Hugging Face
201 articles archived · Visit source ↗ · RSS
-
-
Hugging Face official-blog 6mo ago
Training Design for Text-to-Image Models: Lessons from Ablations
Back to Articles Training Design for Text-to-Image Models: Lessons from Ablations Team Article Published February 3, 2026 Upvote 73 David Bertoin Bertoin Photoroom Roman Frigg photoroman Photoroom Jon Almazán jon-almazan Photoroom Welcome back! This is the second part of our…
13 -
-
We Got Claude to Build CUDA Kernels and teach open models!
Back to Articles We got Claude to teach open models how to write CUDA kernels! Published January 28, 2026 Update on GitHub Upvote 156 ben burtenshaw burtenshaw shaun smith evalstate merve merve Pedro Cuenca pcuenq The best thing about agent skills is upskilling your agents on…
22 -
-
-
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
Back to Articles Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective Team Article Published January 27, 2026 Upvote 74 Jason Zhu JasonZhu13 LinkedIn Hejian Sang pb09204048 LinkedIn Arup De arde171 LinkedIn Rohit Jain rohjain LinkedIn Yanning Chen m0m0chen…
32 -
-
One Year Since the “DeepSeek Moment”
Back to Articles One Year Since the “DeepSeek Moment” Team Article Published January 20, 2026 Upvote 62 Adina Yakefu AdinaY huggingface Irene Solaiman irenesolaiman huggingface This is the first blog in a series that will examine China’s open source community’s historical…
10 -
Differential Transformer V2
Back to Articles Differential Transformer V2 Enterprise Article Published January 20, 2026 Upvote 50 Li Dong unilm microsoft Tianzhu Ye, Li Dong, Yutao Sun, Furu Wei Github Link Notion Link (for better readability) Code We compare DIFF V2 with DIFF V1 below: (For simplicity, we…
31 -
-
Open Responses: What you need to know
Back to Articles Open Responses: What you need to know Published January 15, 2026 Update on GitHub Upvote 111 shaun smith evalstate ben burtenshaw burtenshaw merve merve Pedro Cuenca pcuenq Open Responses is a new and open inference standard. Initiated by OpenAI, built by the…
29 -
-
-
-
-
-
-
CUGA on Hugging Face: Democratizing Configurable AI Agents
Back to Articles CUGA on Hugging Face: Democratizing Configurable AI Agents Enterprise Article Published December 15, 2025 Upvote 67 Jim Laredo laredoj ibm-research Avi Yaeli aviyaeli ibm-research Sami Marreed samimarreed ibm-research Ayhan Sebin ayhansebin ibm-research Merve…
33 -
New in llama.cpp: Model Management
Back to Articles New in llama.cpp: Model Management Team Article Published December 11, 2025 Upvote 134 Xuan-Son Nguyen ngxson ggml-org Victor Mustar victor ggml-org llama.cpp server now ships with router mode , which lets you dynamically load, unload, and switch between…
7 -
Codex is Open Sourcing AI models
Back to Articles Codex is Open Sourcing AI models Published December 11, 2025 Update on GitHub Upvote 82 ben burtenshaw burtenshaw shaun smith evalstate Building on our work to get Claude Code to train open source models, we are now getting Codex to go further. We gave Codex…
23 1 -
-
DeepMath: A lightweight math reasoning Agent with smolagents
Back to Articles DeepMath: A lightweight math reasoning Agent with smolagents Published December 4, 2025 Update on GitHub Upvote 40 Daniel Fleischer danf Intel Moshe Berchansky mber Intel Moshe Wasserblat moshew Intel By Intel AI Software Group DeepMath is an aligned math…
22 -
We Got Claude to Fine-Tune an Open Source LLM
Back to Articles We Got Claude to Fine-Tune an Open Source LLM Published December 4, 2025 Update on GitHub Upvote 624 ben burtenshaw burtenshaw shaun smith evalstate We gave Claude the ability to fine-tune language models using a new tool called Hugging Face Skills . Not just…
35 -
-
Diffusers welcomes FLUX-2
Back to Articles Welcome FLUX.2 - BFL’s new open image generation model 🤗 Published November 25, 2025 Update on GitHub Upvote 190 YiYi Xu YiYiXu Daniel Gu dg845 Sayak Paul sayakpaul Alvaro Somoza OzzyGT Dhruv Nair dn6 Aritra Roy Gosthipaty ariG23498 Linoy Tsaban linoyts…
12 -
Continuous batching from first principles
Back to Articles Continuous batching Published November 25, 2025 Update on GitHub Upvote 379 Rémi Ouazan Reboul ror Arthur Zucker ArthurZ Luc Georges mcpotato TL;DR: in this blog post, starting from attention mechanisms and KV caching, we derive continuous batching by optimizing…
38 -
Building Deep Research: How we Achieved State of the Art
Back to Articles Building Deep Research: How we Achieved State of the Art Team Article Published November 24, 2025 Upvote 36 Michael Griff michaelgriff Tavily Dean Sacoransky deansaco Tavily Noah Nefsky noahnefsky Tavily Research agents are rapidly becoming one of the most…
23 -
OVHcloud on Hugging Face Inference Providers 🔥
Back to Articles OVHcloud on Hugging Face Inference Providers 🔥 Community Article Published November 24, 2025 Upvote 78 Gilles Closset Gilles-Closset OVHcloud Fabien Ric fabric OVHcloud Elias Tourneux eliqs OVHcloud We're thrilled to share that OVHcloud is now a supported…
32 -
20x Faster TRL Fine-tuning with RapidFire AI
Back to Articles 20x Faster TRL Fine-tuning with RapidFire AI Published November 21, 2025 Update on GitHub Upvote 27 Kamran Bigdely kbigdelysh rapidfire-ai-inc Arun Kumar arunkk09 rapidfire-ai-inc Quentin Gallouédec qgallouedec Hugging Face TRL now officially integrates with…
13 -
-
-
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
Back to Articles Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models Enterprise Article Published November 19, 2025 Upvote 34 Torsten Scholak tscholak ServiceNow-AI Oleksiy Ostapenko ostapeno ServiceNow-AI Raymond Li RaymondLi ServiceNow-AI Luke Kumar…
17 -
-
Join the AMD Open Robotics Hackathon
Back to Articles Join the AMD Open Robotics Hackathon Enterprise Article Published November 13, 2025 Upvote 16 Eric Ma eric-amd amd Guruprasad MP guruprasadmp amd Looking to show off your robotics aptitude? The AMD Open Robotics Hackathon hosted by AMD, Hugging Face, and Data…
35 -
-
-
On the Shifting Global Compute Landscape
Back to Articles On the Shifting Global Compute Landscape Team Article Published October 29, 2025 Upvote 61 Tiezhen WANG tiezhen huggingface Irene Solaiman irenesolaiman huggingface Summary The status quo of AI chip usage, that was once almost entirely U.S.-based, is changing.…
14 -
-
-
Granite 4.0 Nano: Just how small can you go?
Back to Articles Granite 4.0 Nano: Just how small can you go? Enterprise Article Published October 28, 2025 Upvote 124 Kate Soule katesoule ibm-granite Rameswar Panda rpand002 ibm-granite Today we are excited to share Granite 4.0 Nano , our smallest models yet, released as part…
15 -
Voice Cloning with Consent
Back to Articles Voice Cloning with Consent Published October 28, 2025 Update on GitHub Upvote 40 Margaret Mitchell meg Lucie-Aimée Kaffee frimelle In this blog post, we introduce the idea of a 'voice consent gate' to support voice cloning with consent. We provide an example…
24 -
Streaming datasets: 100x More Efficient
Back to Articles Streaming datasets: 100x More Efficient Published October 27, 2025 Update on GitHub Upvote 86 Andres Marafioti andito Quentin Lhoest lhoestq ben burtenshaw burtenshaw Pedro Cuenca pcuenq merve merve TLDR We boosted load_dataset('dataset', streaming=True) ,…
14 -
-
LeRobot v0.4.0: Supercharging OSS Robot Learning
Back to Articles LeRobot v0.4.0: Supercharging OSS Robot Learning Published October 24, 2025 Update on GitHub Upvote 49 Steven Palma imstevenpmwork Michel Aractingi aractingi Pepijn Kooijmans pepijn223 Caroline Pascal CarolinePascal Jade Choghari jadechoghari Francesco Capuano…
4 -
-
-
Sentence Transformers is joining Hugging Face!
Back to Articles Sentence Transformers is joining Hugging Face! Published October 22, 2025 Update on GitHub Upvote 88 Tom Aarsen tomaarsen Today, we are announcing that Sentence Transformers is transitioning from Iryna Gurevych’s Ubiquitous Knowledge Processing (UKP) Lab at the…
9 -
Supercharge your OCR Pipelines with Open Models
Back to Articles Supercharge your OCR Pipelines with Open Models Published October 21, 2025 Update on GitHub Upvote 312 merve merve Aritra Roy Gosthipaty ariG23498 Daniel van Strien davanstrien Hynek Kydlicek hynky Andres Marafioti andito Vaibhav Srivastav reach-vb Pedro Cuenca…
8 -
Unlock the power of images with AI Sheets
Back to Articles Unlock the power of images with AI Sheets Published October 21, 2025 Update on GitHub Upvote 33 Ame Vi Ameeeee Daniel Vila dvilasuero Francisco Aranda frascuchon Damián Pumar damianpumar Leandro von Werra lvwerra Thomas Wolf thomwolf 🧭 TL;DR : Hugging Face AI…
17