Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

Webhooks are now publicly available on Hugging Face!

Recent Activity
xianbao  submitted a paper 1 day ago
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
victor  submitted a paper 16 days ago
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
chansung  authored a paper 24 days ago
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
View all activity
victor 
submitted a paper to Daily Papers 16 days ago
chansung 
authored a paper 24 days ago
chansung 
submitted a paper to Daily Papers 24 days ago
julien-c 
submitted a paper to Daily Papers about 1 month ago
victor 
posted an update about 1 month ago
view post
Post
1202
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it 👀

https://huggingface.co/blog/upskill
victor 
posted an update 3 months ago
mrfakename 
posted an update 3 months ago
view post
Post
17776
Excited to share that I've joined the Hugging Face Fellows program! 🤗

Looking forward to contributing to & working more closely with the open-source ecosystem - huge thanks to everyone who's supported me on this journey! 🚀
nouamanetazi 
posted an update 4 months ago
view post
Post
4555
After training 𝐒𝐦𝐨𝐥𝐋𝐌𝟑 on 𝟑𝟖𝟒 𝐇𝟏𝟎𝟎𝐬 for nearly a month, I've come to realize something most people overlook: 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐦𝐚𝐤𝐞-𝐨𝐫-𝐛𝐫𝐞𝐚𝐤 𝐟𝐚𝐜𝐭𝐨𝐫 𝐢𝐧 𝐋𝐋𝐌 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠. 🔥

Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious 𝐍𝐂𝐂𝐋 𝐞𝐫𝐫𝐨𝐫𝐬, or when your expensive GPU cluster is running at 𝟔𝟎% 𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲, the problem isn't your model. It's most probably a 𝐦𝐢𝐬𝐮𝐬𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐡𝐚𝐫𝐝𝐰𝐚𝐫𝐞. 🛠️

Questions that seemed simple but had no clear answers: Why is 𝐌𝐨𝐄 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐬𝐥𝐨𝐰𝐞𝐫 𝐭𝐡𝐚𝐧 𝐝𝐞𝐧𝐬𝐞 𝐦𝐨𝐝𝐞𝐥𝐬? Which 𝐍𝐂𝐂𝐋 𝐟𝐥𝐚𝐠𝐬 should we actually set? How often should we checkpoint without killing throughput?

That's why we built 𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤 📖: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐥𝐚𝐲𝐞𝐫 that most teams get wrong.

We validated real vs theoretical bandwidth across the entire stack: 𝐇𝐁𝐌𝟑 𝐡𝐢𝐭𝐭𝐢𝐧𝐠 𝟑 𝐓𝐁/𝐬, 𝐍𝐕𝐋𝐢𝐧𝐤 𝟒.𝟎 𝐫𝐞𝐚𝐜𝐡𝐢𝐧𝐠 𝟕𝟖𝟔 𝐆𝐁/𝐬, 𝐏𝐂𝐈𝐞 𝐆𝐞𝐧𝟒 𝐚𝐭 𝟏𝟒.𝟐 𝐆𝐁/𝐬. Then we ran collective operations across 𝟏𝟐𝟖 𝐆𝐏𝐔𝐬 (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from 𝟒𝟖𝟎 𝐆𝐁/𝐬 on a single node to 𝟑𝟐𝟎-𝟑𝟓𝟎 𝐆𝐁/𝐬 across 16 nodes.

If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.

𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤: https://lnkd.in/e5MKXUHS

Shared with ❤️ by the HuggingFace team
Zaid 
authored a paper 4 months ago
mrfakename 
posted an update 5 months ago
view post
Post
6289
Trained a model for emotion-controllable TTS based on MiMo audio on LAION's dataset.

Still very early and does have an issue with hallucinating but results seem pretty good so far, given that it is very early into the training run.

Will probably kick off a new run later with some settings tweaked.

Put up a demo here: https://huggingface.co/spaces/mrfakename/EmoAct-MiMo

(Turn 🔊 on to hear audio samples)
·
Zaid 
authored a paper 5 months ago
osanseviero 
authored a paper 6 months ago
davanstrien 
posted an update 6 months ago
chansung 
posted an update 8 months ago
view post
Post
4670
YAML engineering becomes more and more important than ever from infra provisioning to model training (recipes).

Here, I built a simple editor first for @dstackai , and I will share the live endpoint this week. Let me know what you think about this approach.

Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.
victor 
posted an update 9 months ago
view post
Post
7619
Open Source Avengers, Assemble! Ask an expert AI agent team to solve complex problems together 🔥

Consilium brings together multiple agents that debate and use live research (web, arXiv, SEC) to reach a consensus. You set the strategy, they find the answer.

Credit to @azettl for this awesome demo: Agents-MCP-Hackathon/consilium_mcp
  • 2 replies
·
lidiya 
authored a paper 9 months ago
davanstrien 
posted an update 9 months ago
view post
Post
3713
Inspired by Hugging Face's official MCP server, I've developed a complementary tool that exposes my semantic search API to enhance discovery across the HF platform.

Key capabilities:

- AI-powered semantic search for models and datasets
- Parameter count analysis via safetensors metadata
- Trending content discovery
- Find similar models/datasets functionality
- 11 tools total for enhanced ecosystem navigation

The semantic search goes beyond simple keyword matching, understanding context and relationships between different models and datasets.

Example query: "Find around 10 reasoning Hugging Face datasets published in 2025 focusing on topics other than maths and science. Show a link and a short summary for each dataset." (results in video!)

https://github.com/davanstrien/hub-semantic-search-mcp
  • 1 reply
·
Zaid 
authored 3 papers 10 months ago