deepseek-ai/Janus-Pro-7B
Any-to-Any
•
Updated
•
53.1k
•
3.55k
❄️January 2025 - Open releases from the Chinese community
-
-
deepseek-ai/Janus-Pro-1B
Any-to-Any • Updated • 6.78k • 466 -
tencent/Hunyuan3D-2
Image-to-3D • Updated • 64.6k • 1.69k -
tencent/Hunyuan-7B-Instruct-0124
Text Generation • Updated • 83 • 50
ByteDance/Sa2VA-4B
Image-Text-to-Text • 4B • Updated • 144k • • 91Note A unified model for dense grounded understanding of images & videos.
-
ByteDance-Seed/UI-TARS-72B-DPO
Image-Text-to-Text • 73B • Updated • 791 • 148
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 436k • • 12.9kNote 660B reasoning models with MIT license
-
deepseek-ai/DeepSeek-R1-Zero
Text Generation • 685B • Updated • 2.87k • 940
MiniMaxAI/MiniMax-VL-01
Image-Text-to-Text • 456B • Updated • 68.1k • 282Note A non transformer based ( ViT-MLP-LLM framework) VLM
MiniMaxAI/MiniMax-Text-01
Text Generation • 456B • Updated • 1.82k • 652Note 456B LLM with 1M tokens training context
Qwen/Qwen2.5-Math-PRM-7B
Text Classification • 8B • Updated • 35.7k • 80Note Math model
-
Qwen/Qwen2.5-14B-Instruct-1M
Text Generation • 15B • Updated • 4.92k • • 331
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 79.3k • 1.28kNote End-side multimodal LLM that supports real time conversation and video understanding.
-
ICTNLP/llava-mini-llama-3.1-8b
Image-Text-to-Text • 9B • Updated • 314 • 56
BlinkDL/rwkv-7-world
Text Generation • Updated • 104Note RNN+Transfomers
HKUSTAudio/Llasa-3B
Text-to-Speech • 4B • Updated • 710 • 523Note TTS
-
DAMO-NLP-SG/VideoLLaMA3-7B
Video-Text-to-Text • 8B • Updated • 84k • 71 -
internlm/internlm3-8b-instruct
Text Generation • 9B • Updated • 10.1k • 228
baichuan-inc/Baichuan-M1-14B-Base
14B • Updated • 151 • 31Note Medical LLM
opencsg/Fineweb-Edu-Chinese-V2.1
Viewer • Updated • 958M • 30k • 57Note Dataset designed specifically for natural language processing (NLP) tasks in the education sector.
DAMO-NLP-SG/multimodal_textbook
Updated • 3.81k • 156Note 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 • 2.06k • 173 • 8 -
KlingTeam/GameFactory-Dataset
Updated • 522 • 14 -
m-a-p/YuE-s1-7B-anneal-zh-cot
Text Generation • 6B • Updated • 317 • 40 -
m-a-p/YuE-s1-7B-anneal-jp-kr-cot
Text Generation • 6B • Updated • 521 • 22 -
m-a-p/YuE-s1-7B-anneal-en-cot
Text Generation • 6B • Updated • 7.16k • 436 -
Qwen/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • 4B • Updated • 2.13M • 582 -
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 2.3M • • 1.41k -
Hunyuan3D-2.0
🌍3.14kText-to-3D and Image-to-3D Generation
-
UI-TARS
🌖65Find click coordinates on images based on instructions
-
MiniMaxVL01
💬64Generate responses to text and images in a chat interface
-
Chat With Janus-Pro-7B
🌍2.01kA unified multimodal understanding and generation model.
