MCPcopy Create free account

hub / github.com/AMAP-ML/GPG / functions

Functions443 in github.com/AMAP-ML/GPG

⨍ Functions 443◇ Types & classes 45
↓ 1 callersFunctionpush_to_hub_revision
Pushes the model to branch on a Hub repo.
open-r1/src/open_r1/utils/hub.py:39
↓ 1 callersFunctionpush_to_hub_revision
Pushes the model to branch on a Hub repo.
open-rs/src/open_r1/utils/hub.py:39
↓ 1 callersFunctionreasoning_steps_reward
r"""Reward function that checks for clear step-by-step reasoning. Regex pattern: Step \d+: - matches "Step 1:", "Step 2:", etc. ^\
open-r1/src/open_r1/rewards.py:166
↓ 1 callersFunctionremove_duplicates
(bbox_list)
Visual-RFT/lvis_evaluation/Qwen2_VL_lvis_infere.py:151
↓ 1 callersFunctionremove_duplicates
(bbox_list)
Visual-RFT/coco_evaluation/Qwen2_VL_coco_infere.py:149
↓ 1 callersFunctionrle_to_mask
(rle)
Visual-RFT/lisa_evaluation/mask_iou.py:13
↓ 1 callersFunctionrun_async
(scripts: list[str], language: str)
open-r1/src/open_r1/rewards.py:543
↓ 1 callersFunctionrun_async
(scripts: list[str], language: str)
open-rs/src/open_r1/rewards.py:501
↓ 1 callersFunctionrun_async_from_sync
Function wrapping the `run_async` function.
open-r1/src/open_r1/rewards.py:530
↓ 1 callersFunctionrun_async_from_sync
Function wrapping the `run_async` function.
open-rs/src/open_r1/rewards.py:488
↓ 1 callersFunctionrun_benchmark_jobs
(training_args: Union["SFTConfig", "GRPOConfig"], model_args: "ModelConfig")
open-rs/src/open_r1/utils/evaluation.py:96
↓ 1 callersFunctionrun_catch_exceptions
(task)
open-r1/src/open_r1/rewards.py:406
↓ 1 callersFunctionrun_lighteval_job
( benchmark: str, training_args: Union["SFTConfig", "GRPOConfig"], model_args: "ModelConfig" )
open-r1/src/open_r1/utils/evaluation.py:64
↓ 1 callersFunctionrun_lighteval_job
( benchmark: str, training_args: Union["SFTConfig", "GRPOConfig"], model_args: "ModelConfig" )
open-rs/src/open_r1/utils/evaluation.py:64
↓ 1 callersFunctionrun_script
(sbx: AsyncSandbox, script: str, language: str)
open-r1/src/open_r1/rewards.py:560
↓ 1 callersFunctionrun_script
(sbx, script: str, language: str)
open-rs/src/open_r1/rewards.py:518
↓ 1 callersFunctionrun_submission
Executes a submission against a test case using the Piston execution environment. Args: client: PistonClient instance for executing
open-r1/src/open_r1/utils/ioi/scoring.py:266
↓ 1 callersFunctionsave_images
Save images from byte format to PNG files.
VisualThinker-R1-Zero/src/data/SAT/process_dataset.py:24
↓ 1 callersFunctionsave_rle_to_json
(rle_data_list, save_path)
Visual-RFT/lisa_evaluation/box2mask.py:30
↓ 1 callersFunctionscale_bbox
(bbox, width, height)
Visual-RFT/lisa_evaluation/box2mask.py:21
↓ 1 callersFunctionscore_single_test_case
Scores a single test case by running the submission against the provided input and output. Args: client: PistonClient instance for e
open-r1/src/open_r1/utils/ioi/scoring.py:137
↓ 1 callersMethodto_dict
Converts the SubtaskResult to a dictionary representation. Returns: dict: Dictionary containing all subtask result data
open-r1/src/open_r1/utils/ioi/scoring.py:90
↓ 1 callersFunctiontrans_bbox
(image_height, image_width, position)
Visual-RFT/lvis_evaluation/Qwen2_VL_lvis_infere.py:130
↓ 1 callersFunctiontrans_bbox
(image_height, image_width, position)
Visual-RFT/coco_evaluation/Qwen2_VL_coco_infere.py:128
↓ 1 callersFunctionvalidate_qa_pairs
Process QA pairs and save them to separate files. Only saves pairs where parsed answer matches ground truth. Args: input_file: P
R1-V/src/distill_r1/filter_r1.py:80
↓ 1 callersFunctionxyxy2xywh
change bbox to coco format :param bbox: [x1, y1, x2, y2] :return: [x, y, w, h]
Visual-RFT/coco_evaluation/coco_evaluation.py:21
↓ 1 callersFunctionzipngram
(text: str, ngram_size: int)
open-r1/src/open_r1/rewards.py:344
↓ 1 callersFunctionzipngram
(text: str, ngram_size: int)
open-rs/src/open_r1/rewards.py:355
Method__getitem__
(self, idx)
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/sft.py:70
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:117
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
Visual-RFT/src/virft/src/open_r1/trainer/grpo_trainer.py:150
Method__init__
(self, ann_path)
Visual-RFT/coco_evaluation/coco_evaluation.py:36
Method__init__
(self, data_list)
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/sft.py:64
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py:155
Method__init__
( self, data_source: Sized, mini_repeat_count: int, batch_size: int = 1,
open-r1/src/open_r1/gpg_trainer.py:73
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
open-r1/src/open_r1/gpg_trainer.py:178
Method__init__
(self, **kwargs)
open-r1/src/open_r1/utils/callbacks.py:38
Method__init__
(self, model_config)
open-r1/src/open_r1/utils/callbacks.py:44
Method__init__
( self, base_endpoint: str | list[str] = "http://ip-10-53-80-65:3223/api/v2", session=
open-r1/src/open_r1/utils/ioi/piston_client.py:52
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer_modified.py:82
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:118
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
R1-V/src/r1-v/src/open_r1/trainer/grpo_trainer.py:152
Method__init__
(self, **kwargs)
open-rs/src/open_r1/utils/callbacks.py:38
Method__init__
(self, model_config)
open-rs/src/open_r1/utils/callbacks.py:44
Method__init__
( self, model: Union[str, PreTrainedModel], reward_funcs: Union[RewardFunc, list[Rewar
open-rs/src/open_r1/trainer/gpg_std_trainer.py:65
Method__iter__
(self)
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:104
Method__iter__
(self)
open-r1/src/open_r1/gpg_trainer.py:93
Method__iter__
(self)
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:105
Method__len__
(self)
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:112
Method__len__
(self)
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/sft.py:67
Method__len__
(self)
open-r1/src/open_r1/gpg_trainer.py:173
Method__len__
(self)
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:113
Method_generate_and_score_completions
( self, inputs: dict[str, Union[torch.Tensor, Any]] )
open-rs/src/open_r1/trainer/gpg_std_trainer.py:131
Method_get_eval_sampler
(self, eval_dataset)
open-r1/src/open_r1/gpg_trainer.py:724
Method_get_train_sampler
(self)
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:459
Method_get_train_sampler
(self)
open-r1/src/open_r1/gpg_trainer.py:196
Method_get_train_sampler
(self)
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:477
Method_prepare_inputs
( self, inputs: dict[str, Union[torch.Tensor, Any]] )
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:499
Method_prepare_inputs
( self, inputs: dict[str, Union[torch.Tensor, Any]] )
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer_modified.py:425
Method_prepare_inputs
( self, inputs: dict[str, Union[torch.Tensor, Any]] )
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:517
Method_save_checkpoint
(self, model, trial)
open-r1/src/open_r1/gpg_trainer.py:710
Method_send_to_one
(self, endpoint, route, data=None, method="post")
open-r1/src/open_r1/utils/ioi/piston_client.py:103
Method_set_signature_columns_if_needed
(self)
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:450
Method_set_signature_columns_if_needed
(self)
Visual-RFT/src/virft/src/open_r1/trainer/grpo_trainer.py:353
Method_set_signature_columns_if_needed
(self)
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py:344
Method_set_signature_columns_if_needed
(self)
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer_modified.py:380
Method_set_signature_columns_if_needed
(self)
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:468
Method_set_signature_columns_if_needed
(self)
R1-V/src/r1-v/src/open_r1/trainer/grpo_trainer.py:336
Functionaccuracy_reward
Reward function that checks if the completion is correct using either symbolic verification or exact string matching.
Visual-RFT/src/virft/src/open_r1/grpo_classification.py:72
Functionaccuracy_reward
Reward function that checks if the completion is correct using either symbolic verification or exact string matching.
Visual-RFT/src/virft/src/open_r1/grpo_lisa.py:111
Functionaccuracy_reward
Reward function that checks if the completion is correct using either symbolic verification or exact string matching.
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/grpo.py:83
Functionaccuracy_reward
Reward function that checks if the completion is correct using either symbolic verification or exact string matching.
R1-V/src/r1-v/src/open_r1/grpo.py:69
Functionaccuracy_reward
Reward function that checks if the completion is the same as the ground truth.
open-rs/src/open_r1/rewards.py:22
Functionaccuracy_reward_confidence
Reward function that checks if the completion is correct using either symbolic verification or exact string matching.
Visual-RFT/src/virft/src/open_r1/grpo.py:308
Functionaccuracy_reward_iou
Reward function that checks if the completion is correct using either symbolic verification or exact string matching.
Visual-RFT/src/virft/src/open_r1/grpo.py:240
Functionaccuracy_reward_lv35
Reward function that checks if the completion is the same as the ground truth.
open-r1/src/open_r1/rewards.py:71
Functionaime_prompt_fn
(line, task_name: str = None)
open-r1/src/open_r1/evaluate_short.py:89
Functionaime_prompt_fn
(line, task_name: str = None)
open-r1/src/open_r1/evaluate.py:89
Functionaime_prompt_fn
(line, task_name: str = None)
open-rs/src/open_r1/evaluate.py:89
Functionamc_prompt_fn
(line, task_name: str = None)
open-r1/src/open_r1/evaluate.py:98
Functionamc_prompt_fn
(line, task_name: str = None)
open-rs/src/open_r1/evaluate.py:98
Functionbinary_code_reward
(completions, **kwargs)
open-r1/src/open_r1/rewards.py:435
Functioncheck_hub_revision_exists
Checks if a given Hub revision exists.
open-r1/src/open_r1/utils/hub.py:70
Functioncheck_hub_revision_exists
Checks if a given Hub revision exists.
open-rs/src/open_r1/utils/hub.py:70
Functioncode_format_reward
(completions, **kwargs)
open-r1/src/open_r1/rewards.py:522
Functioncode_format_reward
(completions, **kwargs)
open-rs/src/open_r1/rewards.py:480
Functioncode_reward
Reward function that evaluates code snippets using the E2B code interpreter. Assumes the dataset contains a `verification_info` column with test
open-rs/src/open_r1/rewards.py:399
Functioncollate_fn
(examples)
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/sft.py:151
Functioncollate_fn
(examples)
R1-V/src/r1-v/src/open_r1/sft.py:144
Methodcompute_loss
( self, model, inputs, return_outputs=False, num_items_in_batch=None )
Visual-RFT/src/virft/src/open_r1/trainer/vllm_grpo_trainer.py:743
Methodcompute_loss
(self, model, inputs, return_outputs=False, num_items_in_batch=None)
Visual-RFT/src/virft/src/open_r1/trainer/grpo_trainer.py:668
Methodcompute_loss
(self, model, inputs, return_outputs=False, num_items_in_batch=None)
VisualThinker-R1-Zero/src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py:694
Methodcompute_loss
(self, model, inputs, return_outputs=False, num_items_in_batch=None)
open-r1/src/open_r1/gpg_trainer.py:269
Methodcompute_loss
( self, model, inputs, return_outputs=False, num_items_in_batch=None )
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer_modified.py:686
Methodcompute_loss
( self, model, inputs, return_outputs=False, num_items_in_batch=None )
R1-V/src/r1-v/src/open_r1/trainer/vllm_grpo_trainer.py:761
Methodcompute_loss
(self, model, inputs, return_outputs=False, num_items_in_batch=None)
R1-V/src/r1-v/src/open_r1/trainer/grpo_trainer.py:647
Methodcompute_loss
(self, model, inputs, return_outputs=False, num_items_in_batch=None)
open-rs/src/open_r1/trainer/gpg_trainer.py:51
Methodcompute_loss
(self, model, inputs, return_outputs=False, num_items_in_batch=None)
open-rs/src/open_r1/trainer/gpg_std_trainer.py:83
Functioncompute_reward_iou
(iou_results)
Visual-RFT/src/virft/src/open_r1/grpo.py:177
Functioncosine_scaled_reward
Reward function that scales based on completion length using a cosine schedule. Shorter correct solutions are rewarded more than longer ones.
open-r1/src/open_r1/rewards.py:263
← previousnext →201–300 of 443, ranked by callers