Gemma 4 Collection Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 2 days ago • 127
view article Article CoDA-GQA-L: Bounded-Memory Differential Attention with Value-Routed Landmark Banks Feb 16 • 2
view article Article Introducing Daggr: Chain apps programmatically, inspect visually +3 Jan 29 • 106
view article Article Fine-tuning LLMs to 1.58bit: extreme quantization made easy +4 Sep 18, 2024 • 279
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models Paper • 2309.12307 • Published Sep 21, 2023 • 89
Adapting Large Language Models via Reading Comprehension Paper • 2309.09530 • Published Sep 18, 2023 • 82