Pangea Collection A Fully Open Multilingual Multimodal LLM for 39 Languages • 26 items • Updated 4 days ago • 18
DataGemma Release Collection A series of pioneering open models that help ground LLMs in real-world data through Data Commons. • 2 items • Updated Dec 13, 2024 • 84
VideoLLaMA2 Collection Optimized VideoLLaMA with improved spatial-temporal modeling and better audio understanding capability • 13 items • Updated 12 days ago • 20
view article Article Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖 By m-ric • Jun 20, 2024 • 26
C4AI Aya 23 Collection Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 4 items • Updated Dec 3, 2024 • 52
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention Paper • 2405.12981 • Published May 21, 2024 • 29
Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models Paper • 2404.07973 • Published Apr 11, 2024 • 31
StarChat2 15B Collection Model, datasets, and demo for StarChat2 15B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 10 items • Updated Apr 12, 2024 • 13
PERL: Parameter Efficient Reinforcement Learning from Human Feedback Paper • 2403.10704 • Published Mar 15, 2024 • 58