BigScience Large Model Training (@bigsciencellm) 's Twitter Profile
BigScience Large Model Training

@bigsciencellm

Follow the training of "BLOOM ๐ŸŒธ", the @BigScienceW multilingual 176B parameter open-science open-access language model, a research tool for the AI community.

ID: 1502036410081202180

linkhttps://bigscience.notion.site/BigScience-176B-Model-Training-ad073ca07cdf479398d5f95d88e218c4 calendar_today10-03-2022 21:40:30

129 Tweet

8,8K Takipรงi

1 Takip Edilen

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–‘ 91%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–‘ 92%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–‘ 94%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–‘ 95%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–‘ 96%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“ 97%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“ 98%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“ 99%

Saulnier Lucile (@lucilesaulnier) 's Twitter Profile Photo
Saulnier Lucile
@lucilesaulnier

3 years ago

๐ŸŒธBigScience Research Workshop 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! ๐Ÿ‘ถ ๐Ÿงต A thread with some examples

๐ŸŒธ<a href="/BigscienceW/">BigScience Research Workshop</a> 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! ๐Ÿ‘ถ ๐Ÿงต A thread with some examples
BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“ 100%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“ 101%

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
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, @INS2I_CNRS, Megatron & DeepSpeed. Having reached our objective earlier than expected, we'll keep training for a few more days. Stay tuned, more soon ;)

BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“โ–“ 102%

BigScience Research Workshop (@bigsciencew) 's Twitter Profile Photo
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/bloโ€ฆ

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/bloโ€ฆ
Hugging Face (@huggingface) 's Twitter Profile Photo
Hugging Face
@huggingface

3 years ago

The Technology Behind BLOOM Training๐ŸŒธ Discover how BigScience Research Workshop used Microsoft Research DeepSpeed + NVIDIA Megatron-LM technologies to train the World's Largest Open Multilingual Language Model (BLOOM): huggingface.co/blog/bloom-megโ€ฆ

clem ๐Ÿค— (@clementdelangue) 's Twitter Profile Photo
clem ๐Ÿค—
@clementdelangue

3 years ago

What do Stability AI Emad #stablediffusion & BigScience Research Workshop 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

What do <a href="/StabilityAI/">Stability AI</a> <a href="/EMostaque/">Emad</a> #stablediffusion &amp; <a href="/BigscienceW/">BigScience Research Workshop</a> Bloom - aka the coolest new models ;) - have in common? They both use a new gen of ML licenses aimed at making ML more open &amp; inclusive while keeping it harder to do harm with them. So cool! huggingface.co/blog/open_rail
BigScience Large Model Training (@bigsciencellm) 's Twitter Profile Photo
BigScience Large Model Training
@bigsciencellm

3 years ago

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

Niklas Muennighoff (@muennighoff) 's Twitter Profile Photo
Niklas Muennighoff
@muennighoff

3 years ago

Crosslingual Generalization through Multitask Finetuning ๐ŸŒธ Demo: huggingface.co/bigscience/bloโ€ฆ ๐Ÿ“œ arxiv.org/abs/2211.01786 ๐Ÿ’ปgithub.com/bigscience-worโ€ฆ We present BLOOMZ & mT0, a family of models w/ up to 176B params that follow human instructions in >100 languages zero-shot. 1/7

Crosslingual Generalization through Multitask Finetuning ๐ŸŒธ Demo: huggingface.co/bigscience/bloโ€ฆ ๐Ÿ“œ arxiv.org/abs/2211.01786 ๐Ÿ’ปgithub.com/bigscience-worโ€ฆ We present BLOOMZ &amp; mT0, a family of models w/ up to 176B params that follow human instructions in &gt;100 languages zero-shot. 1/7
clem ๐Ÿค— (@clementdelangue) 's Twitter Profile Photo
clem ๐Ÿค—
@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

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 &amp; better than all in zs multi-lingual (which was the main goal). Proud of the work from the community! arxiv.org/abs/2211.05100