Pinned Repositories
composer
Train neural networks up to 7x faster
examples
Fast and flexible reference benchmarks
hash-hop
Long context evaluation for large language models
inference_benchmarking
llm-foundry
LLM training code for Databricks foundation models
lm-evaluation-harness-composergpt-integration
A framework for few-shot evaluation of autoregressive language models.
loss_spike_prediction
NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
the-fine-tuning-mitten
composer
Supercharge Your Model Training
bmosaicml's Repositories
bmosaicml/composer
Train neural networks up to 7x faster
bmosaicml/examples
Fast and flexible reference benchmarks
bmosaicml/hash-hop
Long context evaluation for large language models
bmosaicml/inference_benchmarking
bmosaicml/llm-foundry
LLM training code for Databricks foundation models
bmosaicml/lm-evaluation-harness-composergpt-integration
A framework for few-shot evaluation of autoregressive language models.
bmosaicml/loss_spike_prediction
bmosaicml/NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
bmosaicml/the-fine-tuning-mitten