Hugging Face's logo

BigScience Workshop

non-profit
https://bigscience.huggingface.co
bigscienceW
bigscience-workshop
Activity Feed

AI & ML interests

A one-year long research workshop on large language models: the Summer of Language Models 21 🌸

Recent Activity

christopher  new activity about 8 hours ago
bigscience/bloomz-p3:Adding `safetensors` variant of this model
shannons  authored a paper about 12 hours ago
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
lucmos  authored a paper 2 days ago
Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces
View all activity

bigscience's activity

christopher 
in bigscience/bloomz-p3 about 8 hours ago

Adding `safetensors` variant of this model

1
#3 opened about 15 hours ago by
SFconvertbot
shannons 
authored a paper about 12 hours ago
julien-c 
posted an update 2 days ago
view post
Post
2054
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.
gsarti 
authored a paper 7 days ago
davanstrien 
posted an update 13 days ago
view post
Post
2675
📊 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 14 days ago
view post
Post
3608
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
·
nguyenvulebinh 
authored a paper 15 days ago
yjernite 
authored a paper 16 days ago
IAugenstein 
authored a paper 16 days ago
stas 
posted an update 20 days ago
view post
Post
2078
Do you want ArcticTraining at @SnowflakeDB to add an ability to post-train DeepSeek V3/R1 models with DPO using just a few GPU nodes?

Please vote here and tell others about it: https://github.com/snowflakedb/ArcticTraining/discussions/58

ArcticTraining is an open-source, easy to use post-training framework for NVIDIA GPUs built on top of DeepSpeed.
IAugenstein 
authored a paper 20 days ago
davanstrien 
posted an update 21 days ago
view post
Post
2583
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
IAugenstein 
authored 8 papers 21 days ago