnectionError: Couldn't reach https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.train.txt (ReadTimeout(ReadTimeoutError("HTTPSConnectionPool(host='raw.githubusercontent.com', port=443): Read timed out. (read timeout=100)")))

  #48 opened 8 months ago by qxpBlog
  2

• Loading pruned model for causal llm

  #68 opened a month ago by sriyachakravarthy
  0

• Adaptation of GQA

  #64 opened 2 months ago by junzhang-zj
  7

• 请问能裁剪普通的transformer模型吗

  #62 opened 3 months ago by SKY072410
  0

• 请问可以支持chatglm3剪枝吗

  #61 opened 3 months ago by Franklin-L
  0

• Difference in Perplexity Values

  #60 opened 4 months ago by nikhil-ghosh-berkeley
  0

• No random seed Settings found in post_training.py

  #59 opened 5 months ago by JunKong5
  0

• Pruning llama3

  #57 opened 5 months ago by yinwangsong
  0

• Is this method implementable on multi-GPUs?

  #54 opened 6 months ago by LeonCheng0129
  0

• How to prune the embedding and lm_head?

  #55 opened 6 months ago by L-hongbin
  0

• Unable to reproduce the results for param_first and param_second in the paper after finetuning.

  #52 opened 8 months ago by danyal97
  0

• 剪枝率值的问题

  #51 opened 8 months ago by qxpBlog
  0

• a post-training issue

  #35 opened 10 months ago by cmnfriend
  2

• The quantization of the compressed models

  #49 opened 8 months ago by lihuang258
  0

• Cannot use huggface to load

  #46 opened 9 months ago by coderchem
  0

• 401 Client Error: Unauthorized for url: https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer_config.json

  #43 opened 9 months ago by azuryl
  1

• cannot import name 'SiLUActivation' from 'transformers.activations'

  #44 opened 9 months ago by azuryl
  1

• Latency code

  #33 opened 10 months ago by tuidan
  2

• Supporting device_map = 'auto' similar to the one in .from_pretrained method from Huggingface

  #36 opened 10 months ago by Ahmed-Roushdy
  3

• the new pytorch.bin is bigger than original model issue

  #37 opened 10 months ago by lb553024300
  4

• Question related to the model tuning

  #39 opened 10 months ago by shawnricecake
  2

• Adding a tutorial for adapting new models?

  #42 opened 10 months ago by zhichaoxu-shufe
  0

• 在将部分层进行剪枝之后，不能直接通过tgi加载模型

  #41 opened 10 months ago by coderchem
  0

• Pruning MQA?

  #40 opened 10 months ago by jianyuheng
  0

• 为什么num_examples默认是10？

  #38 opened 10 months ago by coderchem
  2

• Reproducing paper results

  #34 opened 10 months ago by grigorn
  6

• Can not import LlamaConfig

  #32 opened a year ago by Ahmed-Roushdy
  1

• Examples on the Huggingface Hub

  #31 opened a year ago by vgoklani
  0

• When will you support ChatGLM?

  #30 opened a year ago by AboveParadise
  0

• Force even pruning across layers

  #29 opened a year ago by thedarkzeno
  1

• Calculating Importance of 'param_mix'

  #28 opened a year ago by kiucho
  2

• When would the code for GPT-J-6B be released?

  #27 opened a year ago by mumuyeye
  1