Article
A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
•
80
Prasanth Balaraman
pbalaram
·
AI & ML interests
None yet
Recent Activity
updated
a model
26 days ago
pbalaram/SmolLM2-135M-FT-Smoltalk
published
a model
26 days ago
pbalaram/SmolLM2-135M-FT-Smoltalk
updated
a model
7 months ago
pbalaram/pbalaram_flux
Organizations
None yet
pbalaram's activity
upvoted
2
articles
8 months ago
Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
•
126