MCPcopy Create free account

hub / github.com/AMAP-ML/GPG / types & classes

Types & classes45 in github.com/AMAP-ML/GPG

⨍ Functions 443◇ Types & classes 45
↓ 6 callersClassGRPOConfig
args for callbacks, benchmarks etc
open-r1/src/open_r1/configs.py:24
↓ 6 callersClassPistonError
open-r1/src/open_r1/utils/ioi/piston_client.py:12
↓ 3 callersClassRepeatRandomSampler
Sampler that repeats the indices of a dataset N times. Args: data_source (`Sized`): Dataset to sample from. repe
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:82
↓ 2 callersClassSubtaskResult
Represents the result of a subtask containing multiple test cases. Attributes: problem: Problem identifier subtask: Subtask
open-r1/src/open_r1/utils/ioi/scoring.py:28
↓ 2 callersClassTestResult
Represents the result of a single test case execution. Attributes: test_name: Name of the test case score: Score achieved fo
open-r1/src/open_r1/utils/ioi/scoring.py:10
↓ 1 callersClassAdpativeRepeatRandomSampler
open-r1/src/open_r1/gpg_trainer.py:72
↓ 1 callersClassCustomDataset
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/sft.py:63
↓ 1 callersClassDummyConfig
open-r1/src/open_r1/utils/callbacks.py:37
↓ 1 callersClassDummyConfig
open-rs/src/open_r1/utils/callbacks.py:37
↓ 1 callersClassGPGSTDTrainer
open-rs/src/open_r1/trainer/gpg_std_trainer.py:64
↓ 1 callersClassGPGTrainer
open-r1/src/open_r1/gpg_trainer.py:177
↓ 1 callersClassGPGTrainer
Trainer for the Group Policy Gradient (GPG) method. This algorithm is a variation of the GRPO method.
open-rs/src/open_r1/trainer/gpg_trainer.py:46
↓ 1 callersClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
open-r1/src/open_r1/configs.py:106
↓ 1 callersClassPistonClient
A client that will automatically load balance across multiple Piston (https://github.com/engineer-man/piston) workers. This assumes piston is
open-r1/src/open_r1/utils/ioi/piston_client.py:29
↓ 1 callersClassRepeatRandomSampler
Sampler that repeats the indices of a dataset N times. Args: data_source (`Sized`): Dataset to sample from. repe
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:81
↓ 1 callersClassSFTConfig
args for callbacks, benchmarks etc
open-r1/src/open_r1/configs.py:73
ClassCocoDetectionEvaluator
Visual-RFT/coco_evaluation/coco_evaluation.py:35
ClassGPGConfig
args for callbacks, benchmarks etc
open-r1/src/open_r1/configs.py:55
ClassGRPOConfig
args for callbacks, benchmarks etc
open-rs/src/open_r1/configs.py:24
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
Visual-RFT/src/virft/src/open_r1/grpo_classification.py:35
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
Visual-RFT/src/virft/src/open_r1/grpo_lisa.py:35
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
Visual-RFT/src/virft/src/open_r1/grpo.py:36
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/grpo.py:35
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
R1-V/src/r1-v/src/open_r1/grpo.py:33
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
open-rs/src/open_r1/gpg.py:49
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
open-rs/src/open_r1/grpo.py:49
ClassGRPOScriptArguments
Script arguments for the GRPO training script. Args: reward_funcs (`list[str]`): List of reward functions. Possible valu
open-rs/src/open_r1/gpg_std.py:49
ClassPushToHubRevisionCallback
open-r1/src/open_r1/utils/callbacks.py:43
ClassPushToHubRevisionCallback
open-rs/src/open_r1/utils/callbacks.py:43
ClassQwen2VLGRPOTrainer
Trainer for the Group Relative Policy Optimization (GRPO) method. This algorithm was initially proposed in the paper [DeepSeekMath: Pushing t
Visual-RFT/src/virft/src/open_r1/trainer/grpo_trainer.py:66
ClassQwen2VLGRPOTrainer
Trainer for the Group Relative Policy Optimization (GRPO) method. This algorithm was initially proposed in the paper [DeepSeekMath: Pushing t
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py:71
ClassQwen2VLGRPOTrainer
Trainer for the Group Relative Policy Optimization (GRPO) method. This algorithm was initially proposed in the paper [DeepSeekMath: Pushing t
R1-V/src/r1-v/src/open_r1/trainer/grpo_trainer.py:68
ClassQwen2VLGRPOVLLMTrainer
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:116
ClassQwen2VLGRPOVLLMTrainer
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:117
ClassQwen2VLGRPOVLLMTrainerModified
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer_modified.py:81
ClassResetDataLoader
open-r1/src/open_r1/gpg.py:157
ClassSFTConfig
args for callbacks, benchmarks etc
R1-V/src/r1-v/src/open_r1/sft.py:66
ClassSFTConfig
args for callbacks, benchmarks etc
open-rs/src/open_r1/configs.py:56
ClassScriptArguments
open-r1/scripts/upload_details.py:34
ClassScriptArguments
open-r1/scripts/run_benchmarks.py:23
ClassTestCodeFormat
open-r1/tests/test_rewards.py:411
ClassTestCodeRewards
open-r1/tests/slow/test_code_reward.py:23
ClassTestGetRewardFuncs
open-r1/tests/test_rewards.py:32
ClassTestRepetitionPenaltyReward
open-r1/tests/test_rewards.py:243
ClassTestRewards
open-r1/tests/test_rewards.py:73