DeepHermes Collection Preview models of hybrid reasoner Hermes series • 6 items • Updated 3 days ago • 23
DeepSeek R1 (All Versions) Collection DeepSeek R1 - the most powerful reasoning open-source model - available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 29 items • Updated 4 days ago • 209
Gemma 3 Collection All versions of Google's new multimodal models in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 29 items • Updated 2 days ago • 36
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! Paper • 2502.07374 • Published Feb 11 • 37
Hibiki fr-en Collection Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 5 items • Updated Feb 6 • 50
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training Paper • 2501.17161 • Published Jan 28 • 108
Eagle 2 Collection Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated Jan 23 • 31
view article Article Train 400x faster Static Embedding Models with Sentence Transformers Jan 15 • 159