Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
mrfakename  new activity 8 days ago
zero-gpu-explorers/README:Why doesn't anyone host llms in zerogpu spaces?
nroggendorff  new activity 10 days ago
zero-gpu-explorers/README:Why doesn't anyone host llms in zerogpu spaces?
limingcv  authored a paper 10 days ago
Seedance 2.0: Advancing Video Generation for World Complexity
View all activity
Tonic 
posted an update 3 days ago
view post
Post
3195
🙋🏻‍♂️ Hey there folks ,

I'm sharing huggingface's largest dataset of annotated statelite images today.

check it out here : NuTonic/sat-image-boundingbox-sft-full

I hope you like it , the idea is to be able to use this with small vision models 🚀
akhaliq 
submitted a paper to Daily Papers 3 days ago
mrfakename 
in zero-gpu-explorers/README 8 days ago

Why doesn't anyone host llms in zerogpu spaces?

8
#172 opened 10 days ago by
Reality123b
nroggendorff 
in zero-gpu-explorers/README 10 days ago

Why doesn't anyone host llms in zerogpu spaces?

8
#172 opened 10 days ago by
Reality123b
sergiopaniego 
posted an update 11 days ago
view post
Post
1177
Earlier this month, Apple introduced Simple Self-Distillation: a fine-tuning method that improves models on coding tasks just by sampling from the model and training on its own outputs with plain cross-entropy

And… it's already supported in TRL, built by Kashif Rasul. you can really feel the pace of development in the team 🐎

Paper by Ruixiang ZHANG, He Bai, Huangjie Zheng, Navdeep Jaitly, Ronan Collobert, Yizhe Zhang at Apple 🍎

How it works: the model generates completions at a training-time temperature (T_train) with top_k/top_p truncation, then fine-tunes on them with plain cross-entropy. no labels or verifier needed

You can try it right away with this ready-to-run example (Qwen3-4B on rStar-Coder):
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd.py
or benchmark a checkpoint with the eval script:
https://github.com/huggingface/trl/blob/main/trl/experimental/ssd/ssd_eval.py

One neat insight from the paper: T_train and T_eval compose into an effective T_eff = T_train × T_eval, so a broad band of configs works well. even very noisy samples still help

Want to dig deeper?

Paper: Embarrassingly Simple Self-Distillation Improves Code Generation (2604.01193)
Trainer docs: https://huggingface.co/docs/trl/main/en/ssd_trainer
qnguyen3 
authored a paper 16 days ago
sergiopaniego 
posted an update 17 days ago
chengtim 
authored a paper 19 days ago
akhaliq 
submitted a paper to Daily Papers 23 days ago
chengtim 
submitted a paper to Daily Papers 24 days ago
sergiopaniego 
posted an update 24 days ago
sergiopaniego 
posted an update 26 days ago
view post
Post
2031
TRL is officially an adult 🥳

excited to announce TRL v1.0❗️

head to the blog to see how we got here and what’s next for this post-training library, designed to keep pace with the field

https://huggingface.co/blog/trl-v1
  • 2 replies
·
akhaliq 
submitted a paper to Daily Papers about 1 month ago
Severian 
posted an update about 1 month ago
view post
Post
4435
I’ve been working on a new mathematical approach to real-time video compositing and background removal, and I wanted to share a live demo.

Traditionally, real-time keyers either use 3D color-space bounding boxes (which struggle with semi-transparent hair and motion blur) or heavy Machine Learning models (which require massive GPU compute and often suffer from temporal "jitter" on the edges).

I wanted to see if I could solve this using purely deterministic math so it could run client-side in a standard browser.

The engine uses a custom mathematical framework I call CMT SRL SEFA. Instead of looking at raw color values or guessing semantics like an AI, it treats the video feed as complex-encoded sequences. It uses harmonic frequencies to map phase geometry and applies a "Stability Cost Function" to find the global minimum stability. In short: it isolates the foreground from the background by measuring signal complexity and structural contradictions.

Give it a try using your own messy plates and such. As I am not a VFX artist, I am curious to hear thoughts and what should be improved upon and made better

https://severian-cmt-sefa-realtime-vfx-keyer.hf.space/
  • 2 replies
·
MykolaL 
authored 3 papers about 1 month ago
akhaliq 
submitted 2 papers to Daily Papers about 1 month ago
sergiopaniego 
posted an update about 1 month ago
view post
Post
794
ICYMI, great blog by @kashif and @stas on Ulysses Sequence Parallelism: train with million-token contexts

on 4×H100s: 12x longer sequences, 3.7x throughput

learn how to integrate it with Accelerate, Transformers, and TRL ⤵️
https://huggingface.co/blog/ulysses-sp