The Curse of Depth in Large Language Models
Paper • 2502.05795 • Published • 40 •
5
Avelina Hadji-Kyriacou
Avelina
AI & ML interests
Trying to squeeze the most performance out of small language models to bring AI inference to the user, and keep personal data out of the cloud.
Organizations
Delete hendrycks_test.py
#33 opened 9 months ago
by Avelina
HuggingFace version does NOT use efficient MLA caching
2
#95 opened about 1 year ago
by Avelina
[bot] Conversion to Parquet
#1 opened about 1 year ago
by 
parquet-converter
[bot] Conversion to Parquet
#1 opened about 1 year ago
by parquet-converter
commented a
paper about 1 year ago
How to filter for language?
4
#2 opened over 1 year ago
by 
Rijgersberg
[bot] Conversion to Parquet
#1 opened over 1 year ago
by parquet-converter
[bot] Conversion to Parquet
#1 opened over 1 year ago
by parquet-converter
Feature Request: Running Evaluation Locally for Custom Models // Provide Documentation for 3rd Party Implementation
#787 opened almost 2 years ago
by Avelina
Too much Junk vocab words in the vocab.json.
8
#28 opened about 2 years ago
by 
MartialTerran
Creating train splits dies
1
#12 opened about 3 years ago
by 
surya-narayanan