BigScience Workshop

Popular repositories

1. petals Public

   🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

   Python 3k 86

2. promptsource Public

   Toolkit for creating, sharing and using natural language prompts.

   Python 1.1k 199

3. bigscience Public

   Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

   Shell 505 49

4. Megatron-DeepSpeed Public

   Ongoing research training transformer language models at scale, including: BERT & GPT-2

   Python 355 82

5. t-zero Public

   Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)

   Python 295 46

6. biomedical Public

   Tools for curating biomedical training data for large-scale language modeling

   Python 257 89