| | MosaicBERT: Pretraining Bert from Scratch for $20 (mosaicml.com) |
| 4 points by ashvardanian on Jan 2, 2024 | past | 1 comment |
|
| | Llama2-70B with MosaicML Inference (mosaicml.com) |
| 2 points by fzliu on Aug 24, 2023 | past | 1 comment |
|
| | MPT-7B-8K: 8K Context Length for Document Understanding (mosaicml.com) |
| 3 points by brianjking on July 18, 2023 | past | 1 comment |
|
| | Training LLMs with AMD MI250 GPUs (mosaicml.com) |
| 28 points by tboerstad on July 1, 2023 | past | 2 comments |
|
| | Training LLMs with AMD MI250 GPUs and MosaicML (mosaicml.com) |
| 15 points by tasubotadas on June 30, 2023 | past | 3 comments |
|
| | Databricks acquires OpenAI Competitor MosaicML for 1.3B (mosaicml.com) |
| 3 points by sandkoan on June 27, 2023 | past |
|
| | MosaicML Agrees to Join Databricks to Power Generative AI for All (mosaicml.com) |
| 3 points by tim_sw on June 26, 2023 | past |
|
| | MPT-30B: Raising the bar for open-source foundation models (mosaicml.com) |
| 34 points by hansonw on June 22, 2023 | past | 2 comments |
|
| | Training Stable Diffusion from Scratch Costs <$160k (mosaicml.com) |
| 3 points by mooreds on June 13, 2023 | past |
|
| | Training Stable Diffusion from Scratch for <$50k with MosaicML (mosaicml.com) |
| 3 points by sdht0 on May 8, 2023 | past |
|
| | MosaicML MPT-7B: A Commercially-Usable LLaMa-Quality Model (mosaicml.com) |
| 119 points by ml_hardware on May 5, 2023 | past | 11 comments |
|
| | Revolutionalize ML Training – MosiacML (mosaicml.com) |
| 2 points by zachllama on April 29, 2023 | past | 2 comments |
|
| | We Trained Stable Diffusion for Less Than $50k (mosaicml.com) |
| 2 points by tim_sw on April 28, 2023 | past |
|
| | Benchmarking Large Language Models on Nvidia H100 GPUs (mosaicml.com) |
| 3 points by tim_sw on April 28, 2023 | past |
|
| | Training Stable Diffusion from Scratch for <$50k with MosaicML (mosaicml.com) |
| 4 points by GaggiX on April 27, 2023 | past | 2 comments |
|
| | Training Stable Diffusion from Scratch for <$50k (mosaicml.com) |
| 6 points by ollin on April 26, 2023 | past | 2 comments |
|
| | MosaicBERT: Pretraining Bert from Scratch for $20 (mosaicml.com) |
| 2 points by eureka_universe on March 13, 2023 | past | 1 comment |
|
| | Training Stable Diffusion from Scratch Costs <$160k (mosaicml.com) |
| 98 points by moinnadeem on Jan 25, 2023 | past | 48 comments |
|
| | PubMed GPT: A Domain-Specific Large Language Model for Biomedical Text (mosaicml.com) |
| 24 points by sebg on Dec 15, 2022 | past |
|
| | GPT-3 quality models for $450k (mosaicml.com) |
| 1 point by ml_hardware on Oct 5, 2022 | past |
|
| | Training GPT-3 Quality Models For $450k (mosaicml.com) |
| 2 points by ml_hardware on Sept 30, 2022 | past | 1 comment |
|
| | Training billion-parameter GPTs with MosaicML (mosaicml.com) |
| 2 points by ml_hardware on Aug 11, 2022 | past |
|
| | Farewell, CUDA OOM: Automatic Gradient Accumulation (mosaicml.com) |
| 4 points by ffast-math on June 23, 2022 | past |
|
| | 7x faster ML training by standing on the shoulders of giants (mosaicml.com) |
| 2 points by dskhudia on June 10, 2022 | past |
|
| | 7.1x faster ImageNet ResNet-50 in 27 minutes (mosaicml.com) |
| 5 points by averylamp on June 9, 2022 | past |
|
| | MosaicML Algorithmic ML Improvements for Model Speedups (mosaicml.com) |
| 4 points by averylamp on Oct 13, 2021 | past |
|
| | MosaicML Explorer: Train ResNet101 4x faster with algorithmic methods (mosaicml.com) |
| 24 points by moinnadeem on Oct 13, 2021 | past |
|
