Hugging Face's logo

Webhooks Explorers (BETA)

community
https://huggingface.co/docs/hub/webhooks
Activity Feed Request to join this org

AI & ML interests

Webhooks are now publicly available on Hugging Face!

Recent Activity

osanseviero  authored a paper 18 days ago
Gemma 3 Technical Report
bpHigh  authored a paper 29 days ago
MMTEB: Massive Multilingual Text Embedding Benchmark
LihiShalmon  authored a paper about 1 month ago
More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG
View all activity

webhooks-explorers's activity

davanstrien 
posted an update 6 days ago
view post
Post
1486
I've created a v1 dataset ( davanstrien/reasoning-required) and model ( davanstrien/ModernBERT-based-Reasoning-Required) to help curate "wild text" data for generating reasoning examples beyond the usual code/math/science domains.

- I developed a "Reasoning Required" dataset with a 0-4 scoring system for reasoning complexity
- I used educational content from HuggingFaceFW/fineweb-edu, adding annotations for domains, reasoning types, and example questions

My approach enables a more efficient workflow: filter text with small models first, then use LLMs only on high-value content.

This significantly reduces computation costs while expanding reasoning dataset domain coverage.
nouamanetazi 
authored a paper 7 days ago
osanseviero 
authored a paper 18 days ago
chansung 
posted an update 20 days ago
view post
Post
3424
simple guide on the recipe for GRPO on Open-R1 which is built on top of TRL

I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!
·
emre 
authored a paper 22 days ago
emre 
posted an update 22 days ago
view post
Post
3284
having trouble with auto train
hello there this is the first time i am testing auto train with a 1.8k SFT dataset. Howevery i am not quite sure the training is going smooth. Logs seem quite confusing, token did not match can not auth, generates confusing train splits, do you know how i can check my running job properly?
what is being used for training as data?
any ideas?
  • 1 reply
·
chansung 
posted an update 26 days ago
view post
Post
2562
Mistral AI Small 3.1 24B is not only commercial free but also the best model in a single GPU deployment.

I packed up all the information you need to know in a single picture. Hope this helps! :)
  • 1 reply
·
bpHigh 
authored a paper 29 days ago
chansung 
posted an update about 1 month ago
view post
Post
1569
Gemma 3 Release in a nutshell
(seems like function calling is not supported whereas the announcement said so)
taesiri 
authored a paper about 1 month ago
davanstrien 
posted an update about 2 months ago
view post
Post
2919
📊 Introducing "Hugging Face Dataset Spotlight" 📊

I'm excited to share the first episode of our AI-generated podcast series focusing on nice datasets from the Hugging Face Hub!

This first episode explores mathematical reasoning datasets:

- SynthLabsAI/Big-Math-RL-Verified: Over 250,000 rigorously verified problems spanning multiple difficulty levels and mathematical domains
- open-r1/OpenR1-Math-220k: 220,000 math problems with multiple reasoning traces, verified for accuracy using Math Verify and Llama-3.3-70B models.
- facebook/natural_reasoning: 1.1 million general reasoning questions carefully deduplicated and decontaminated from existing benchmarks, showing superior scaling effects when training models like Llama3.1-8B-Instruct.

Plus a bonus segment on bespokelabs/bespoke-manim!

https://www.youtube.com/watch?v=-TgmRq45tW4
davanstrien 
posted an update about 2 months ago
view post
Post
3663
Quick POC: Turn a Hugging Face dataset card into a short podcast introducing the dataset using all open models.

I think I'm the only weirdo who would enjoy listening to something like this though 😅

Here is an example for eth-nlped/stepverify
  • 2 replies
·
davanstrien 
posted an update about 2 months ago
view post
Post
2630
Hacked together a way to log trl GRPO training completions to a 🤗 dataset repo. This allows you to:

- Track rewards from multiple reward functions
- Treat the completion and rewards from training as a "proper" dataset and do EDA
- Share results for open science

The implementation is super hacky, but I'm curious if people would find this useful.

To push completions to the Hub, you just need two extra parameters:

log_completions=True
log_completions_hub_repo='your-username/repo-name'

Example dataset: davanstrien/test-logs
Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g
taesiri 
authored a paper about 2 months ago
davanstrien 
posted an update about 2 months ago
davanstrien 
posted an update about 2 months ago
view post
Post
1964
How do you make 1M+ Hugging Face models & datasets more discoverable?

davanstrien/Smol-Hub-tldr!

I fine-tuned HuggingFaceTB/SmolLM2-360M to generate one-line summaries from a model or dataset README.

Its own self-description?
"A model for generating concise summaries of model & dataset cards from the Hugging Face Hub"

The goal? Make it easier to find the right models and datasets for your specific needs. It's already powering a semantic search for datasets Space.

It's still a WIP but thanks to @loubnabnl , @anton-l , @eliebak et al, for cooking such a nice base model for fine-tuning small, efficient models for specific domains and tasks. 🙏
davanstrien 
posted an update 2 months ago
chansung 
posted an update 2 months ago
view post
Post
3017
Simple Paper Review #5

I briefly reviewed the paper "SFT Memorizes, RL Generalizes," which compares SFT and RL in post-training of LLM/VLM from HKU, UC Berkeley, Google DeepMind, and New York University

The conclusion suggests SFT excels in memorization, while RL is better for generalization. However, since LLM/VLM should benefit humans beyond just generalization, a mix of SFT and RL is advisable. Typically, some SFT is followed by RL to understand prompt formats and enhance generalization through trial and error.

The study focused on one model, Llama-3.2-Vision-11B, using environments like General Points for arithmetic reasoning and V-IRL for spatial reasoning. Training data was used for both SFT and RL, with evaluations on in-distribution and out-of-distribution data to assess memorization and generalization.

I want to apply RL extensively, but it requires building a similar simulation environment. For domain-specific models, significant investment in creating a "playground" for the model is crucial, as the effort will directly influence the outcomes.

https://arxiv.org/abs/2501.17161
chansung 
posted an update 2 months ago
view post
Post
4388
A brief summary of the o3-mini

The OpenAI o3-mini model is a significant improvement over the o1-mini, reaching o1 performance levels. While generally good, its performance isn't universally better than previous models (o1, o1-prev.) or GPT-4o across all benchmarks. This means workflows should be re-evaluated with each model upgrade.

The o3-mini has "low," "medium," and "high" versions, with "low" being the base model used for benchmarking. It's speculated that the higher versions simply involve more processing. A fair comparison with other models like Gemini 2.0 Thinking or DeepSeek-R1 would likely need to use the "low" version and a similar "think more" mechanism.

The system card is recommended reading due to its comprehensive benchmark data.

https://openai.com/index/openai-o3-mini/
davanstrien 
posted an update 3 months ago