IST-DASLab sparsegpt issues

IST-DASLab / sparsegpt

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

https://arxiv.org/abs/2301.00774

Apache License 2.0

727 stars 97 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Update bloom.py

#42 Varun-2103 closed 1 month ago
0
Update csv bloom.py

#41 Varun-2103 closed 1 month ago
0
Delete demo.ipynb

#40 raccoonxxi closed 3 months ago
0
[feature request] all models.

#39 0wwafa opened 4 months ago
0
Add trust_remote_code=True to support loading local custom models

#38 Russyyds opened 6 months ago
0
why i can't reproduce the result of paper?

#37 SHUSHENGQIGUI closed 6 months ago
7
AWQ alongside sparsegpt

#36 Returnvoidspec opened 6 months ago
0
AttributeError: 'NoneType' object has no attribute 'shape'

#35 thistleknot opened 7 months ago
9
fixed allenai c4 builder config bug

#34 mikailkhona closed 6 months ago
2
Why transpose the input when in case of nn.Linear or nn.Conv1d?

#33 tada0347 closed 7 months ago
0
Breaking stuff

#32 izzortsi closed 8 months ago
0
Why Hessian can get by activation ($H = XX^T$) ？

#31 Beatlesso closed 8 months ago
4
Updating c4 data loader as allenai--c4 config doesn't exist

#30 Donyme closed 6 months ago
1
Update demo.ipynb

#29 Donyme closed 6 months ago
0
2:4 sparsity with to_sparse_semi_structured method from pytorch results in memory issue

#28 Ahmed-Roushdy opened 8 months ago
0
how to use for Baichuan?

#27 njuhang opened 9 months ago
0
Mistral Support

#26 fakerybakery opened 11 months ago
2
transformers version is not correct

#25 Navid-visual opened 11 months ago
0
Using llama.py silently fails and occasionally causes system instability

#24 Pyroglyph opened 1 year ago
0
Can SparseGPT be used on BERT ?

#23 soonchangAI closed 1 year ago
0
Adaptation for Pruning Conv2d or Conv3d Layers?

#22 satabios closed 1 year ago
1
When would the code for GPT-J-6B be released?

#21 mumuyeye opened 1 year ago
0
Would sparsegpt be available for Llama2?

#20 moonlightian opened 1 year ago
3
Dependencies are wrong

#19 MrGranddy opened 1 year ago
3
Inference Speedup

#18 pkulium opened 1 year ago
3
finetuning sparsified LLaMa

#17 kiucho closed 1 year ago
5
Purpose of this update

#16 waveajay closed 1 year ago
0
How should I verify the speedup effect of the algorithm?

#15 moonlightian opened 1 year ago
4
OOM:cannot download opt-30b, opt-66b

#14 HaihangWu closed 1 year ago
0
Added LLaMA pruning script and colab demo

#13 Godofnothing closed 1 year ago
0
Different error between OBS and SparseGPT

#12 sbwww closed 1 year ago
5
Lack of comments in the code

#11 MrGranddy opened 1 year ago
0
why there is no inference related code in the project？

#10 18140663659 closed 1 year ago
10
Question about multi-GPU inference

#9 lsder closed 1 year ago
1
Gaussian elimination

#8 Lihengwannafly closed 1 year ago
1
Why LLaMa pruning is difficult?

#7 akisd2020 closed 1 year ago
4
Hessian Inverse

#6 Calmepro777 closed 1 year ago
1
Pruning log files

#5 simoneangarano closed 1 year ago
1
Out of memory issue

#4 xiamengzhou closed 1 year ago
2
Added saving and logging option

#3 Godofnothing closed 1 year ago
0
Saving the pruned checkpoint?

#2 AlpinDale closed 1 year ago
4
What causes gpu memory increase compred to dense mode？Is this normal？

#1 chenrui17 closed 1 year ago
4