Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
•
140
Mert
mertgulexe
·
AI & ML interests
None yet
Organizations
None yet
mertgulexe's activity
upvoted
4
articles
11 months ago
Article
A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
•
86
Article
🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware
•
77
Article
Overview of natively supported quantization schemes in 🤗 Transformers
•
12