Python Module Index

n
 
n
nemo_rl
    nemo_rl.algorithms
    nemo_rl.algorithms.advantage_estimator
    nemo_rl.algorithms.async_utils
    nemo_rl.algorithms.async_utils.interfaces
    nemo_rl.algorithms.async_utils.replay_buffer
    nemo_rl.algorithms.async_utils.trajectory_collector
    nemo_rl.algorithms.distillation
    nemo_rl.algorithms.dpo
    nemo_rl.algorithms.grpo
    nemo_rl.algorithms.grpo_sync
    nemo_rl.algorithms.logits_sampling_utils
    nemo_rl.algorithms.loss
    nemo_rl.algorithms.loss.interfaces
    nemo_rl.algorithms.loss.loss_functions
    nemo_rl.algorithms.loss.utils
    nemo_rl.algorithms.loss.wrapper
    nemo_rl.algorithms.opd
    nemo_rl.algorithms.ppo
    nemo_rl.algorithms.reward_functions
    nemo_rl.algorithms.rm
    nemo_rl.algorithms.sft
    nemo_rl.algorithms.utils
    nemo_rl.algorithms.x_token
    nemo_rl.algorithms.x_token.loss_utils
    nemo_rl.algorithms.x_token.token_aligner
    nemo_rl.algorithms.x_token.utils
    nemo_rl.algorithms.xtoken_off_policy_distillation
    nemo_rl.data
    nemo_rl.data.chat_templates
    nemo_rl.data.collate_fn
    nemo_rl.data.cross_tokenizer_collate
    nemo_rl.data.dataloader
    nemo_rl.data.datasets
    nemo_rl.data.datasets.eval_datasets
    nemo_rl.data.datasets.eval_datasets.aime
    nemo_rl.data.datasets.eval_datasets.gpqa
    nemo_rl.data.datasets.eval_datasets.local_math_dataset
    nemo_rl.data.datasets.eval_datasets.math
    nemo_rl.data.datasets.eval_datasets.mmau
    nemo_rl.data.datasets.eval_datasets.mmlu
    nemo_rl.data.datasets.eval_datasets.mmlu_pro
    nemo_rl.data.datasets.preference_datasets
    nemo_rl.data.datasets.preference_datasets.binary_preference_dataset
    nemo_rl.data.datasets.preference_datasets.helpsteer3
    nemo_rl.data.datasets.preference_datasets.preference_dataset
    nemo_rl.data.datasets.preference_datasets.tulu3
    nemo_rl.data.datasets.processed_dataset
    nemo_rl.data.datasets.raw_dataset
    nemo_rl.data.datasets.response_datasets
    nemo_rl.data.datasets.response_datasets.aime
    nemo_rl.data.datasets.response_datasets.arrow_text_dataset
    nemo_rl.data.datasets.response_datasets.audiomcq
    nemo_rl.data.datasets.response_datasets.avqa
    nemo_rl.data.datasets.response_datasets.clevr
    nemo_rl.data.datasets.response_datasets.daily_omni
    nemo_rl.data.datasets.response_datasets.dapo_math
    nemo_rl.data.datasets.response_datasets.deepscaler
    nemo_rl.data.datasets.response_datasets.general_conversations_dataset
    nemo_rl.data.datasets.response_datasets.geometry3k
    nemo_rl.data.datasets.response_datasets.gsm8k
    nemo_rl.data.datasets.response_datasets.helpsteer3
    nemo_rl.data.datasets.response_datasets.mmpr_tiny
    nemo_rl.data.datasets.response_datasets.nemogym_dataset
    nemo_rl.data.datasets.response_datasets.nemotron_cascade2_sft
    nemo_rl.data.datasets.response_datasets.oai_format_dataset
    nemo_rl.data.datasets.response_datasets.oasst
    nemo_rl.data.datasets.response_datasets.openmathinstruct2
    nemo_rl.data.datasets.response_datasets.refcoco
    nemo_rl.data.datasets.response_datasets.response_dataset
    nemo_rl.data.datasets.response_datasets.squad
    nemo_rl.data.datasets.response_datasets.tulu3
    nemo_rl.data.datasets.utils
    nemo_rl.data.interfaces
    nemo_rl.data.llm_message_utils
    nemo_rl.data.multimodal_utils
    nemo_rl.data.packing
    nemo_rl.data.packing.algorithms
    nemo_rl.data.packing.metrics
    nemo_rl.data.processors
    nemo_rl.data.utils
    nemo_rl.data_plane
    nemo_rl.data_plane.adapters
    nemo_rl.data_plane.adapters.noop
    nemo_rl.data_plane.adapters.transfer_queue
    nemo_rl.data_plane.codec
    nemo_rl.data_plane.column_io
    nemo_rl.data_plane.factory
    nemo_rl.data_plane.interfaces
    nemo_rl.data_plane.observability
    nemo_rl.data_plane.preshard
    nemo_rl.data_plane.schema
    nemo_rl.data_plane.worker_mixin
    nemo_rl.distributed
    nemo_rl.distributed.batched_data_dict
    nemo_rl.distributed.collectives
    nemo_rl.distributed.model_utils
    nemo_rl.distributed.named_sharding
    nemo_rl.distributed.numa_utils
    nemo_rl.distributed.ray_actor_environment_registry
    nemo_rl.distributed.stateless_process_group
    nemo_rl.distributed.virtual_cluster
    nemo_rl.distributed.worker_group_utils
    nemo_rl.distributed.worker_groups
    nemo_rl.environments
    nemo_rl.environments.code_environment
    nemo_rl.environments.code_jaccard_environment
    nemo_rl.environments.dapo_math_verifier
    nemo_rl.environments.interfaces
    nemo_rl.environments.math_environment
    nemo_rl.environments.metrics
    nemo_rl.environments.nemo_gym
    nemo_rl.environments.reward_model_environment
    nemo_rl.environments.rewards
    nemo_rl.environments.utils
    nemo_rl.environments.vlm_environment
    nemo_rl.evals
    nemo_rl.evals.answer_parsing
    nemo_rl.evals.eval
    nemo_rl.experience
    nemo_rl.experience.interfaces
    nemo_rl.experience.rollout_manager
    nemo_rl.experience.rollouts
    nemo_rl.experience.sync_rollout_actor
    nemo_rl.modelopt
    nemo_rl.modelopt.models
    nemo_rl.modelopt.models.generation
    nemo_rl.modelopt.models.generation.vllm_modelopt_patch
    nemo_rl.modelopt.models.generation.vllm_quant_backend
    nemo_rl.modelopt.models.generation.vllm_quant_patch
    nemo_rl.modelopt.models.generation.vllm_quant_worker
    nemo_rl.modelopt.models.policy
    nemo_rl.modelopt.models.policy.workers
    nemo_rl.modelopt.models.policy.workers.dtensor_quant_policy_worker
    nemo_rl.modelopt.models.policy.workers.dtensor_quant_policy_worker_v2
    nemo_rl.modelopt.models.policy.workers.megatron_quant_policy_worker
    nemo_rl.modelopt.models.policy.workers.utils
    nemo_rl.modelopt.registry
    nemo_rl.modelopt.utils
    nemo_rl.models
    nemo_rl.models.automodel
    nemo_rl.models.automodel.checkpoint
    nemo_rl.models.automodel.config
    nemo_rl.models.automodel.data
    nemo_rl.models.automodel.setup
    nemo_rl.models.automodel.train
    nemo_rl.models.dtensor
    nemo_rl.models.dtensor.parallelize
    nemo_rl.models.generation
    nemo_rl.models.generation.constants
    nemo_rl.models.generation.interfaces
    nemo_rl.models.generation.megatron
    nemo_rl.models.generation.megatron.config
    nemo_rl.models.generation.megatron.megatron_generation
    nemo_rl.models.generation.megatron.megatron_worker
    nemo_rl.models.generation.megatron.utils
    nemo_rl.models.generation.vllm
    nemo_rl.models.generation.vllm.config
    nemo_rl.models.generation.vllm.patches
    nemo_rl.models.generation.vllm.utils
    nemo_rl.models.generation.vllm.vllm_backend
    nemo_rl.models.generation.vllm.vllm_generation
    nemo_rl.models.generation.vllm.vllm_worker
    nemo_rl.models.generation.vllm.vllm_worker_async
    nemo_rl.models.huggingface
    nemo_rl.models.huggingface.common
    nemo_rl.models.megatron
    nemo_rl.models.megatron.common
    nemo_rl.models.megatron.community_import
    nemo_rl.models.megatron.config
    nemo_rl.models.megatron.data
    nemo_rl.models.megatron.draft
    nemo_rl.models.megatron.draft.eagle
    nemo_rl.models.megatron.draft.hidden_capture
    nemo_rl.models.megatron.draft.utils
    nemo_rl.models.megatron.pipeline_parallel
    nemo_rl.models.megatron.router_replay
    nemo_rl.models.megatron.setup
    nemo_rl.models.megatron.train
    nemo_rl.models.policy
    nemo_rl.models.policy.interfaces
    nemo_rl.models.policy.lm_policy
    nemo_rl.models.policy.teacher_worker_group
    nemo_rl.models.policy.tq_policy
    nemo_rl.models.policy.utils
    nemo_rl.models.policy.workers
    nemo_rl.models.policy.workers.base_policy_worker
    nemo_rl.models.policy.workers.dtensor_policy_worker
    nemo_rl.models.policy.workers.dtensor_policy_worker_v2
    nemo_rl.models.policy.workers.megatron_policy_worker
    nemo_rl.models.policy.workers.patches
    nemo_rl.models.value
    nemo_rl.models.value.config
    nemo_rl.models.value.interfaces
    nemo_rl.models.value.lm_value
    nemo_rl.models.value.workers
    nemo_rl.models.value.workers.dtensor_value_worker_v2
    nemo_rl.models.value.workers.megatron_value_worker
    nemo_rl.package_info
    nemo_rl.utils
    nemo_rl.utils.checkpoint
    nemo_rl.utils.config
    nemo_rl.utils.flops_formulas
    nemo_rl.utils.flops_tracker
    nemo_rl.utils.logger
    nemo_rl.utils.memory_tracker
    nemo_rl.utils.native_checkpoint
    nemo_rl.utils.nsys
    nemo_rl.utils.nvml
    nemo_rl.utils.packed_tensor
    nemo_rl.utils.prefetch_venvs
    nemo_rl.utils.r3_trace
    nemo_rl.utils.timer
    nemo_rl.utils.venvs
    nemo_rl.weight_sync
    nemo_rl.weight_sync.collective_weight_synchronizer
    nemo_rl.weight_sync.factory
    nemo_rl.weight_sync.http_weight_synchronizer
    nemo_rl.weight_sync.interfaces
    nemo_rl.weight_sync.ipc_weight_synchronizer