Skywork-R1V2 Collection Multimodal Hybrid Reinforcement Learning for Reasoning β’ 7 items β’ Updated Aug 13 β’ 12
PaddleOCR-VL Collection Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model β’ 3 items β’ Updated Oct 17 β’ 20
βοΈ Liquid Nanos Collection Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices β’ 21 items β’ Updated Oct 30 β’ 94
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research Paper β’ 2509.13312 β’ Published Sep 16 β’ 104
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning Paper β’ 2509.13305 β’ Published Sep 16 β’ 90
Multimodal GGUFs Collection Vision and audio models compatible with llama-server and llama-mtmd-cli β’ 13 items β’ Updated Aug 20 β’ 13
Transformers.js demos Collection A collection of my favorite WebML demos, built with Transformers.js! β’ 30 items β’ Updated Jul 11, 2024 β’ 128
view article Article Transformers.js v3: WebGPU Support, New Models & Tasks, and More⦠Oct 22, 2024 ⒠77
Text-to-Speech (TTS) models Collection A collection of 4-bit, Dynamic 4-bit and 16-bit voice models including Sesame-CSM, OpenAI's Whisper, Orpheus. Fine-tune them with Unsloth now! β’ 16 items β’ Updated Oct 31 β’ 26
π§ LFM2 Collection LFM2 is a new generation of hybrid models, designed for on-device deployment. β’ 22 items β’ Updated 26 days ago β’ 119
ποΈ LFM2-VL Collection LFM2-VL is our first series of vision-language models, designed for on-device deployment. β’ 9 items β’ Updated Oct 30 β’ 52