Yay! Organizations can now publish blog Articles
•
45
Hugging Face
Enterprise
company
Verified
AI & ML interests
The AI community building the future.
Recent Activity
View all activity
Articles
huggingface's activity
Post
155
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"
tianbaoxiexxx/Jedi xlangai/Jedi-7B-1080p 🤗
Based on Qwen2.5-VL with Apache 2.0 license
prompt with below screenshot → select "find more"
evijit
updated
a
dataset
2 days ago
Post
1759
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 🔥
not only that, but also MIT license & usable with transformers 🔥
lhoestq
updated
a
dataset
2 days ago
[FEEDBACK] Notifications
🤗
❤️
15
148
#6 opened almost 3 years ago
by
victor
Post
373
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
XiaomiMiMo/mimo-vl-68382ccacc7c2875500cd212
✨ 7B with RL & SFT
✨ Native resolution ViT for fine grained perception
✨ MORL = smarter alignment across perception, grounding & reasoning
[FEEDBACK] Inference Playground
👍
🔥
6
39
#1 opened 8 months ago
by
victor
Post
2578
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!
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!
Post
2763
🎵 Dream come true for content creators! TIGER AI can extract voice, effects & music from ANY audio file 🤯
This lightweight model uses frequency band-split technology to separate speech like magic. Kudos to @fffiloni for the amazing demo! fffiloni/TIGER-audio-extraction
This lightweight model uses frequency band-split technology to separate speech like magic. Kudos to @fffiloni for the amazing demo! fffiloni/TIGER-audio-extraction
Post
2557
🔥 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
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
Post
2176
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
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
Post
2472
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
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
Post
1849
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
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
albertvillanova
posted
an
update
5 days ago
Post
318
New in smolagents v1.17.0:
- Structured generation in CodeAgent 🧱
- Streamable HTTP MCP support 🌐
- Agent.run() returns rich RunResult 📦
Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0
- Structured generation in CodeAgent 🧱
- Streamable HTTP MCP support 🌐
- Agent.run() returns rich RunResult 📦
Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0
Post
3711
Just completed the AI Agents course and wow, that capstone project really makes you understand how to build agents that can handle real-world complexity!
The final project uses the GAIA dataset - your agent has to solve tasks like analyzing Excel files, processing audio recordings, answering questions about YouTube videos, and diving into research papers. This isn't toy examples, it's the messy, multimodal stuff agents need to handle in practice.
Whether you’re just getting started with agents or want to go deeper with tools like LangChain, LlamaIndex, and SmolAgents, this course has tons of useful stuff. A few key insights:
- Code agents are incredibly versatile once you get the architecture right
- The sweet spot is finding the right balance of guidance vs autonomy for each use case
- Once the logic clicks, the possibilities really are endless - it's like letting LLMs break free from the chatbox
The course is free and the certification deadline is July 1st, 2025.
The Hugging Face team built something special here. If you're tired of AI that impresses in demos but fails in practice, this is your path to building agents that actually deliver. https://huggingface.co/learn/agents-course/unit0/introduction
Best part? There's the MCP course next!
The final project uses the GAIA dataset - your agent has to solve tasks like analyzing Excel files, processing audio recordings, answering questions about YouTube videos, and diving into research papers. This isn't toy examples, it's the messy, multimodal stuff agents need to handle in practice.
Whether you’re just getting started with agents or want to go deeper with tools like LangChain, LlamaIndex, and SmolAgents, this course has tons of useful stuff. A few key insights:
- Code agents are incredibly versatile once you get the architecture right
- The sweet spot is finding the right balance of guidance vs autonomy for each use case
- Once the logic clicks, the possibilities really are endless - it's like letting LLMs break free from the chatbox
The course is free and the certification deadline is July 1st, 2025.
The Hugging Face team built something special here. If you're tired of AI that impresses in demos but fails in practice, this is your path to building agents that actually deliver. https://huggingface.co/learn/agents-course/unit0/introduction
Best part? There's the MCP course next!
Post
2775
Orsta 🔥 vision language models trained with V-Triune, a unified reinforcement learning system by MiniMax AI
One-RL-to-See-Them-All/one-rl-to-see-them-all-6833d27abce23898b2f9815a
✨ 7B & 32B with MIT license
✨ Masters 8 visual tasks: math, science QA, charts, puzzles, object detection, grounding, OCR, and counting
✨ Uses Dynamic IoU rewards for better visual understanding
✨Strong performance in visual reasoning and perception
One-RL-to-See-Them-All/one-rl-to-see-them-all-6833d27abce23898b2f9815a
✨ 7B & 32B with MIT license
✨ Masters 8 visual tasks: math, science QA, charts, puzzles, object detection, grounding, OCR, and counting
✨ Uses Dynamic IoU rewards for better visual understanding
✨Strong performance in visual reasoning and perception
Post
2041
QwenLong-L1🔥 long-context reasoning model by Alibaba Tongyi Zhiwen team.
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning (2505.17667)
Tongyi-Zhiwen/QwenLong-L1-32B
✨ 32B & Apache 2.0
✨ Outperforms OpenAI-o3-mini & Qwen3-235B-A22B
✨ Trained on a unique 1.6K DocQA RL dataset spanning math, logic & multi-hop reasoning
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning (2505.17667)
Tongyi-Zhiwen/QwenLong-L1-32B
✨ 32B & Apache 2.0
✨ Outperforms OpenAI-o3-mini & Qwen3-235B-A22B
✨ Trained on a unique 1.6K DocQA RL dataset spanning math, logic & multi-hop reasoning
Post
2405
A new research paper from KAIST builds on smolagents to push boundaries of distillation 🥳
➡️ "Distilling LLM Agent into Small Models with Retrieval and Code Tools" teaches that, when trying to distil reasoning capability from a strong LLM ("teacher") into a smaller one ("student"), it's much better to use Agent traces than CoT traces.
Advantages are:
1. Improved generalization
Intuitively, this is because your agent can encounter more "surprising" results by interacting with its environment : for example, a web research called by the LLM teacher in agent mode can bring results that the LLM teacher would not have generated in CoT.
2. Reduce hallucinations
The trace won't hallucinate tool call outputs!
Thank you @akseljoonas for mentioning this paper!
➡️ "Distilling LLM Agent into Small Models with Retrieval and Code Tools" teaches that, when trying to distil reasoning capability from a strong LLM ("teacher") into a smaller one ("student"), it's much better to use Agent traces than CoT traces.
Advantages are:
1. Improved generalization
Intuitively, this is because your agent can encounter more "surprising" results by interacting with its environment : for example, a web research called by the LLM teacher in agent mode can bring results that the LLM teacher would not have generated in CoT.
2. Reduce hallucinations
The trace won't hallucinate tool call outputs!
Thank you @akseljoonas for mentioning this paper!
Post
3066
what happened in open AI past week? so many vision LM & omni releases 🔥
merve/releases-23-may-68343cb970bbc359f9b5fb05
multimodal 💬🖼️
> new moondream (VLM) is out: it's 4-bit quantized (with QAT) version of moondream-2b, runs on 2.5GB VRAM at 184 tps with only 0.6% drop in accuracy (OS) 🌚
> ByteDance released BAGEL-7B, an omni model that understands and generates both image + text. they also released Dolphin, a document parsing VLM 🐬 (OS)
> Google DeepMind dropped MedGemma in I/O, VLM that can interpret medical scans, and Gemma 3n, an omni model with competitive LLM performance
> MMaDa is a new 8B diffusion language model that can generate image and text
LLMs
> Mistral released Devstral, a 24B coding assistant (OS) 👩🏻💻
> Fairy R1-32B is a new reasoning model -- distilled version of DeepSeek-R1-Distill-Qwen-32B (OS)
> NVIDIA released ACEReason-Nemotron-14B, new 14B math and code reasoning model
> sarvam-m is a new Indic LM with hybrid thinking mode, based on Mistral Small (OS)
> samhitika-0.0.1 is a new Sanskrit corpus (BookCorpus translated with Gemma3-27B)
image generation 🎨
> MTVCrafter is a new human motion animation generator
multimodal 💬🖼️
> new moondream (VLM) is out: it's 4-bit quantized (with QAT) version of moondream-2b, runs on 2.5GB VRAM at 184 tps with only 0.6% drop in accuracy (OS) 🌚
> ByteDance released BAGEL-7B, an omni model that understands and generates both image + text. they also released Dolphin, a document parsing VLM 🐬 (OS)
> Google DeepMind dropped MedGemma in I/O, VLM that can interpret medical scans, and Gemma 3n, an omni model with competitive LLM performance
> MMaDa is a new 8B diffusion language model that can generate image and text
LLMs
> Mistral released Devstral, a 24B coding assistant (OS) 👩🏻💻
> Fairy R1-32B is a new reasoning model -- distilled version of DeepSeek-R1-Distill-Qwen-32B (OS)
> NVIDIA released ACEReason-Nemotron-14B, new 14B math and code reasoning model
> sarvam-m is a new Indic LM with hybrid thinking mode, based on Mistral Small (OS)
> samhitika-0.0.1 is a new Sanskrit corpus (BookCorpus translated with Gemma3-27B)
image generation 🎨
> MTVCrafter is a new human motion animation generator
- 1 reply
Post
2490
Two lines in your terminal and you have an AI agent running whatever model and tools you want 🤯
Just tried the new Tiny Agents in Python. Asked it which team won the Italian Serie A soccer league and to export the final table to CSV. Coolest thing is you can interact with the agent, guide it, and correct its mistakes.
The agent connected to web browsing tools, searched for Serie A standings, identified the champion, and generated a CSV export.
The setup:
That's it. The MCP protocol handles all the tool integrations automatically - no custom APIs to write, no complex setups. Want file system access? It's already there. Need web browsing? Built in.
You can swap models, change inference providers, run local models, or add new tools just by editing a simple JSON config. You can also use Gradio Spaces as MCP servers! The entire agent is ~70 lines of Python - essentially a while loop that streams responses and executes tools. Everything is open-source. ❤️ Hugging Face
Blog post: https://huggingface.co/blog/python-tiny-agents
Just tried the new Tiny Agents in Python. Asked it which team won the Italian Serie A soccer league and to export the final table to CSV. Coolest thing is you can interact with the agent, guide it, and correct its mistakes.
The agent connected to web browsing tools, searched for Serie A standings, identified the champion, and generated a CSV export.
The setup:
pip install "huggingface_hub[mcp]>=0.32.0"
tiny-agents runThat's it. The MCP protocol handles all the tool integrations automatically - no custom APIs to write, no complex setups. Want file system access? It's already there. Need web browsing? Built in.
You can swap models, change inference providers, run local models, or add new tools just by editing a simple JSON config. You can also use Gradio Spaces as MCP servers! The entire agent is ~70 lines of Python - essentially a while loop that streams responses and executes tools. Everything is open-source. ❤️ Hugging Face
Blog post: https://huggingface.co/blog/python-tiny-agents
- 1 reply