trinity.common package#
Subpackages#
- trinity.common.models package
- trinity.common.rewards package
- Submodules
- trinity.common.rewards.accuracy_reward module
- trinity.common.rewards.agents_reward module
- trinity.common.rewards.countdown_reward module
- trinity.common.rewards.dapo_reward module
- trinity.common.rewards.format_reward module
- trinity.common.rewards.human_reward module
- trinity.common.rewards.math_reward module
- trinity.common.rewards.reward_fn module
- trinity.common.rewards.tool_reward module
- trinity.common.rewards.utils module
- Module contents
- Submodules
- trinity.common.workflows package
- Subpackages
- Submodules
- trinity.common.workflows.agentscope_workflow module
- trinity.common.workflows.customized_math_workflows module
- trinity.common.workflows.customized_toolcall_workflows module
- trinity.common.workflows.eval_workflow module
- trinity.common.workflows.math_rm_workflow module
- trinity.common.workflows.math_ruler_workflow module
- trinity.common.workflows.math_trainable_ruler_workflow module
- trinity.common.workflows.rubric_judge_workflow module
- trinity.common.workflows.simple_mm_workflow module
- trinity.common.workflows.step_wise_workflow module
- trinity.common.workflows.workflow module
- Module contents
Submodules#
- trinity.common.config module
set_if_none()FormatConfigFormatConfig.prompt_typeFormatConfig.prompt_keyFormatConfig.response_keyFormatConfig.system_prompt_keyFormatConfig.system_promptFormatConfig.messages_keyFormatConfig.tools_keyFormatConfig.image_keyFormatConfig.video_keyFormatConfig.reply_prefixFormatConfig.workflow_keyFormatConfig.reward_fn_keyFormatConfig.chosen_keyFormatConfig.rejected_keyFormatConfig.enable_concatenated_multi_turnFormatConfig.chat_templateFormatConfig.__init__()
GenerationConfigOptimizerConfigOptimizerConfig.lrOptimizerConfig.lr_warmup_stepsOptimizerConfig.lr_warmup_steps_ratioOptimizerConfig.min_lr_ratioOptimizerConfig.warmup_styleOptimizerConfig.lr_scheduler_typeOptimizerConfig.optimizer_typeOptimizerConfig.betasOptimizerConfig.weight_decayOptimizerConfig.clip_gradOptimizerConfig.__init__()
LoRAConfigTaskSelectorConfigReplayBufferConfigOverRolloutConfigDynamicTimeoutConfigStorageConfigStorageConfig.nameStorageConfig.storage_typeStorageConfig.pathStorageConfig.repeat_timesStorageConfig.indexStorageConfig.splitStorageConfig.subset_nameStorageConfig.formatStorageConfig.capacityStorageConfig.max_read_timeoutStorageConfig.replay_bufferStorageConfig.max_retry_timesStorageConfig.max_retry_intervalStorageConfig.default_workflow_typeStorageConfig.default_reward_fn_typeStorageConfig.rollout_argsStorageConfig.workflow_argsStorageConfig.reward_fn_argsStorageConfig.task_selectorStorageConfig.enable_progress_barStorageConfig.ray_namespaceStorageConfig.wrap_in_rayStorageConfig.schema_typeStorageConfig.total_epochsStorageConfig.total_stepsStorageConfig.batch_sizeStorageConfig.tokenizer_pathStorageConfig.is_evalStorageConfig.__init__()
TasksetConfigTasksetConfig.nameTasksetConfig.storage_typeTasksetConfig.pathTasksetConfig.default_workflow_typeTasksetConfig.default_reward_fn_typeTasksetConfig.rollout_argsTasksetConfig.workflow_argsTasksetConfig.reward_fn_argsTasksetConfig.task_selectorTasksetConfig.splitTasksetConfig.subset_nameTasksetConfig.formatTasksetConfig.max_retry_timesTasksetConfig.max_retry_intervalTasksetConfig.enable_progress_barTasksetConfig.repeat_timesTasksetConfig.indexTasksetConfig.is_evalTasksetConfig.batch_sizeTasksetConfig.total_epochsTasksetConfig.total_stepsTasksetConfig.ray_namespaceTasksetConfig.to_storage_config()TasksetConfig.__init__()
ExperienceBufferConfigExperienceBufferConfig.nameExperienceBufferConfig.storage_typeExperienceBufferConfig.pathExperienceBufferConfig.capacityExperienceBufferConfig.max_read_timeoutExperienceBufferConfig.replay_bufferExperienceBufferConfig.max_retry_timesExperienceBufferConfig.max_retry_intervalExperienceBufferConfig.splitExperienceBufferConfig.subset_nameExperienceBufferConfig.formatExperienceBufferConfig.enable_progress_barExperienceBufferConfig.schema_typeExperienceBufferConfig.indexExperienceBufferConfig.batch_sizeExperienceBufferConfig.tokenizer_pathExperienceBufferConfig.total_epochsExperienceBufferConfig.total_stepsExperienceBufferConfig.ray_namespaceExperienceBufferConfig.to_storage_config()ExperienceBufferConfig.__init__()
OperatorConfigExperiencePipelineConfigTaskPipelineConfigDataProcessorConfigTinkerConfigModelConfigModelConfig.model_pathModelConfig.trust_remote_codeModelConfig.critic_model_pathModelConfig.custom_chat_templateModelConfig.chat_template_pathModelConfig.temperatureModelConfig.top_pModelConfig.top_kModelConfig.logprobsModelConfig.max_model_lenModelConfig.max_prompt_tokensModelConfig.max_response_tokensModelConfig.min_response_tokensModelConfig.enable_prompt_truncationModelConfig.repetition_penaltyModelConfig.lora_configsModelConfig.fully_sharded_lorasModelConfig.max_cpu_lorasModelConfig.rope_scalingModelConfig.rope_thetaModelConfig.tinkerModelConfig.__init__()
InferenceModelConfigInferenceModelConfig.model_pathInferenceModelConfig.nameInferenceModelConfig.trust_remote_codeInferenceModelConfig.engine_typeInferenceModelConfig.engine_numInferenceModelConfig.tensor_parallel_sizeInferenceModelConfig.use_v1InferenceModelConfig.enforce_eagerInferenceModelConfig.enable_prefix_cachingInferenceModelConfig.enable_chunked_prefillInferenceModelConfig.gpu_memory_utilizationInferenceModelConfig.dtypeInferenceModelConfig.seedInferenceModelConfig.temperatureInferenceModelConfig.top_pInferenceModelConfig.top_kInferenceModelConfig.logprobsInferenceModelConfig.max_model_lenInferenceModelConfig.max_prompt_tokensInferenceModelConfig.max_response_tokensInferenceModelConfig.min_response_tokensInferenceModelConfig.enable_prompt_truncationInferenceModelConfig.repetition_penaltyInferenceModelConfig.ignore_eosInferenceModelConfig.chat_templateInferenceModelConfig.enable_thinkingInferenceModelConfig.enable_historyInferenceModelConfig.enable_openai_apiInferenceModelConfig.enable_log_requestsInferenceModelConfig.enable_auto_tool_choiceInferenceModelConfig.tool_call_parserInferenceModelConfig.reasoning_parserInferenceModelConfig.bundle_indicesInferenceModelConfig.ray_namespaceInferenceModelConfig.cuda_visible_devicesInferenceModelConfig.enable_loraInferenceModelConfig.enable_runtime_lora_updatingInferenceModelConfig.lora_modulesInferenceModelConfig.lora_kwargsInferenceModelConfig.rope_scalingInferenceModelConfig.rope_thetaInferenceModelConfig.__init__()
AlgorithmConfigAlgorithmConfig.algorithm_typeAlgorithmConfig.repeat_timesAlgorithmConfig.optimizerAlgorithmConfig.sample_strategyAlgorithmConfig.sample_strategy_argsAlgorithmConfig.advantage_fnAlgorithmConfig.advantage_fn_argsAlgorithmConfig.kl_penalty_fnAlgorithmConfig.kl_penalty_fn_argsAlgorithmConfig.policy_loss_fnAlgorithmConfig.policy_loss_fn_argsAlgorithmConfig.kl_loss_fnAlgorithmConfig.kl_loss_fn_argsAlgorithmConfig.entropy_loss_fnAlgorithmConfig.entropy_loss_fn_argsAlgorithmConfig.loss_agg_modeAlgorithmConfig.__init__()
ClusterConfigClusterConfig.ray_addressClusterConfig.node_numClusterConfig.gpu_per_nodeClusterConfig.total_gpu_numClusterConfig.rollout_gpu_numClusterConfig.auxiliary_model_gpu_numClusterConfig.explorer_gpu_numClusterConfig.trainer_gpu_numClusterConfig.trainer_node_numClusterConfig.trainer_gpu_num_per_nodeClusterConfig.__init__()
ExplorerInputTrainerInputBufferConfigExplorerConfigExplorerConfig.nameExplorerConfig.runner_per_modelExplorerConfig.max_timeoutExplorerConfig.max_retry_timesExplorerConfig.env_varsExplorerConfig.concurrent_modeExplorerConfig.max_repeat_times_per_runnerExplorerConfig.runner_numExplorerConfig.rollout_modelExplorerConfig.auxiliary_modelsExplorerConfig.eval_intervalExplorerConfig.eval_on_startupExplorerConfig.bench_on_latest_checkpointExplorerConfig.proxy_portExplorerConfig.listen_addressExplorerConfig.service_status_check_intervalExplorerConfig.min_running_model_numExplorerConfig.db_urlExplorerConfig.over_rolloutExplorerConfig.dynamic_timeoutExplorerConfig.runner_state_report_intervalExplorerConfig.__init__()
TrainerConfigTrainerConfig.nameTrainerConfig.trainer_typeTrainerConfig.trainer_strategyTrainerConfig.save_intervalTrainerConfig.enable_previewTrainerConfig.total_stepsTrainerConfig.save_hf_checkpointTrainerConfig.grad_clipTrainerConfig.use_dynamic_bszTrainerConfig.max_token_len_per_gpuTrainerConfig.ulysses_sequence_parallel_sizeTrainerConfig.fix_actor_microbatch_loss_scaleTrainerConfig.save_strategyTrainerConfig.max_checkpoints_to_keepTrainerConfig.trainer_configTrainerConfig.trainer_config_pathTrainerConfig.__init__()
MonitorConfigSynchronizerConfigDataJuicerServiceConfigServiceConfigLogConfigStageConfigConfigConfig.modeConfig.projectConfig.groupConfig.nameConfig.checkpoint_root_dirConfig.checkpoint_job_dirConfig.ray_namespaceConfig.continue_from_checkpointConfig.ignore_validator_suggestionsConfig.algorithmConfig.data_processorConfig.modelConfig.clusterConfig.bufferConfig.explorerConfig.trainerConfig.monitorConfig.synchronizerConfig.serviceConfig.logConfig.stagesConfig.save()Config.check_and_update()Config.flatten()Config.get_envs()Config.get_checkpoint_job_dir()Config.__init__()
load_config()
- trinity.common.constants module
- trinity.common.experience module
EIDCustomFieldExperienceExperience.__init__()Experience.eidExperience.rewardExperience.token_level_rewardExperience.advantagesExperience.returnsExperience.infoExperience.metricsExperience.truncate_statusExperience.prompt_lengthExperience.response_textExperience.prompt_textExperience.messagesExperience.toolsExperience.chosen_messagesExperience.rejected_messagesExperience.multi_modal_inputsExperience.tokensExperience.logprobsExperience.action_maskExperience.chosenExperience.rejectedExperience.teacher_logprobsExperience.custom_fieldsExperience.serialize()Experience.deserialize()Experience.to_dict()Experience.gather()
split_dpo_experience_to_single_turn()ExperiencesExperiences.__init__()Experiences.eidsExperiences.tokensExperiences.rewardsExperiences.token_level_rewardsExperiences.advantagesExperiences.returnsExperiences.attention_masksExperiences.action_masksExperiences.prompt_lengthExperiences.logprobsExperiences.multi_modal_inputsExperiences.custom_fieldsExperiences.teacher_logprobsExperiences.batch_sizeExperiences.gather_experiences()
empty_experiences()gather_token_ids()gather_action_masks()gather_attention_masks()gather_response_attrs()gather_multi_modal_inputs()group_by()to_hf_datasets()from_hf_datasets()
- trinity.common.verl_config module