Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
danielhanchen 
posted an update 2 days ago
yeonseok-zeticai 
posted an update 1 day ago
view post
Post
1273
πŸš€ NEW DROP: run your own on-device LLMβ€”in minutes, on any phone
Today we’re open-sourcing everything you need to put Qwen3-0.6B straight into a production-ready mobile app:

πŸŽ₯ Watch Qwen3-0.6B chat in real time on any smartphones!

πŸ“Š TPS benchmarks – slides comparing token-per-second across heterogeneous mobile devices

πŸ’» Plug-and-play source – Just Copy & Run the source to your project for Android (Kotlin & Java) and iOS (Swift).

🀞 Cross-platform, one pipeline – ZETIC.MLange auto-tunes kernels for every different devices, we’ve tested.

πŸ‘¨β€πŸ’» Ready for production – swap in your own model, re-benchmark with one command, publish.

Get started
Just Sign-up and check the playground project, QWEN-0.6B
- https://mlange.zetic.ai/p/zetic-example/Qwen3-0.6B

We built this to show that cloud-free LLMs are ready today. Dive in, fork it, and tag ZETIC.ai when you launch your own on-device assistant, game NPC, or offline content generatorβ€”we’ll spotlight the best projects.
VirtualOasis 
posted an update 1 day ago
view post
Post
1860
I built an AI Website: ai-garden.netlify.app
It is a curated garden of AI resources.
It's my database for writing and research, organized by category and designed for quick access. Whether you're looking for learning materials, development tools, research papers, or industry news, everything's laid out in a clean, searchable format.

Feel free to suggest new resources or improvements - this garden grows better with community input. 🍻
Β·
danaaubakirova 
posted an update 1 day ago
azettl 
posted an update 2 days ago
view post
Post
1518
Agents & MCP Hackathon Day 1

Before starting with the second night of the Agents & MCP Hackathon, I briefly wanted to share my progress from last night. Not much sleep, but lots of progress!

So I managed to build the first MVP version of my custom Gradio component, azettl/gradio_consilium_roundtable (https://pypi.org/project/gradio-consilium-roundtable/). This creates a visual roundtable component for AI consensus discussions. Displays AI participants as avatars positioned around an oval table (poker style!) with animated speech bubbles, thinking states, and real-time discussion updates.

Also, I managed to get a rough draft of the Gradio app + MCP server done, but not so much yet that I can share the space with you. You will be able to define your question the AI participants should discuss, decide on the protocol, do role assignments like having a devil's advocate on the table, and define the communication pattern. Lastly, you can decide which AI should be the moderator and how many rounds of discussions there should be. You can see my progress in the attached image.

Most of the options are just placeholders right now, and I will work on their implementation tonight. Hopefully, I can add an MVP tomorrow evening to the following space: https://huggingface.co/spaces/Agents-MCP-Hackathon/consilium_mcp.

I am also very interested in the cool stuff you all are building; please let me know in the comments. :)
  • 1 reply
Β·
danieldk 
posted an update about 10 hours ago
view post
Post
221
We have been working on a project called kernels. kernels makes it possible to load compute kernels directly from the Hub! πŸš€

We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release:

- New layer API with torch.compile support.
- Experimental support for loading Apple Silicon Metal Kernels.
- Generate wheels from Hub kernels for legacy deployments.

Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0
attackerElvies 
posted an update 1 day ago
view post
Post
1419
HALOOO MY COMMUNITY
shivance 
posted an update 1 day ago
view post
Post
1376
The AI Memory Layer Will Change Everything ‼️

Why do even the smartest AIs like OpenAI's o3 and GPT-4o, Google's Gemini and Anthropic's Claude forget?

In this blog we unpack this challenge and explore how building a real memory into AI will redefine personalization and agent capabilities!

https://fullstackagents.substack.com/p/forget-me-not-the-ai-memory-layer
ProCreations 
posted an update 2 days ago
view post
Post
2186
60 followers,
yay
  • 2 replies
Β·
codelion 
posted an update 3 days ago
view post
Post
3264
🧠 We just implemented Andrej Karpathy's "third paradigm" for LLM learning!

System Prompt Learning (SPL) enables LLMs to automatically learn problem-solving strategies from experience, rather than relying on static prompts.

πŸš€ How it works:
Your LLM builds a database of effective strategies, selects the best ones for each problem, and refines them over time based on success rates.

πŸ“Š Results across math benchmarks:
Arena Hard: 29% β†’ 37.6% (+8.6%)
AIME24: 23.33% β†’ 30% (+6.67%)
OptILLMBench: 61% β†’ 65% (+4%)

The best part? All strategies are human-readable and the system gets progressively better at problem types you use frequently.

✨ Key benefits:
πŸ”„ Cumulative learning over time
πŸ“– Transparent, inspectable strategies
πŸ”Œ Works with any OpenAI-compatible API
⚑ Simple integration: just add "spl-" prefix to your model

Built as an open-source plugin in optillm. After 500 queries, our system developed 129 strategies and refined 97 of them!

This feels like a genuine step toward AI that learns from experience while staying completely interpretable.

πŸ”— GitHub: https://github.com/codelion/optillm/tree/main/optillm/plugins/spl
πŸ“– Full article: https://huggingface.co/blog/codelion/system-prompt-learning
🐦 Original Karpathy tweet: https://x.com/karpathy/status/1921368644069765486

Have you experimented with advanced system prompting? What strategies would you want your LLM to learn?
Recently active users