
❄️January 2025 - Open releases from the Chinese community
- Any-to-Any • Updated • 299k • 3.29k
deepseek-ai/Janus-Pro-1B
Any-to-Any • Updated • 38.9k • 415tencent/Hunyuan3D-2
Image-to-3D • Updated • 605k • 1.18ktencent/Hunyuan-7B-Instruct
Text Generation • Updated • 546 • 48
ByteDance/Sa2VA-4B
Image-Text-to-Text • Updated • 2.35k • 72Note A unified model for dense grounded understanding of images & videos.
bytedance-research/UI-TARS-72B-DPO
Image-Text-to-Text • Updated • 11.3k • 113
deepseek-ai/DeepSeek-R1
Text Generation • Updated • 1.4M • • 11.8kNote 660B reasoning models with MIT license
deepseek-ai/DeepSeek-R1-Zero
Text Generation • Updated • 7.83k • 885
MiniMaxAI/MiniMax-VL-01
Image-Text-to-Text • Updated • 173 • 250Note A non transformer based ( ViT-MLP-LLM framework) VLM
MiniMaxAI/MiniMax-Text-01
Text Generation • Updated • 2.4k • 564Note 456B LLM with 1M tokens training context
Qwen/Qwen2.5-Math-PRM-7B
Text Classification • Updated • 29.4k • 63Note Math model
Qwen/Qwen2.5-14B-Instruct-1M
Text Generation • Updated • 53.5k • 291
openbmb/MiniCPM-o-2_6
Any-to-Any • Updated • 858k • 1.08kNote End-side multimodal LLM that supports real time conversation and video understanding.
ICTNLP/llava-mini-llama-3.1-8b
Image-Text-to-Text • Updated • 8.54k • 50
BlinkDL/rwkv-7-world
Text Generation • Updated • 90Note RNN+Transfomers
HKUSTAudio/Llasa-3B
Text-to-Speech • Updated • 2.72k • 484Note TTS
DAMO-NLP-SG/VideoLLaMA3-7B
Visual Question Answering • Updated • 35.2k • 42internlm/internlm3-8b-instruct
Text Generation • Updated • 44.4k • 214
baichuan-inc/Baichuan-M1-14B-Base
Updated • 175 • 27Note Medical LLM
opencsg/Fineweb-Edu-Chinese-V2.1
Viewer • Updated • 958M • 29.8k • 22Note Dataset designed specifically for natural language processing (NLP) tasks in the education sector.
DAMO-NLP-SG/multimodal_textbook
Updated • 3.3k • 138Note A multimodel dataset for vision language pretraining , includes 6.5M images + 0.8B text from 22k hours of instructional videos
hithink-ai/MME-Finance
Viewer • Updated • 402 • 234 • 8KwaiVGI/GameFactory-Dataset
Updated • 287 • 9m-a-p/YuE-s1-7B-anneal-zh-cot
Text Generation • Updated • 3.47k • 37m-a-p/YuE-s1-7B-anneal-jp-kr-cot
Text Generation • Updated • 768 • 18m-a-p/YuE-s1-7B-anneal-en-cot
Text Generation • Updated • 37.7k • 396Qwen/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • Updated • 1.23M • 311Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • Updated • 3.34M • • 783- 2.21k
Hunyuan3D-2.0
🌍Text-to-3D and Image-to-3D Generation
- 46
UI-TARS
🌖Select coordinates on an image based on instructions
- 51
MiniMaxVL01
💬Generate responses using text and images
- 1.92k
Chat With Janus-Pro-7B
🌍A unified multimodal understanding and generation model.
- 573
Qwen2.5 Max Demo
🐢Chat with an AI language model