BigScience Large Model Training @BigScienceLLM

Follow the training of "BLOOM 🌸", the @BigScienceW multilingual 176B parameter open-science open-access language model, a research tool for the AI community. bigscience.notion.site/BigScience-176… JeanZay supercomputer (France) Joined March 2022

Tweets

129
Followers

9K
Following

1
Likes

49

clem 🤗 @ClementDelangue

3 years ago

The Bloom paper is out. Looks like it's doing worse than current GPT3 API in zero-shot generation tasks in English but better than other open-source LLMs & better than all in zs multi-lingual (which was the main goal). Proud of the work from the community! arxiv.org/abs/2211.05100

11 105 595 0 119

Download Image

Niklas Muennighoff @Muennighoff

3 years ago

Crosslingual Generalization through Multitask Finetuning 🌸 Demo: huggingface.co/bigscience/blo… 📜 arxiv.org/abs/2211.01786 💻github.com/bigscience-wor… We present BLOOMZ & mT0, a family of models w/ up to 176B params that follow human instructions in >100 languages zero-shot. 1/7

10 77 286 0 60

Download Image

BigScience Large Model Training @BigScienceLLM

3 years ago

The super-fast inference solutions are finally here for all to use:

Stas Bekman @StasBekman

3 years ago

The super-fast inference solutions are finally here for all to use:

4 57 321 0 85

1 2 32 0 2

clem 🤗 @ClementDelangue

3 years ago

What do @StabilityAI @EMostaque #stablediffusion & @BigscienceW Bloom - aka the coolest new models ;) - have in common? They both use a new gen of ML licenses aimed at making ML more open & inclusive while keeping it harder to do harm with them. So cool! huggingface.co/blog/open_rail

8 36 179 0 29

Download Image

Hugging Face @huggingface

3 years ago

The Technology Behind BLOOM Training🌸 Discover how @BigscienceW used @MSFTResearch DeepSpeed + @nvidia Megatron-LM technologies to train the World's Largest Open Multilingual Language Model (BLOOM): huggingface.co/blog/bloom-meg…

8 149 613 0 148

BigScience Research Workshop @BigscienceW

3 years ago

BLOOM is here. The largest open-access multilingual language model ever. Read more about it or get it at bigscience.huggingface.co/blog/bloom hf.co/bigscience/blo…

29 777 3K 0 441

Download Image

Saulnier Lucile @LucileSaulnier

3 years ago

🌸@BigscienceW BLOOM's intermediate checkpoints have already shown some very cool capabilities! What's great about BLOOM is that you can ask it to generate the rest of a text - and this even if it is not yet fully trained yet! 👶 🧵 A thread with some examples

Saulnier Lucile @LucileSaulnier

3 years ago

0 0 15 0 1

5 25 146 0 18

Download Image

BigScience Large Model Training @BigScienceLLM

3 years ago

▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ 102%

15 6 178 0 1

BigScience Large Model Training @BigScienceLLM

3 years ago

For 111 days, we've enjoyed world-class hardware stability and throughput thanks to the hard work of our friends at @Genci_fr, @INS2I_CNRS, Megatron & DeepSpeed. Having reached our objective earlier than expected, we'll keep training for a few more days. Stay tuned, more soon ;)