Qwen

Enterprise

company

https://qwen.ai/

alibaba_qwen

QwenLM

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

KnutJaegersberg new activity about 8 hours ago

Qwen/Qwen3-32B:Base Model?

JustinLin610 authored a paper about 19 hours ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

alielfilali01 authored a paper 6 days ago

Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi

View all activity

Qwen's activity

KnutJaegersberg

in Qwen/Qwen3-32B about 8 hours ago

Base Model?

➕ 😔 7

#3 opened about 1 month ago by

Downtown-Case

merve

posted an update about 15 hours ago

Post

187

H Company released Holo-1: 3B and 7B GUI Action Vision Language Models for various web and computer agent tasks 🤗

Holo-1 has Apache 2.0 license and transformers support from day-0 🔥
> Read the blog: https://huggingface.co/blog/Hcompany/holo1
> Model repositories: Hcompany/holo1-683dd1eece7eb077b96d0cbd

AdinaY

posted an update about 17 hours ago

Post

144

SynLogic 🧠 logical reasoning model & dataset by MiniMax.

MiniMaxAI/synlogic-6836c3246fca0277657ff032

✨ 3 models: 7B/32B/ Mix-3-32B (MIT license)
✨ Dataset: 35 verifiable logic tasks (Sudoku, Cipher, Arrow Maze etc.)
✨ RL training with auto-verifiable rewards
✨ Generalizes to math without explicit math training
✨ +6 pts on BBEH, +9.5 on KOR-Bench vs baselines

Zhenru

authored a paper about 19 hours ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 1 day ago • 102

JustinLin610

authored a paper about 19 hours ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 1 day ago • 102

AdinaY

posted an update about 20 hours ago

Post

671

Video-XL-2 🔥 long video understanding model by BAAI & Shanghai Jiaotong University

BAAI/Video-XL-2

✨ Apache 2.0
✨ Handles up to 10,000+ frames on a single GPU
✨ 2048-frame encoding in just 12s
✨ Efficient Chunk-based Prefilling & Bi-granularity KV decoding

chujiezheng

authored a paper about 20 hours ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 1 day ago • 102

danielhanchen

posted an update 1 day ago

Post

1739

New DeepSeek-R1-0528 1.65-bit Dynamic GGUF!

Run the model locally even easier! Will fit on a 192GB Macbook and run at 7 tokens/s.

DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-GGUF
Qwen3-8B DeepSeek-R1-0528 GGUFs: unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

And read our Guide: https://docs.unsloth.ai/basics/deepseek-r1-0528

merve

posted an update 1 day ago

Post

406

ColQwen2 just landed to transformers main 😍 vidore/colqwen2-v1.0-hf

use state-of-the-art visual document retrieval model ColQwen2 for your PDF retrieval or RAG pipelines 🎉

Here's a notebook to try right away: https://colab.research.google.com/drive/11_Vp6wB5RcQgK1MHt2M9On07EYXHH5E-?usp=sharing

AdinaY

posted an update 1 day ago

Post

1746

May highlights from China’s open source ecosystem 🔥

zh-ai-community/may-2025-open-works-from-the-chinese-community-681a3494145f2914dc679b7c

✨ DeepSeek dropped R1 updates
- Both R1 & 8B distralled smol model

✨ Bytedance goes big on open source:
- BAGEL, Dolphin, Seedcoder, Dream0...

✨ Multimodal is on fire!
- HuyuanCustom / HunyuanVideo-Avatar / HunyuanPortrait
- MiniMax: SynLogic / Orsta-7B
- Xiaomi: MiMo VL
- Alibaba Wan: Wan2.1-VACE
- OpenGVlab: ZeroGUI
- StepFun: ACE-Step-v1/Step1X-3D

✨ Specialized models/datasets excels
- Alibaba Qwen: World PM 72B
- BAAI:RobotBrain (MLLM for robotic)
- HiThink Research: BizFinBench (dataset)
- OpenBMB: Ultra FineWeb (dataset)
- Bilibili: Index-anisora (Anime/ACG)
- Skywork:Matrix-Game (game)

More awesome releases: Alibaba QwenLong-L1-32B, SkyWork OR1, OpenS2V-5M etc...

merve

posted an update 3 days ago

Post

1042

New GUI model by Salesforce AI & Uni HK: Jedi
tianbaoxiexxx/Jedi xlangai/Jedi-7B-1080p 🤗
Based on Qwen2.5-VL with Apache 2.0 license

prompt with below screenshot → select "find more"

1 reply

merve

posted an update 5 days ago

Post

1907

HOT: MiMo-VL new 7B vision LMs by Xiaomi surpassing gpt-4o (Mar), competitive in GUI agentic + reasoning tasks ❤️‍🔥 XiaomiMiMo/mimo-vl-68382ccacc7c2875500cd212

not only that, but also MIT license & usable with transformers 🔥

AdinaY

posted an update 5 days ago

Post

477

MiMo-VL 🔥 smol & mighty vision language model by Xiaomi

XiaomiMiMo/mimo-vl-68382ccacc7c2875500cd212

✨ 7B with RL & SFT
✨ Native resolution ViT for fine grained perception
✨ MORL = smarter alignment across perception, grounding & reasoning

merve

posted an update 6 days ago

Post

2656

introducing: VLM vibe eval 🪭 visionLMsftw/VLMVibeEval

vision LMs are saturated over benchmarks, so we built vibe eval 💬

> compare different models with refreshed in-the-wild examples in different categories 🤠
> submit your favorite model for eval
no numbers -- just vibes!

alielfilali01

authored a paper 6 days ago

Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi

Paper • 2504.06011 • Published Apr 8 • 1

jklj077

in Qwen/Qwen3-30B-A3B-FP8 6 days ago

Remove vLLM FP8 Limitation

#2 opened about 1 month ago by

simon-mo

AdinaY

posted an update 7 days ago

Post

2608

🔥 New benchmark & dataset for Subject-to-Video generation

OPENS2V-NEXUS by Pekin University

✨ Fine-grained evaluation for subject consistency
BestWishYsh/OpenS2V-Eval
✨ 5M-scale dataset:
BestWishYsh/OpenS2V-5M
✨ New metrics – automatic scores for identity, realism, and text match

2 replies

AdinaY

posted an update 7 days ago

Post

2220

HunyuanVideo-Avatar 🔥 another image to video model byTencent Hunyuan

tencent/HunyuanVideo-Avatar

✨Emotion-controlled, high-dynamic avatar videos
✨Multi-character support with separate audio control
✨Works with any style: cartoon, 3D, real face, while keeping identity consistent

merve

posted an update 8 days ago

Post

2518

emerging trend: models that can understand image + text and generate image + text

don't miss out ⤵️
> MMaDA: single 8B diffusion model aligned with CoT (reasoning!) + UniGRPO Gen-Verse/MMaDA
> BAGEL: 7B MoT model based on Qwen2.5, SigLIP-so-400M, Flux VAE ByteDance-Seed/BAGEL
both by ByteDance! 😱

I keep track of all any input → any output models here https://huggingface.co/collections/merve/any-to-any-models-6822042ee8eb7fb5e38f9b62

1 reply

AdinaY

posted an update 8 days ago

Post

1886

HunyuanPortrait 🔥 video model by Tencent Hunyuan team.

HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation (2503.18860)
tencent/HunyuanPortrait

✨Portrait animation from just one image + a video prompt
✨Diffusion-based, implicit motion control
✨Superior temporal consistency & detail

AI & ML interests

Recent Activity

Team members 139

Qwen's activity

Base Model?

Remove vLLM FP8 Limitation