Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
mlabonne 
posted an update 1 day ago
AdinaY 
posted an update 3 days ago
view post
Post
1655
Chinese open source AI in December 2025 was about the stack coming together: open, end to end, and ready to ship 🔥

https://huggingface.co/collections/zh-ai-community/december-2025-china-open-source-highlights

✨ Big wave of foundation models: still scaling, but efficiency, reasoning, and deployment now matter more than size
- DeepSeek-V3.2
- Z.ai GLM-4.7
- MiniMax-M2.1
- Xiaomi: MiMo-V2-Flash

✨ Multimodal reasoning is now default
- Z.ai GLM-4.6V
- Z.ai AutoGLM-Phone 9B
- Bytedance: Dolphin-v2

✨ Image & video: editable assets and real workflows
- Qwen-Image-Layered / Image-2512
- Meituan: LongCat-Image & Image Edit
- AIDC: Ovis-Image-7B
- Live-Avatar / LongCat-Video-Avatar
- HY-WorldPlay / RealVideo

✨ Audio goes edge ready
- GLM-ASR-Nano / Fun-ASR-Nano
- GLM-TTS / VoxCPM1.5
- CosyVoice 0.5B

✨ The quiet backbone: data & infrastructure
- Finch (FinWorkBench)
- Tencent ARC: TimeLens-100K
- BIGAI: TongSIM-Asset
- MiniMax: VTP-Base

✨ Also congrats on Minimax and Z.ai announced their IPOs and Moonshot announced a new $500M funding round 🔥

Like everyone else, I was OOO at the end of December, so feel free to share (in comments or PR) any I missed in this list!
vincentg64 
posted an update 1 day ago
view post
Post
1132
New Book: No-Blackbox, Secure, Efficient AI and LLM Solutions https://mltblog.com/4aRwvM5

Large language models and modern AI is often presented as technology that needs deep neural networks (DNNs) with billions of Blackbox parameters, expensive and time consuming training, along with GPU farms, yet prone to hallucinations. This book presents alternatives that rely on explainable AI, featuring new algorithms based on radically different technology with trustworthy, auditable, fast, accurate, secure, replicable Enterprise AI. Most of the material is proprietary and made from scratch, showcasing the culmination of decades of research away from standard models to establish a new framework in machine learning and AI technology.

I discuss an efficient DNN architecture based on a new type of universal functions in chapter 4, with DNN distillation and protection via watermarking in chapter 5. Then, in chapter 6, I discuss non-DNN alternatives that yield exact interpolation on the training set yet benefit from benign overfitting in any dimension. Accurate predictions are obtained with a simple closed-form expression, without gradient descent or other iterative optimization technique, essentially without training.

Case studies include 96% correct predictions for the next token on a Nvidia PDF repository, automated heart beat clustering and unusually high data compression rates (big data), anomaly detection and fraud litigation linked to large-scale cybsersecurity breach (large Excel repository, automated SQL, time series and geospatial data) as well as predicting next sequence on real-world genome data with home-made LLM technology. Some datasets with 1000 dimensions are generated with the best and fastest tabular data synthesizer on the market, described in details in chapter 2 along with the best model evaluation metric. These cases correspond to different agents linked to the xLLM technology (extreme LLM) developed by the author.
mindchain 
posted an update 2 days ago
view post
Post
1180
Skill Reflect: A Concept for Automated AI Skill Mastery

Let’s be real for a second: most of us are using AI all wrong. We send a prompt, get a "meh" answer, and then spend twenty minutes fixing it ourselves. That’s not a workflow; that’s just a digital chore. I wanted to see if I could push Claude further—to see if I could build a system that actually learns and refines itself. That’s how the Claude-Reflect-System (Skill Reflect) was born.

But here’s the thing: this isn’t some polished, final product. It’s a concept. It’s a blueprint. I’ve built the foundation of a recursive reflection loop that forces the AI to step back, look at its work, and act as its own harshest critic. It identifies the "skill delta"—the gap between "okay" and "mastery"—and closes it. This logic isn't just for Claude; you can grab this architecture and drop it right into codex-cli, terminal agents, or whatever stack you're building.

I’m a big believer in the law of causality. Action, reaction. Cause and effect. If you control the cause—the way the AI thinks about its mistakes—you dictate the effect: a perfected skill. This is a playground for builders who are tired of stochastic guessing. I want you to take this. Fork it. Break it. Make it better. This is an open invitation to the community to take this reflection loop and see how far we can push the boundaries of agentic reasoning. Whether you're building Claude Code plugins or just want to automate your self-learning, the code is there for you to smash. Stop accepting the first draft. Let’s build something that actually thinks.

https://github.com/haddock-development/claude-reflect-system

#Skills #ClaudeCode #ClaudeCodeSkills #ClaudeCodePlugins #ClaudeCodeMarketplace #CodexCLI #AI #SelfLearning #Automation #OpenSource #LLM #Reasoning #Causality #Matrix #Concept
MikeDoes 
posted an update 2 days ago
view post
Post
1027
We can't build more private AI if we can't measure privacy intelligence.

That's why we're highlighting the Priv-IQ benchmark, a new, solution-oriented framework for evaluating LLMs on eight key privacy competencies, from visual privacy to knowledge of privacy law. The direct connection to our work is clear: the researchers relied on samples from the Ai4Privacy dataset to build out questions for Privacy Risk Assessment and Multilingual Entity Recognition.

This is the power of open-source collaboration. We provide the data building blocks, and researchers construct powerful new evaluation tools on top of them. It's a win-win for the entire ecosystem when we can all benefit from transparent, data-driven benchmarks that help push for better, safer AI.

Kudos to Sakib Shahriar and Rozita A. Dara for this important contribution. Read the paper to see the results: https://www.proquest.com/docview/3170854914?pq-origsite=gscholar&fromopenview=true&sourcetype=Scholarly%20Journals

#OpenSource
#DataPrivacy
#LLM
#Anonymization
#AIsecurity
#HuggingFace
#Ai4Privacy
#Worldslargestopensourceprivacymaskingdataset
tsungyi 
posted an update 2 days ago
view post
Post
1775
Big news from CES — Cosmos Reason 2 is here — our most advanced reasoning vision-language model for physical AI, now topping the Physical AI Bench leaderboard🏆 shi-labs/physical-ai-bench-leaderboard

What’s new:
- Enhanced physical reasoning & spatio-temporal understanding
- Flexible deployment with 2B & 8B model sizes
- Long-context understanding (up to 256K tokens)
- Object detection with 2D/3D point localizations and trajectory data
- New Cosmos Cookbook Recipes for faster onboarding

Read the full blog 📖 https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning
Download Cosmos Reason 2 👉 nvidia/Cosmos-Reason2-8B

On top of Cosmos Reason 2, we also rolled out other new updates, including:
- Cosmos Predict 2.5 – Unified Text2World/Image2World/Video2World model for higher-quality synthetic video worlds
- Cosmos Transfer 2.5-2B – Lightweight, high-fidelity world-to-world translation with stronger physics alignment
- NVIDIA GR00T N1.6 – Open robot foundation model for general-purpose robotic learning and control, integrated with Cosmos Reason

Get Started with the Cosmos Cookbook 🧑🏻‍🍳 https://nvda.ws/4qevli8
Hellohal2064 
posted an update 3 days ago
view post
Post
1536
🚀 Excited to share: The vLLM container for NVIDIA DGX Spark!

I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!

📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)

🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround

📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10

The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!
·
MaziyarPanahi 
posted an update 2 days ago
view post
Post
1316
🎉 OpenMed 2025 Year in Review: 6 Months of Open Medical AI

I'm thrilled to share what the OpenMed community has accomplished since our July 2025 launch!

📊 The Numbers

29,700,000 downloads Thank you! 🙏

- 481 total models (475 medical NER models + 6 fine-tuned LLMs)
- 475 medical NER models in [OpenMed](
OpenMed ) organization
- 6 fine-tuned LLMs in [openmed-community](
openmed-community )
- 551,800 PyPI downloads of the [openmed package](https://pypi.org/project/openmed/)
- 707 followers on HuggingFace (you!)
- 97 GitHub stars on the [toolkit repo](https://github.com/maziyarpanahi/openmed)

🏆 Top Models by Downloads

1. [OpenMed-NER-PharmaDetect-SuperClinical-434M]( OpenMed/OpenMed-NER-PharmaDetect-SuperClinical-434M) — 147,305 downloads
2. [OpenMed-NER-ChemicalDetect-ElectraMed-33M]( OpenMed/OpenMed-NER-ChemicalDetect-ElectraMed-33M) — 126,785 downloads
3. [OpenMed-NER-BloodCancerDetect-TinyMed-65M]( OpenMed/OpenMed-NER-BloodCancerDetect-TinyMed-65M) — 126,465 downloads

🔬 Model Categories

Our 481 models cover comprehensive medical domains:

- Disease Detection (~50 variants)
- Pharmaceutical Detection (~50 variants)
- Oncology Detection (~50 variants)
- Genomics/DNA Detection (~80 variants)
- Chemical Detection (~50 variants)
- Species/Organism Detection (~60 variants)
- Protein Detection (~50 variants)
- Pathology Detection (~50 variants)
- Blood Cancer Detection (~30 variants)
- Anatomy Detection (~40 variants)
- Zero-Shot NER (GLiNER-based)


OpenMed
OpenMed NER: Open-Source, Domain-Adapted State-of-the-Art Transformers for Biomedical NER Across 12 Public Datasets (2508.01630)
https://huggingface.co/collections/OpenMed/medical-and-clinical-ner
https://huggingface.co/collections/OpenMed/zeroshot-medical-and-clinical-ner
OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B
  • 1 reply
·
dhruv3006 
posted an update 2 days ago
view post
Post
1160
Need a variable that's not fixed but depends on another request's response?

Runtime variables let you capture values from one API call and reuse them in subsequent requests.

What are Runtime Variables?
Runtime variables are dynamic values that get set during request execution.

They're perfect for scenarios like:
- Capturing an auth token from login and using it in authenticated requests
- Storing a user ID from a create-user response
- Saving an order ID to use in later order management calls

Use Runtime Variables in Voiden : https://voiden.md/
pcuenq 
posted an update 3 days ago
view post
Post
2354
👉 What happened in AI in 2025? 👈

We prepared the 2025 version of the HF AI Timeline Grid, highlighting open vs API-based model releases, and allowing you to browse and filter by access, modality, and release type!

Play with it here:
2025-ai-timeline/2025-ai-timeline

Here's my personal quarterly TL;DR:

1️⃣ Q1 — Learning to Reason
Deepseek not only releases a top-notch reasoning model, but shows how to train them and compete with closed frontier models. OpenAI debuts Deep Research.

Significant milestones: DeepSeek R1 & R1-Zero, Qwen 2.5 VL, OpenAI Deep Research, Gemini 2.5 Pro (experimental)

2️⃣ Q2 — Multimodality and Coding
More LLMs embrace multimodality by default, and there's a surge in coding agents. Strong vision, audio, and generative models emerge.

Significant milestones: Llama 4, Qwen 3, Imagen 4, OpenAI Codex, Google Jules, Claude 4

3️⃣ Q3 — "Gold" rush, OpenAI opens up, the community goes bananas
Flagship models get gold in Math olympiads and hard benchmarks. OpenAI releases strong open source models and Google releases the much anticipated nano-banana for image generation and editing. Agentic workflows become commonplace.

Significant milestones: Gemini and OpenAI IMO Gold, gpt-oss, Gemini 2.5 Flash Image, Grok 4, Claude Sonnet 4.5

4️⃣ Q4 — Mistral returns, leaderboard hill-climbing
Mistral is back with updated model families. All labs release impressive models to wrap up the year!

Significant milestones: Claude Opus 4.5, DeepSeek Math V2, FLUX 2, GPT 5.1, Kimi K2 Thinking, Nano Banana Pro, GLM 4.7, Gemini 3, Mistral 3, MiniMax M2.1 🤯

Credits
🙏 NHLOCAL for the source data https://github.com/NHLOCAL/AiTimeline

🫡 @reach-vb for the original idea, design and recipe

🙌 @ariG23498 and yours truly for compiling and verifying the 2025 edition

🥳 Here's to 2026, wishing it becomes the best year ever for open releases and on-device-first use-cases! 🥂
  • 1 reply
·
Recently active users