Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
•
102
Artidoro Pagnoni
artidoro
AI & ML interests
NLP, generation, factuality, disinformation.
Recent Activity
commented
a paper
9 days ago
Byte Latent Transformer: Patches Scale Better Than Tokens
authored
a paper
9 days ago
Socratic Pretraining: Question-Driven Pretraining for Controllable
Summarization
authored
a paper
9 days ago
Byte Latent Transformer: Patches Scale Better Than Tokens
Articles
Organizations
datasets
None public yet