Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
•
113
Mert
mertgulexe
·
AI & ML interests
None yet
Recent Activity
liked
a model
about 21 hours ago
FacebookAI/xlm-roberta-base
liked
a model
about 1 month ago
Datou1111/shou_xin
liked
a model
3 months ago
mosaicml/mpt-7b
Organizations
None yet
mertgulexe's activity
upvoted
5
articles
9 months ago
Article
A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
•
71
Article
Introduction to Quantization cooked in 🤗 with 💗🧑🍳
By
•
•
27Article
🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware
•
54
Article
Overview of natively supported quantization schemes in 🤗 Transformers
•
11