Yay! Organizations can now publish blog Articles
•
46
AI & ML interests
The AI community building the future.
Recent Activity
View all activity
Articles
lysandre
updated
a
dataset
about 2 hours ago
Rename `azure-ml` to `azure-ai`
#510 opened about 2 hours ago
by
alvarobartt
a-r-r-o-w
updated
a
dataset
about 6 hours ago
Post
100
Just published: Nano-vLLM meets Inference Endpoints
I show how to bind Nano-vLLM (supporting Qwen3-0.6B) to a web service — and deploy it easily on Hugging Face Inference Endpoints.
Minimalist engine, maximum fun!
https://huggingface.co/blog/angt/nano-vllm-meets-inference-endpoints
I show how to bind Nano-vLLM (supporting Qwen3-0.6B) to a web service — and deploy it easily on Hugging Face Inference Endpoints.
Minimalist engine, maximum fun!
https://huggingface.co/blog/angt/nano-vllm-meets-inference-endpoints
[FEEDBACK] Daily Papers
🔥
❤️
20
137
#32 opened about 1 year ago
by
kramp
jeffboudier
posted
an
update
about 24 hours ago
Post
182
AMD summer hackathons are here!
A chance to get hands-on with MI300X GPUs and accelerate models.
🇫🇷 Paris - Station F - July 5-6
🇮🇳 Mumbai - July 12-13
🇮🇳 Bengaluru - July 19-20
Hugging Face and GPU Mode will be on site and on July 6 in Paris @ror will share lessons learned while building new kernels to accelerate Llama 3.1 405B on ROCm
Register to Paris event: https://lu.ma/fmvdjmur?tk=KeAbiP
All dates: https://lu.ma/calendar/cal-3sxhD5FdxWsMDIz
A chance to get hands-on with MI300X GPUs and accelerate models.
🇫🇷 Paris - Station F - July 5-6
🇮🇳 Mumbai - July 12-13
🇮🇳 Bengaluru - July 19-20
Hugging Face and GPU Mode will be on site and on July 6 in Paris @ror will share lessons learned while building new kernels to accelerate Llama 3.1 405B on ROCm
Register to Paris event: https://lu.ma/fmvdjmur?tk=KeAbiP
All dates: https://lu.ma/calendar/cal-3sxhD5FdxWsMDIz
Post
261
LongWriter-Zero 🔥 A Purely RL trained LLM handles 10K+ token coherent passages by Tsinghua University
Model:
THU-KEG/LongWriter-Zero-32B
Dataset:
THU-KEG/LongWriter-Zero-RLData
Paper:
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning (2506.18841)
✨ 32B
✨ Multi-reward GRPO: length, fluency, structure, non-redundancy
✨ Enforces <think><answer> format via Format RM
✨ Build on Qwen2.5-32B-base
Model:
THU-KEG/LongWriter-Zero-32B
Dataset:
THU-KEG/LongWriter-Zero-RLData
Paper:
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning (2506.18841)
✨ 32B
✨ Multi-reward GRPO: length, fluency, structure, non-redundancy
✨ Enforces <think><answer> format via Format RM
✨ Build on Qwen2.5-32B-base
Post
151
MOSS-TTSD 🔊 Bilingual text-to-spoken dialogue model by Fudan University - Open MOSS team.
Model:
fnlp/MOSS-TTSD-v0
Demo:
fnlp/MOSS-TTSD
✨ Supports Chinese & English
✨ Zero-shot 2-speaker voice cloning
✨ Long-form generation (up to 960s)
✨ Built on Qwen 3
Model:
fnlp/MOSS-TTSD-v0
Demo:
fnlp/MOSS-TTSD
✨ Supports Chinese & English
✨ Zero-shot 2-speaker voice cloning
✨ Long-form generation (up to 960s)
✨ Built on Qwen 3
Post
1609
Hackathons in Paris on July 5th and 6th!
Hugging Face just wrapped 4 months of deep work with AMD to push kernel-level optimization on their MI300X GPUs. Now, it's time to share everything we learned.
Join us in Paris at STATION F for a hands-on weekend of workshops and a hackathon focused on making open-source LLMs faster and more efficient on AMD.
Prizes, amazing host speakers, ... if you want more details, navigate to https://lu.ma/fmvdjmur!
Hugging Face just wrapped 4 months of deep work with AMD to push kernel-level optimization on their MI300X GPUs. Now, it's time to share everything we learned.
Join us in Paris at STATION F for a hands-on weekend of workshops and a hackathon focused on making open-source LLMs faster and more efficient on AMD.
Prizes, amazing host speakers, ... if you want more details, navigate to https://lu.ma/fmvdjmur!
- 2 replies
sergiopaniego
posted
an
update
2 days ago
Post
227
One of my favorite perks of the Hugging Face Pro plan: ✨Dev mode✨
Connect your HF Space to VS Code and just build — with hot reload out of the box.
Game changer for fast prototyping. 💻
Google Colab made AI accessible. Now HF Spaces are doing it too! 😍
💡 New Hugging Face pricing: http://hf.co/pricing
💡 More details: https://huggingface.co/learn/cookbook/en/enterprise_cookbook_dev_spaces
Connect your HF Space to VS Code and just build — with hot reload out of the box.
Game changer for fast prototyping. 💻
Google Colab made AI accessible. Now HF Spaces are doing it too! 😍
💡 New Hugging Face pricing: http://hf.co/pricing
💡 More details: https://huggingface.co/learn/cookbook/en/enterprise_cookbook_dev_spaces
Post
196
Skywork-SWE 🔥 New code agent model by Skywork 天工
Skywork/Skywork-SWE-32B
✨ 32B - Apache 2.0
✨ 38.0% pass@1 on SWE-bench Verified
✨ Up to 47.0% with test-time scaling
✨ Shows clear data scaling law (8K+ demos)
✨ Built on Qwen2.5-Coder-32B + OpenHands
Skywork/Skywork-SWE-32B
✨ 32B - Apache 2.0
✨ 38.0% pass@1 on SWE-bench Verified
✨ Up to 47.0% with test-time scaling
✨ Shows clear data scaling law (8K+ demos)
✨ Built on Qwen2.5-Coder-32B + OpenHands
Post
1809
🗣️ Whose voice do we hear when AI speaks?
Every language carries its own cultural values and worldviews. So, when we build AI systems, we're not just deciding how they speak but also whose perspectives they represent.
Even choosing which dialect to train on in Norway becomes a question of inclusion and power. In Kenya, will AI speak Swahili from Nairobi or coastal regions? What about indigenous languages with rich oral traditions but limited written text, like Quechua in Peru or Cherokee in North America?
The path forward? Building WITH communities, not just FOR them. Working with local partners (libraries, universities, civil society), testing for cultural alignment, and asking hard questions about representation.
Just published some thoughts on this after my keynote in Norway a few weeks ago: https://huggingface.co/blog/giadap/when-ai-speaks
Every language carries its own cultural values and worldviews. So, when we build AI systems, we're not just deciding how they speak but also whose perspectives they represent.
Even choosing which dialect to train on in Norway becomes a question of inclusion and power. In Kenya, will AI speak Swahili from Nairobi or coastal regions? What about indigenous languages with rich oral traditions but limited written text, like Quechua in Peru or Cherokee in North America?
The path forward? Building WITH communities, not just FOR them. Working with local partners (libraries, universities, civil society), testing for cultural alignment, and asking hard questions about representation.
Just published some thoughts on this after my keynote in Norway a few weeks ago: https://huggingface.co/blog/giadap/when-ai-speaks
- 1 reply
Post
2213
multimodalart
posted
an
update
6 days ago
Post
3290
Self-Forcing - a real-time video distilled model from Wan 2.1 by
@adobe
is out, and they open sourced it 🐐
I've built a live real time demo on Spaces 📹💨
multimodalart/self-forcing
I've built a live real time demo on Spaces 📹💨
multimodalart/self-forcing
-
- 2 replies
Post
1256
SongGeneration 🎵 A model by Tencent for vocal + accompaniment music generation.
Model:
tencent/SongGeneration
Demo:
https://huggingface.co/spaces/waytan22/SongGeneration-LeVo
✨ Mixed & dual-track token modeling
✨ Hi-fi music with custom codec
✨ Currently supports Chinese, English version coming soon!
Model:
tencent/SongGeneration
Demo:
https://huggingface.co/spaces/waytan22/SongGeneration-LeVo
✨ Mixed & dual-track token modeling
✨ Hi-fi music with custom codec
✨ Currently supports Chinese, English version coming soon!
Post
2349
Webinar Alert
Build your first chatbot with a Hugging Face Spaces frontend and Gaudi-powered backend with @bconsolvo ! He will teach you how to build an LLM-powered chatbot using Streamlit and Hugging Face Spaces—integrating a model endpoint hosted on an Intel® Gaudi® accelerator.
Beginners are welcome
https://web.cvent.com/event/70e11f23-7c52-4994-a918-96fa9d5e935f/summary
Build your first chatbot with a Hugging Face Spaces frontend and Gaudi-powered backend with @bconsolvo ! He will teach you how to build an LLM-powered chatbot using Streamlit and Hugging Face Spaces—integrating a model endpoint hosted on an Intel® Gaudi® accelerator.
Beginners are welcome
https://web.cvent.com/event/70e11f23-7c52-4994-a918-96fa9d5e935f/summary
- 1 reply
Post
4003
Kimi-Dev 💻 New coding model by Moonshot AI
moonshotai/Kimi-Dev-72B
✨ 72B - MIT license
✨ 60.4% on SWE-bench Verified
✨ RL-trained to patch real repos in Docker
✨ Only rewarded if full test suite passes
moonshotai/Kimi-Dev-72B
✨ 72B - MIT license
✨ 60.4% on SWE-bench Verified
✨ RL-trained to patch real repos in Docker
✨ Only rewarded if full test suite passes
Post
633
MiniMax-M1 🔥 The First reasoning model by MiniMax.
MiniMaxAI/minimax-m1-68502ad9634ec0eeac8cf094
✨ 40k/80k thinking budget
✨ Powered by Hybrid MoE + Lightning Attention 👀
✨ 1M context length 🤯
✨ Apache 2.0
✨ RL-trained for math, coding & real-world software
MiniMaxAI/minimax-m1-68502ad9634ec0eeac8cf094
✨ 40k/80k thinking budget
✨ Powered by Hybrid MoE + Lightning Attention 👀
✨ 1M context length 🤯
✨ Apache 2.0
✨ RL-trained for math, coding & real-world software
Post
425
Hunyuan 3D 2.1 🔥 Industrial-grade 3D model just released by Tencent Hunyuan
tencent/Hunyuan3D-2.1
tencent/Hunyuan3D-2.1
✨ PBR materials: leather, bronze & more, breathtaking realism under any light
✨ Consumer GPU-ready: good for developers and small teams
tencent/Hunyuan3D-2.1
tencent/Hunyuan3D-2.1
✨ PBR materials: leather, bronze & more, breathtaking realism under any light
✨ Consumer GPU-ready: good for developers and small teams
Post
2217
New diffusion model for text-to-image and video-to-world generation: Cosmos Predict-2 👽
Model collection: nvidia/cosmos-predict2-68028efc052239369a0f2959
Diffusers support: https://github.com/huggingface/diffusers/pull/11695
Documentation: https://huggingface.co/docs/diffusers/main/en/api/pipelines/cosmos
These are results with the 2B param model. Imagine what you could do with the 14B version! Go check it out now!
Model collection: nvidia/cosmos-predict2-68028efc052239369a0f2959
Diffusers support: https://github.com/huggingface/diffusers/pull/11695
Documentation: https://huggingface.co/docs/diffusers/main/en/api/pipelines/cosmos
These are results with the 2B param model. Imagine what you could do with the 14B version! Go check it out now!
- 1 reply