BigScience Workshop

non-profit

https://bigscience.huggingface.co

bigscience-workshop

AI & ML interests

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

Recent Activity

christopher new activity 13 days ago

bigscience/bloom:[SPAM] Deleted

christopher new activity 20 days ago

bigscience/bloom:pretokenizer Regex issues?

christopher new activity 25 days ago

bigscience/bloom:Test PR

View all activity

RTT1

authored a paper 8 days ago

EvoClaw: Evaluating AI Agents on Continuous Software Evolution

Paper • 2603.13428 • Published 13 days ago • 20

authored 3 papers 9 days ago

Agentic Uncertainty Reveals Agentic Overconfidence

Paper • 2602.06948 • Published Feb 6

Complex Query Answering with Neural Link Predictors

Paper • 2011.03459 • Published Nov 6, 2020

Rethinking the Harmonic Loss via Non-Euclidean Distance Layers

Paper • 2603.10225 • Published 15 days ago

in bigscience/bloom 13 days ago

[SPAM] Deleted

#289 opened 13 days ago by

stas

posted an update 15 days ago

Post

183

Good news! Ulysses Sequence Parallelism from the Snowflake AI Research and the Deepspeed teams has been integrated into
HuggingFace Trainer, Accelerate and TRL

For extensive details please see this writeup:
https://huggingface.co/blog/ulysses-sp

Thanks a lot to Kashif Rasul for helping make it happen. Also the others in the HF team who helped with integration.

in bigscience/bloom 20 days ago

pretokenizer Regex issues?

#278 opened over 1 year ago by

in bigscience/bloom 25 days ago

Test PR

#286 opened 25 days ago by

Test discussion

#287 opened 25 days ago by

Test discussion

#288 opened 25 days ago by

submitted a paper to Daily Papers 28 days ago

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking

Paper • 2602.21196 • Published 29 days ago • 5

submitted 2 papers to Daily Papers about 1 month ago

Single-minus gluon tree amplitudes are nonzero

Paper • 2602.12176 • Published Feb 12 • 8

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL

Paper • 2602.03773 • Published Feb 3 • 12

RTT1

submitted a paper to Daily Papers about 1 month ago

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

Paper • 2602.07075 • Published Feb 6 • 18

stas

authored a paper about 2 months ago

Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences

Paper • 2506.13996 • Published Jun 16, 2025 • 1

in bigscience/bloomz-560m 4 months ago

Fails to load with transformers v4.57+

#14 opened 4 months ago by

in bigscience/petals-api 4 months ago

Bloom

#2 opened 4 months ago by

authored a paper 4 months ago

Grounding Computer Use Agents on Human Demonstrations

Paper • 2511.07332 • Published Nov 10, 2025 • 107

authored a paper 5 months ago

OpenSIR: Open-Ended Self-Improving Reasoner

Paper • 2511.00602 • Published Nov 1, 2025 • 21

authored a paper 5 months ago

Language Models are Injective and Hence Invertible

Paper • 2510.15511 • Published Oct 17, 2025 • 70