sramshetty/ShortGPT
Unofficial implementations of block/layer-wise pruning methods for LLMs.
Jupyter NotebookMIT
Issues
- 0
Inquiry on GPU Usage and Time Requirement for Reproducing ShortGPT Experiment
#6 opened by wangyinkai6 - 3
importance score
#5 opened by riyajatar37003 - 2
Provide an implemention on hf transformers
#4 opened by xpq-tech - 0
Add Angular Distance Metric
#3 opened by sramshetty - 1
Model Healing
#2 opened by sramshetty - 4
Mistral
#1 opened by fakerybakery