Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
- +3
ybelkada, timdettmers, artidoro, sgugger, smangrul
• • 180Vishnu Dutt Pathak
Naruke
AI & ML interests
NLP, Reinforcement Learning, Graph Neural Network
Organizations
None yet
upvoted 2
articles almost 2 years ago
Article
Estimating Memory Consumption of LLMs for Inference and Fine-Tuning for Cohere Command-R+
Andyrasika
• • 13