Language Models

24 tasks in this category.

24 tasks
Task Category PackagesBaselines Envs Logs
llm-algorithm-16MqatLanguage Modelsllm-16m-qat-runtime33-
llm-dllm-demask-strategyLanguage ModelsLLaDA33
llm-hybrid-posttrainingLanguage Modelsverl41-
llm-offline-rlLanguage ModelsLLaMA-Factory, MathRuler, alpaca_eval23
llm-pretrain-attentionLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-bitlinearLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-embeddingLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-kernelLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-linear-attentionLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-lossLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-lr-scheduleLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-mlpLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-normalizationLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-optimizerLanguage Modelslm-evaluation-harness, nanoGPT32
llm-pretrain-residualLanguage Modelslm-evaluation-harness, nanoGPT42
llm-ptq-algorithmLanguage Modelsgptq33-
llm-qat-algorithmLanguage Modelsgptq33-
llm-rl-advantageLanguage Modelsverl31-
llm-rl-advantage-1.5b-probeLanguage Modelsverl11-
llm-rl-importance-samplingLanguage Modelsverl31-
llm-scaling-law-discoveryLanguage Modelsscaling-law-lab43-
llm-sft-lossLanguage ModelsLLaMA-Factory, lm-evaluation-harness42-
llm-ttrl-rewardLanguage Modelsttrl33-
llm-ttt-adaptationLanguage ModelsnanoGPT31-