MambaVision Collection MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. ā¢ 13 items ā¢ Updated 1 day ago ā¢ 29
TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting Paper ā¢ 2503.17032 ā¢ Published 7 days ago ā¢ 19
MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving Paper ā¢ 2503.16905 ā¢ Published 7 days ago ā¢ 51
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Paper ā¢ 2503.03601 ā¢ Published 22 days ago ā¢ 218
SurveyX: Academic Survey Automation via Large Language Models Paper ā¢ 2502.14776 ā¢ Published Feb 20 ā¢ 97
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. ā¢ 29 items ā¢ Updated 2 days ago ā¢ 212
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages Paper ā¢ 2410.01036 ā¢ Published Oct 1, 2024 ā¢ 15
HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors Paper ā¢ 2408.06019 ā¢ Published Aug 12, 2024 ā¢ 15
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction Paper ā¢ 2409.18124 ā¢ Published Sep 26, 2024 ā¢ 33
Llama 3.2 Collection Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. ā¢ 27 items ā¢ Updated 2 days ago ā¢ 58
view article Article Fine-tuning LLMs to 1.58bit: extreme quantization made easy Sep 18, 2024 ā¢ 227
Qwen2.5 Collection Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. ā¢ 46 items ā¢ Updated 30 days ago ā¢ 574