Holo1 Collection Vision-Language Action Model for use in Surfer-H web navigation agent β’ 6 items β’ Updated 29 days ago β’ 48
view article Article nanoVLM: The simplest repository to train your VLM in pure PyTorch By ariG23498 and 6 others β’ May 21 β’ 185
Emerging Properties in Unified Multimodal Pretraining Paper β’ 2505.14683 β’ Published May 20 β’ 131
view article Article Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM By ariG23498 and 3 others β’ Mar 12 β’ 443
Pleias-RAG Collection New generation of small reasoning models for RAG, search, and source summarization. β’ 4 items β’ Updated Apr 24 β’ 27
view article Article Tiny Agents: a MCP-powered agent in 50 lines of code By julien-c β’ Apr 25 β’ 285
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory β’ 15 items β’ Updated about 15 hours ago β’ 203
β UI is a good thing π β Collection cool spaces with a cool UI, what could be better? β’ 5 items β’ Updated May 5 β’ 21
Foundation Models for Vision π§© Collection Foundation models for computer vision. β’ 24 items β’ Updated Mar 11, 2024 β’ 20
Vision Language Leaderboards Collection This collection has all the vision language leaderboards. β’ 7 items β’ Updated Aug 24, 2024 β’ 19
view article Article Open-Source Handwritten Signature Detection Model By samuellimabraz β’ Mar 14 β’ 114
Leaderboards and benchmarks β¨ Collection Cool leaderboard spaces collection for models across modalities! Text, vision, audio, ... β’ 91 items β’ Updated Feb 28 β’ 108
view article Article π¦βοΈ Using Llama3 and distilabel to build fine-tuning datasets By dvilasuero β’ Jun 4, 2024 β’ 79
view article Article FastRTC: The Real-Time Communication Library for Python By freddyaboulton and 1 other β’ Feb 25 β’ 169
Search-o1: Agentic Search-Enhanced Large Reasoning Models Paper β’ 2501.05366 β’ Published Jan 9 β’ 100
view article Article Open-source DeepResearch β Freeing our search agents By m-ric and 4 others β’ Feb 4 β’ 1.27k
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models Paper β’ 2502.01061 β’ Published Feb 3 β’ 219