MCPcopy Create free account

hub / github.com/PRIME-RL/PRIME / functions

Functions2,604 in github.com/PRIME-RL/PRIME

↓ 1 callersFunctionmain
(llm, tokenizer, data_name, args)
eval/Math/Qwen25-Math/evaluation/math_eval.py:158
↓ 1 callersFunctionmain
()
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/custom_evaluator.py:15
↓ 1 callersFunctionmain
()
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/main.py:19
↓ 1 callersFunctionmain
(config)
training/verl/trainer/main_generation.py:40
↓ 1 callersFunctionmain
(config)
training/verl/trainer/main_eval.py:35
↓ 1 callersFunctionmain
(config)
training/verl/trainer/fsdp_sft_trainer.py:353
↓ 1 callersFunctionmain
()
data_preprocessing/stage2_format_choice.py:206
↓ 1 callersFunctionmain
()
data_preprocessing/stage4_judge.py:323
↓ 1 callersFunctionmake_conv_hf
(question, tokenizer)
eval/Math/aime/evaluate_aime.py:147
↓ 1 callersFunctionmake_conv_hf
(question, tokenizer)
eval/Math/amc/evaluate_amc.py:156
↓ 1 callersFunctionmake_conv_hf
(question, tokenizer)
eval/Math/math/evaluate_math.py:141
↓ 1 callersFunctionmake_conv_hf
(example, tokenizer)
eval/Coding/human_eval/evaluate_human_eval.py:34
↓ 1 callersFunctionmake_conv_hf
(signature, description, test_list, tokenizer)
eval/Coding/mbpp/evaluate_mbpp.py:65
↓ 1 callersFunctionmake_conv_hf
(example, tokenizer)
eval/Coding/leetcode/evaluate_leetcode.py:70
↓ 1 callersFunctionmake_cot_output_prompt
(s)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_execution.py:7
↓ 1 callersFunctionmake_direct_output_prompt
(s)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/code_execution.py:38
↓ 1 callersFunctionmake_signature
(example)
eval/Coding/human_eval/evaluate_human_eval.py:102
↓ 1 callersFunctionmake_signature
(code)
eval/Coding/mbpp/evaluate_mbpp.py:57
↓ 1 callersFunctionmasked_var
Compute variance of tensor with masked values.
training/verl/utils/torch_functional.py:112
↓ 1 callersFunctionmatch_answer
(response)
eval/Math/aime/evaluate_aime.py:97
↓ 1 callersFunctionmatch_answer
(response)
eval/Math/amc/evaluate_amc.py:103
↓ 1 callersFunctionmatch_answer
(response)
eval/Math/math/evaluate_math.py:93
↓ 1 callersFunctionmatch_answer
(response)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:333
↓ 1 callersFunctionmatch_code
(s)
eval/Coding/human_eval/evaluate_human_eval.py:65
↓ 1 callersFunctionmatch_code
(s)
eval/Coding/mbpp/evaluate_mbpp.py:21
↓ 1 callersFunctionmatch_code
(s)
eval/Coding/leetcode/evaluate_leetcode.py:32
↓ 1 callersMethodmath
(self)
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:873
↓ 1 callersFunctionmath_equal_timeout
(pred, gt)
eval/Math/Qwen25-Math/evaluation/rm_maj_eval.py:9
↓ 1 callersFunctionmodel_parallel_is_initialized
Check if tensor and pipeline parallel groups are initialized.
training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py:98
↓ 1 callersFunctionmodel_parallel_is_initialized
Check if tensor and pipeline parallel groups are initialized.
training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py:95
↓ 1 callersFunctionmodel_parallel_is_initialized
Check if tensor and pipeline parallel groups are initialized.
training/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py:92
↓ 1 callersFunctionmy_parse_latex
(expr_str)
eval/Math/Qwen25-Math/evaluation/math_utils.py:46
↓ 1 callersFunctionnormalize_model_name
Transform the model name in each model_chunk in each pp stage into the name in inference engine
training/verl/utils/model.py:192
↓ 1 callersFunctionoffload_fsdp_grad
(module)
training/verl/utils/fsdp_utils.py:71
↓ 1 callersFunctionoffload_megatron_param_and_grad
(module_list: nn.ModuleList, offload_grad=False, hybrid_engine=None)
training/verl/utils/megatron_utils.py:226
↓ 1 callersMethodoffload_params_to_cpu
offload params of models that are not of current pp rank to cpu
training/verl/workers/hybrid_engine/megatron_vllm.py:157
↓ 1 callersFunctiononly_int_check
(val)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/testing_util.py:71
↓ 1 callersFunctiononly_int_check
(val)
training/verl/utils/reward_score/evaluation_utils/code_util/testing_util.py:72
↓ 1 callersFunctionpad_to_sequence_parallel
pad the tokens such that the total length is a multiple of sp world size Args: unpad_tokens: (total_nnz, ...). Tokens after removing padd
training/verl/utils/megatron/sequence_parallel.py:29
↓ 1 callersFunctionparallel_evaluate_continual_async
Evaluate rows in parallel with a process pool and timeout handling.
training/verl/utils/reward_score/prime.py:46
↓ 1 callersFunctionparse_args
()
eval/Math/Qwen25-Math/evaluation/math_eval.py:21
↓ 1 callersFunctionparse_args
()
eval/Math/Qwen25-Math/evaluation/evaluate.py:96
↓ 1 callersFunctionparse_assert_statement
Parse a Python assert statement and extract the expected output from the right side of the '==' operator as a string. :param statement:
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_test_output_prediction_metrics.py:9
↓ 1 callersFunctionparse_function_name_from_starter_code
starter_code : str
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/prompts/test_output_prediction.py:53
↓ 1 callersFunctionparse_question
(example, data_name)
eval/Math/Qwen25-Math/evaluation/parser.py:654
↓ 1 callersFunctionpass_at_k
(n, c, k)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/compute_code_execution_metrics.py:21
↓ 1 callersMethodping
Check if the tokenizer group is alive.
training/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py:35
↓ 1 callersFunctionprepare_data
(data_name, args)
eval/Math/Qwen25-Math/evaluation/math_eval.py:61
↓ 1 callersMethodprepare_input_tensors
( self, seq_group_metadata_list: Optional[List[SequenceGroupMetadata]], )
training/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py:174
↓ 1 callersMethodprepare_input_tensors
( self, seq_group_metadata_list: List[SequenceGroupMetadata], )
training/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py:147
↓ 1 callersMethodprocess
(prompt, idx)
data_preprocessing/stage4_judge.py:148
↓ 1 callersFunctionprocess_fn
(d, idx)
data_preprocessing/stage1_filter.py:28
↓ 1 callersFunctionprocess_fn
(d)
data_preprocessing/stage3_merge.py:43
↓ 1 callersMethodprocess_generation_to_code
(self, gens: str)
eval/Math/Qwen25-Math/evaluation/python_executor.py:91
↓ 1 callersFunctionprocess_row_with_timeout
Process a single row with a timeout.
training/verl/utils/reward_score/prime.py:23
↓ 1 callersMethodprofile_num_available_blocks
( self, block_size: int, gpu_memory_utilization: float, cpu_swap_space: int,
training/verl/third_party/vllm/vllm_v_0_3_1/worker.py:121
↓ 1 callersMethodre_encode_by_rm_tokenizer
(self, data: DataProto)
training/verl/workers/reward_model/megatron/reward_model.py:58
↓ 1 callersFunctionread_dataset
( data_file: str = None, dataset_type: str = "humaneval", num_shot=None, )
eval/utils/evaluation_leetcode.py:68
↓ 1 callersFunctionread_jsonl_file
(file_path)
eval/Math/aime/evaluate_aime.py:29
↓ 1 callersFunctionread_jsonl_file
(file_path)
eval/Math/amc/evaluate_amc.py:29
↓ 1 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro
eval/utils/execution.py:158
↓ 1 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro
eval/utils/execution_leetcode.py:659
↓ 1 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:189
↓ 1 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/testing_util.py:678
↓ 1 callersFunctionreliability_guard
This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other pro
training/verl/utils/reward_score/evaluation_utils/code_util/testing_util.py:669
↓ 1 callersFunctionremove_boxed
(s)
training/verl/utils/reward_score/math.py:49
↓ 1 callersFunctionremove_right_units
(string)
training/verl/utils/reward_score/math.py:140
↓ 1 callersMethodrename
Note that this function only rename the key in the batch
training/verl/protocol.py:305
↓ 1 callersFunctionrun
(args, max=-1)
eval/Math/aime/evaluate_aime.py:158
↓ 1 callersFunctionrun
(args, max=-1)
eval/Math/amc/evaluate_amc.py:167
↓ 1 callersFunctionrun
(args, max=-1)
eval/Math/math/evaluate_math.py:152
↓ 1 callersFunctionrun_execute
(executor, result, prompt_type, data_name, execute=False)
eval/Math/Qwen25-Math/evaluation/parser.py:722
↓ 1 callersMethodrun_main
(self, benchmark: list, format_prompt: callable)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/base_runner.py:173
↓ 1 callersMethodrun_main_repair
(self, benchmark: list, format_prompt: callable)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/base_runner.py:123
↓ 1 callersMethodrun_single
Run the model for a single prompt and return the output Static method to be used in multiprocessing Calls the _run_single met
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/base_runner.py:40
↓ 1 callersFunctionrun_tasks_in_parallel
Args: func: The function to run. The function must accept a single argument. tasks: A list of tasks i.e. arguments to func.
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:193
↓ 1 callersFunctionrun_tasks_in_parallel_iter
Args: func: The function to run. The function must accept a single argument. tasks: A list of tasks i.e. arguments to func.
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/utils/multiprocess.py:98
↓ 1 callersFunctionrun_test
if test(generated_code) is not None it'll try to run the code. otherwise it'll just return an input and output pair.
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/testing_util.py:83
↓ 1 callersFunctionrun_test
if test(generated_code) is not None it'll try to run the code. otherwise it'll just return an input and output pair.
training/verl/utils/reward_score/evaluation_utils/code_util/testing_util.py:89
↓ 1 callersMethodsave_cache
(self)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/runner/base_runner.py:30
↓ 1 callersFunctionsave_jsonl
(samples, save_path)
eval/Math/Qwen25-Math/evaluation/utils.py:30
↓ 1 callersMethodsave_results
(self, data: Dict)
data_preprocessing/stage4_judge.py:307
↓ 1 callersFunctionselect_reward_fn
(data_source)
training/verl/trainer/main_eval.py:27
↓ 1 callersFunctionserializedATN
()
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSParser.py:9
↓ 1 callersFunctionserializedATN
()
eval/Math/Qwen25-Math/evaluation/latex2sympy/gen/PSLexer.py:9
↓ 1 callersFunctionset_basic_config
This function sets the global logging format and level. It will be called when import verl
training/verl/utils/logging_utils.py:18
↓ 1 callersFunctionset_pad_token_id
Set pad_token_id to eos_token_id if it is None. Args: tokenizer (transformers.PreTrainedTokenizer): The tokenizer to be set.
training/verl/utils/tokenizer.py:20
↓ 1 callersFunctionset_seed
(seed: int = 42)
eval/Math/Qwen25-Math/evaluation/utils.py:13
↓ 1 callersFunctionshould_allow_eval
(expr: str)
training/verl/utils/reward_score/evaluation_utils/math_util/__init__.py:191
↓ 1 callersFunctionshould_allow_eval
(expr: str)
data_preprocessing/math_util/__init__.py:191
↓ 1 callersMethodslice_batch
Note that this operation is in-place
training/verl/protocol.py:127
↓ 1 callersMethodstart_new_epoch
Reset for new epoch
training/verl/utils/dataset/rl_dataset.py:161
↓ 1 callersFunctionstr_to_pmatrix
(input_str)
eval/Math/Qwen25-Math/evaluation/grader.py:60
↓ 1 callersFunctionstream_jsonl_all
(filename: str)
eval/utils/evaluation_leetcode.py:172
↓ 1 callersFunctionstring_int_check
(val)
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/testing_util.py:75
↓ 1 callersFunctionstring_int_check
(val)
training/verl/utils/reward_score/evaluation_utils/code_util/testing_util.py:76
↓ 1 callersFunctionswallow_io
()
eval/utils/execution.py:103
↓ 1 callersFunctionswallow_io
()
eval/utils/execution_leetcode.py:604
↓ 1 callersFunctionswallow_io
()
eval/Coding/livecodebench/LiveCodeBench-main/lcb_runner/evaluation/utils_execute.py:134
↓ 1 callersFunctionsymbolic_equal
(a, b, tolerance, timeout=10.0)
eval/utils/grader.py:317
← previousnext →1,001–1,100 of 2,604, ranked by callers