BigScienceLLM Profile Banner
BigScience Large Model Training Profile
BigScience Large Model Training

@BigScienceLLM

Followers
9K
Following
49
Media
5
Statuses
129

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

JeanZay supercomputer (France)
Joined March 2022
Don't wanna be here? Send us removal request.
@BigScienceLLM
BigScience Large Model Training
3 years
The BLOOM model is now officially released!. Read more here: Find the model here:
@BigscienceW
BigScience Research Workshop
3 years
BLOOM is here. The largest open-access multilingual language model ever. Read more about it or get it at.
Tweet media one
6
64
254
@BigScienceLLM
BigScience Large Model Training
3 years
RT @ClementDelangue: The Bloom paper is out. Looks like it's doing worse than current GPT3 API in zero-shot generation tasks in English but….
0
105
0
@BigScienceLLM
BigScience Large Model Training
3 years
RT @Muennighoff: Crosslingual Generalization through Multitask Finetuning 🌸. Demo: πŸ“œ πŸ’»http….
0
78
0
@BigScienceLLM
BigScience Large Model Training
3 years
The super-fast inference solutions are finally here for all to use:.
@StasBekman
Stas Bekman
3 years
Learn how you can get under 1msec per token generation time with BLOOM 176B model!. Not one, but multiple super-fast solutions including Deepspeed-Inference, Accelerate and Deepspeed-ZeRO!.
1
2
29
@BigScienceLLM
BigScience Large Model Training
3 years
RT @ClementDelangue: What do @StabilityAI @EMostaque #stablediffusion & @BigscienceW Bloom - aka the coolest new models ;) - have in common….
0
36
0
@BigScienceLLM
BigScience Large Model Training
3 years
RT @huggingface: The Technology Behind BLOOM Training🌸. Discover how @BigscienceW used @MSFTResearch DeepSpeed + @nvidia Megatron-LM techno….
0
148
0
@BigScienceLLM
BigScience Large Model Training
3 years
RT @BigscienceW: BLOOM is here. The largest open-access multilingual language model ever. Read more about it or get it at..
0
779
0
@BigScienceLLM
BigScience Large Model Training
3 years
RT @LucileSaulnier: 🌸@BigscienceW BLOOM's intermediate checkpoints have already shown some very cool capabilities! . What's great about BLO….
0
25
0
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 102%.
15
6
178
@BigScienceLLM
BigScience Large Model Training
3 years
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 ;).
3
25
306
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 101%.
68
78
988
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 100%.
44
310
2K
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 99%.
16
75
736
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 98%.
4
13
231
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“ 97%.
2
8
169
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–‘ 96%.
1
2
80
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–‘ 95%.
1
8
175
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–‘ 94%.
6
1
78
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–‘ 92%.
2
8
169
@BigScienceLLM
BigScience Large Model Training
3 years
β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–“β–‘ 91%.
0
1
59