lunarflu (Adam Molnar)

reacted to merve's post with ❤️🔥👍🚀 1 day ago

Post

5140

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥

D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩

> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352

Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩

Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️

D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩

Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️

this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

2 replies

·

reacted to onekq's post with 🔥 8 days ago

Post

1989

AxB stand for Approximately xB or Activating xB (for a Mixture-of-Expert model), this is really interesting naming 😅

Qwen/Qwen3-235B-A22B
Qwen/Qwen3-30B-A3B

1 reply

·

reacted to anakin87's post with 👍 8 days ago

Post

3273

𝗜 𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝗮 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝘁𝗼 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗲𝘃𝗲𝗻𝘁𝘀 𝘄𝗶𝘁𝗵 𝗚𝗥𝗣𝗢! 👑 🗓️

✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo

I experimented with GRPO lately.

I am fascinated by models learning from prompts and rewards - no example answers needed like in Supervised Fine-Tuning.

After the DeepSeek boom, everyone is trying GRPO with GSM8K or the Countdown Game...

I wanted a different challenge, like 𝘁𝗲𝗮𝗰𝗵𝗶𝗻𝗴 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗮 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗳𝗿𝗼𝗺 𝗮 𝗹𝗶𝘀𝘁 𝗼𝗳 𝗲𝘃𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗽𝗿𝗶𝗼𝗿𝗶𝘁𝗶𝗲𝘀.

Choosing an original problem forced me to:
🤔 Think about the problem setting
🧬 Generate data
🤏 Choose the right base model
🏆 Design reward functions (and experiencing reward hacking)
🔄 Run multiple rounds of training, hoping that my model would learn something.

A fun and rewarding 😄 experience.

I learned a lot of things, that I want to share with you. 👇
✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo
💻 Code: https://github.com/anakin87/qwen-scheduler-grpo
🤗 Hugging Face collection (dataset and model): anakin87/qwen-scheduler-grpo-680bcc583e817390525a8837

2 replies

·

reacted to julien-c's post with 😎👍🚀🔥 16 days ago

Post

3742

Important notice 🚨

For Inference Providers who have built support for our Billing API (currently: Fal, Novita, HF-Inference – with more coming soon), we've started enabling Pay as you go (=PAYG)

What this means is that you can use those Inference Providers beyond the free included credits, and they're charged to your HF account.

You can see it on this view: any provider that does not have a "Billing disabled" badge, is PAYG-compatible.

9 replies

·

reacted to as-cle-bert's post with 🤗 17 days ago

Post

2973

Finding a job that matches with our resume shouldn't be difficult, especially now that we have AI... And still, we're drowning in unclear announcements, jobs whose skill requirements might not really fit us, and tons of material😵‍💫
That's why I decided to build 𝐑𝐞𝐬𝐮𝐦𝐞 𝐌𝐚𝐭𝐜𝐡𝐞𝐫 (https://github.com/AstraBert/resume-matcher), a fully open-source application that scans your resume and searches the web for jobs that match with it!🎉
The workflow is very simple:
🦙 A LlamaExtract agent parses the resume and extracts valuable data that represent your profile
🗄️The structured data are passed on to a Job Matching Agent (built with LlamaIndex😉) that uses them to build a web search query based on your resume
🌐 The web search is handled by Linkup, which finds the top matches and returns them to the Agent
🔎 The agent evaluates the match between your profile and the jobs, and then returns a final answer to you

So, are you ready to find a job suitable for you?💼 You can spin up the application completely locally and with Docker, starting from the GitHub repo ➡️ https://github.com/AstraBert/resume-matcher
Feel free to leave your feedback and let me know in the comments if you want an online version of Resume Matcher as well!✨

2 replies

·

reacted to AdinaY's post with 🚀 17 days ago

Post

3136

SkyReels-V2 🔥 UNLIMITED duration video generation model by Kunlun Tech-Skywork 天工

Paper: SkyReels-V2: Infinite-length Film Generative Model (2504.13074)
Model: Skywork/skyreels-v2-6801b1b93df627d441d0d0d9

✨ 1.3B & 14B
✨ Generates infinite length videos using Diffusion Forcing with diffusion models + autoregressive methods

1 reply

·

reacted to as-cle-bert's post with ❤️ 17 days ago

Post

2973

Finding a job that matches with our resume shouldn't be difficult, especially now that we have AI... And still, we're drowning in unclear announcements, jobs whose skill requirements might not really fit us, and tons of material😵‍💫
That's why I decided to build 𝐑𝐞𝐬𝐮𝐦𝐞 𝐌𝐚𝐭𝐜𝐡𝐞𝐫 (https://github.com/AstraBert/resume-matcher), a fully open-source application that scans your resume and searches the web for jobs that match with it!🎉
The workflow is very simple:
🦙 A LlamaExtract agent parses the resume and extracts valuable data that represent your profile
🗄️The structured data are passed on to a Job Matching Agent (built with LlamaIndex😉) that uses them to build a web search query based on your resume
🌐 The web search is handled by Linkup, which finds the top matches and returns them to the Agent
🔎 The agent evaluates the match between your profile and the jobs, and then returns a final answer to you

So, are you ready to find a job suitable for you?💼 You can spin up the application completely locally and with Docker, starting from the GitHub repo ➡️ https://github.com/AstraBert/resume-matcher
Feel free to leave your feedback and let me know in the comments if you want an online version of Resume Matcher as well!✨

2 replies

·

reacted to yjernite's post with 🔥 21 days ago

Post

3181

Today in Privacy & AI Tooling - introducing a nifty new tool to examine where data goes in open-source apps on 🤗

HF Spaces have tons (100Ks!) of cool demos leveraging or examining AI systems - and because most of them are OSS we can see exactly how they handle user data 📚🔍

That requires actually reading the code though, which isn't always easy or quick! Good news: code LMs have gotten pretty good at automatic review, so we can offload some of the work - here I'm using Qwen/Qwen2.5-Coder-32B-Instruct to generate reports and it works pretty OK 🙌

The app works in three stages:
1. Download all code files
2. Use the Code LM to generate a detailed report pointing to code where data is transferred/(AI-)processed (screen 1)
3. Summarize the app's main functionality and data journeys (screen 2)
4. Build a Privacy TLDR with those inputs

It comes with a bunch of pre-reviewed apps/Spaces, great to see how many process data locally or through (private) HF endpoints 🤗

Note that this is a POC, lots of exciting work to do to make it more robust, so:
- try it: yjernite/space-privacy
- reach out to collab: yjernite/space-privacy

reacted to jsulz's post with 🚀🔥👀 27 days ago

Post

995

As

xet-team infrastructure begins backing hundreds of repositories on the Hugging Face Hub, we’re getting to put on our researcher hats and peer into the bytes. 👀 🤓

IMO, one of the most interesting ideas Xet storage introduces is a globally shared store of data.

When you upload a file through Xet, the contents are split into ~64KB chunks and deduplicated, but what if those same chunks already exist in another repo on the Hub?

If we can detect and reuse them, we skip them as well saving time and bandwidth for AI builders. More on how that works here:
🔗 https://huggingface.co/blog/from-chunks-to-blocks#scaling-deduplication-with-aggregation

Because of this, different repositories can share bytes we store. That opens up something cool - we can draw a graph of which repos actually share data at the chunk level, where:

- Nodes = repositories
- Edges = shared chunks
- Edge thickness = how much they overlap

xet-team/repo-graph

Come find the many BERT islands. Or see how datasets relate in practice, not just in theory. See how libraries or tasks can tie repositories together. You can play around with node size using storage/likes/downloads too.

The result is a super fun visualization from @saba9 and @znation that I’ve already lost way too much time to. I'm excited to see how the networks grow as we add more repositories!

reacted to merterbak's post with ❤️👀🔥 29 days ago

Post

4743

Qwen 3 can launch very soon. 👀

https://github.com/ggml-org/llama.cpp/pull/12828

3 replies

·

Adam Molnar

AI & ML interests

Recent Activity

Organizations

lunarflu's activity