MCPcopy Create free account

hub / github.com/LeapLabTHU/Absolute-Zero-Reasoner / functions

Functions861 in github.com/LeapLabTHU/Absolute-Zero-Reasoner

⨍ Functions 861◇ Types & classes 85↳ Endpoints 9
Method__init__
( self, runtime: Optional[Any] = None, get_answer_symbol: Optional[str] = None,
evaluation/math_eval/eval/python_executor.py:76
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/fireworks_runner.py:19
Method__init__
(self, args, model: LanguageModel)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/base_runner.py:14
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/vllm_runner.py:12
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/cohere_runner.py:15
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/claude_runner.py:15
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/oai_runner.py:19
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/mistral_runner.py:17
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/deepseek_runner.py:19
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/gemini_runner.py:37
Method__init__
(self, args, model)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/claude3_runner.py:15
Method__init__
(self, target_functors)
evaluation/code_eval/coding/evalplus/tools/collect_valid_solutions.py:61
Method__init__
(self, prob: float)
evaluation/code_eval/coding/evalplus/tools/_experimental/type_mut_for_eff.py:28
Method__init__
(self, inputs: List, signature: str, contract_code: str)
evaluation/code_eval/coding/evalplus/tools/_experimental/type_mut_for_eff.py:99
Method__init__
(self, prob: float)
evaluation/code_eval/coding/evalplus/evalplus/gen/type_mut.py:20
Method__init__
(self, inputs: List, signature: str, contract_code: str)
evaluation/code_eval/coding/evalplus/evalplus/gen/type_mut.py:35
Method__init__
Initializing a input mutator. Args: inputs (List[Any]): The set of initial inputs (i.e., seeds) entry_point (str)
evaluation/code_eval/coding/evalplus/evalplus/gen/__init__.py:6
Method__init__
(self, inputs: List, signature: str, contract_code: str, gd_code: str)
evaluation/code_eval/coding/evalplus/evalplus/gen/chatgpt_gen.py:15
Method__init__
(self, inputs: List, signature: str, contract_code: str)
evaluation/code_eval/coding/evalplus/evalplus/gen/mut_gen.py:10
Method__init__
( self, name: str, batch_size: int = 1, temperature: float = 0.8, max_
evaluation/code_eval/coding/evalplus/evalplus/provider/base.py:8
Method__init__
( self, name: str, dataset: str, force_base_prompt: bool = False, tens
evaluation/code_eval/coding/evalplus/evalplus/provider/vllm.py:14
Method__init__
(self, name: str, base_url=None, **kwargs)
evaluation/code_eval/coding/evalplus/evalplus/provider/openai.py:12
Method__init__
(self, name: str, **kwargs)
evaluation/code_eval/coding/evalplus/evalplus/provider/google.py:58
Method__init__
(self, role_arn, region_name)
evaluation/code_eval/coding/evalplus/evalplus/provider/bedrock.py:15
Method__init__
(self, name: str, **kwargs)
evaluation/code_eval/coding/evalplus/evalplus/provider/bedrock.py:60
Method__init__
( self, name: str, dataset: str, force_base_prompt: bool = False, attn
evaluation/code_eval/coding/evalplus/evalplus/provider/hf.py:14
Method__init__
(self, name: str, **kwargs)
evaluation/code_eval/coding/evalplus/evalplus/provider/anthropic.py:11
Method__init__
( self, name: str, dataset: str, gptqmodel_backend: str = 'auto', forc
evaluation/code_eval/coding/evalplus/evalplus/provider/gptqmodel.py:22
Method__init__
(self, project_name, experiment_name, default_backend: Union[str, List[str]] = 'console', config=None, resume=
absolute_zero_reasoner/utils/tracking.py:7
Method__init__
(self, parquet_files: Union[str, List[str]], tokenizer: PreTrainedTokenizer,
absolute_zero_reasoner/utils/dataset/rl_dataset.py:68
Method__init__
(self, use_china_mirror=True, silent=False)
absolute_zero_reasoner/utils/code_utils/sandboxfusion_executor.py:33
Method__init__
( self, timeout_length: int = 10, ast_check: bool = False, max_workers: int =
absolute_zero_reasoner/utils/code_utils/sandboxfusion_executor.py:136
Method__init__
(self)
absolute_zero_reasoner/utils/code_utils/checks.py:104
Method__init__
(self, composite_functions, scope_vars)
absolute_zero_reasoner/utils/code_utils/checks.py:121
Method__init__
(self)
absolute_zero_reasoner/utils/code_utils/python_executor.py:43
Method__init__
( self, runtime: Optional[Any] = None, get_answer_symbol: Optional[str] = None,
absolute_zero_reasoner/utils/code_utils/python_executor.py:97
Method__init__
( self, tokenizer: AutoTokenizer, num_examine: int, split: str, reward
absolute_zero_reasoner/rewards/reward_managers.py:38
Method__init__
(self, past_epoch_window: int = 10, *args, **kwargs)
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:587
Method__init__
Initialize distributed PPO trainer with Ray backend. Note that this trainer runs on the driver process on a single CPU/GPU node.
absolute_zero_reasoner/trainer/ppo/reason_rl_ray_trainer.py:28
Method__iter__
(self)
evaluation/math_eval/eval/python_executor.py:68
Method__iter__
(self)
absolute_zero_reasoner/utils/code_utils/python_executor.py:88
Method__len__
(self)
absolute_zero_reasoner/utils/dataset/rl_dataset.py:137
Method__post_init__
(self)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/benchmarks/code_generation.py:35
Method__post_init__
(self)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/benchmarks/code_generation.py:56
Method__post_init__
(self)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/benchmarks/test_output_prediction.py:29
Method__post_init__
(self)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/benchmarks/code_execution.py:23
Method__repr__
(self)
evaluation/code_eval/coding/evalplus/evalplus/provider/base.py:41
Method__run_single
(counter)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/fireworks_runner.py:39
Method__run_single
(counter)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/cohere_runner.py:27
Method__run_single
(counter)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/claude_runner.py:26
Method__run_single
(counter)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/mistral_runner.py:28
Method__run_single
(counter)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/deepseek_runner.py:36
Method__run_single
(counter)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/claude3_runner.py:26
Method__str__
(self)
evaluation/code_eval/coding/evalplus/tools/_experimental/type_mut_for_eff.py:50
Method__str__
(self)
evaluation/code_eval/coding/evalplus/evalplus/provider/base.py:44
Method_call_one
(self, messages: List[Dict[str, str]])
evaluation/code_eval/coding/evalplus/evalplus/provider/bedrock.py:63
Method_combine_rewards
(acc, intrinsic_components, method)
absolute_zero_reasoner/rewards/reward_managers.py:396
Method_impl
(*_)
evaluation/code_eval/coding/evalplus/tools/_experimental/type_mut_for_eff.py:168
Method_impl
(*_)
evaluation/code_eval/coding/evalplus/evalplus/gen/type_mut.py:71
Method_run_single
(self, prompt: str | list[dict[str, str]])
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/base_runner.py:36
Method_run_single
(self, prompt: str)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/vllm_runner.py:37
Method_run_single
(self, prompt: tuple[dict[str,str], str])
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/cohere_runner.py:24
Method_run_single
(self, prompt: str)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/claude_runner.py:24
Method_run_single
(self, prompt: list[dict[str, str]])
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/oai_runner.py:48
Method_run_single
(self, prompt: list[dict[str, str]])
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/mistral_runner.py:26
Method_run_single
(self, prompt: str)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/gemini_runner.py:61
Method_run_single
(self, prompt: tuple[str, str])
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/runner/claude3_runner.py:24
Function_temp_run
(sample, generation, debug, result, metadata_list, timeout)
evaluation/code_eval/coding/LiveCodeBench/lcb_runner/evaluation/compute_code_generation_metrics.py:23
Method_truncate_text
Truncate text with ellipsis if it exceeds max_length
absolute_zero_reasoner/utils/logging_utils/stdout.py:71
Methodadd_error_batch
(self, entries: List[Dict], global_step: int)
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:362
Methodadd_error_seed_batch
(self, entries: List[Dict], global_step: int)
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:373
Methodadd_input_batch
(self, entries: List[Dict], global_step: int)
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:340
Methodadd_output_batch
(self, entries: List[Dict], global_step: int)
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:351
Methodadd_problem_batch
(self, entries: List[Dict], global_step: int)
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:384
Methodanswer
(self)
evaluation/math_eval/eval/python_executor.py:56
Methodanswer
(self)
absolute_zero_reasoner/utils/code_utils/python_executor.py:75
Functionast_edit_operations
Generate a list of edit operations needed to transform ast1 into ast2. Args: ast1: First AST ast2: Second AST
absolute_zero_reasoner/rewards/code_reward.py:178
Methodcheck_all
( self, code: str, inputs: str, banned_keywords: List[str] = [], check
absolute_zero_reasoner/utils/code_utils/sandboxfusion_executor.py:294
Functioncheck_correctness
( dataset: str, completion_id: int, problem: Dict[str, Any], solution: str, expected_outpu
evaluation/code_eval/coding/evalplus/evalplus/evaluate.py:79
Functioncheck_determinism
expects an executor that outputs string output and status
absolute_zero_reasoner/utils/code_utils/checks.py:7
Methodcheck_mutually_exclusive
(mbs, mbs_per_gpu, name: str)
absolute_zero_reasoner/trainer/ppo/reason_rl_ray_trainer.py:129
Functionclean_units
Clean the units in the number.
evaluation/math_eval/eval/parser.py:433
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/vllm.py:52
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/openai.py:16
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/google.py:63
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/bedrock.py:83
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/hf.py:61
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/anthropic.py:15
Methodcodegen
( self, prompt: str, do_sample: bool = True, num_samples: int = 200 )
evaluation/code_eval/coding/evalplus/evalplus/provider/gptqmodel.py:63
Functioncollate_fn
(data_list: list[dict])
absolute_zero_reasoner/utils/dataset/rl_dataset.py:36
Functioncompute_method_ranks
Compute, for each metric, the rank of each model (1 = best accuracy). Args: data (List[Dict]): your JSON‐like list of dicts.
evaluation/math_eval/collect_all_math_results.py:84
Functionconvert_latex_table
Convert a list of dicts into a LaTeX table, sorted by descending average accuracy. Args: data (List[Dict]): your JSON‐like list.
evaluation/math_eval/collect_all_math_results.py:24
Functioncorrectness_worker
(task_id: str, samples: list, ctask: Dict, expected_output: Dict)
evaluation/code_eval/coding/evalplus/evalplus/evalperf.py:124
Functioncount_nested_html
(input_string)
evaluation/math_eval/eval/custom_evaluate.py:274
Functioncreate_default_dict
()
absolute_zero_reasoner/trainer/ppo/azr_ray_trainer.py:47
Methoddefault
(self, obj)
evaluation/code_eval/coding/evalplus/evalplus/inputgen.py:16
Methodeval_code
(self, expr: str)
evaluation/math_eval/eval/python_executor.py:48
Methodeval_code
(self, expr: str)
absolute_zero_reasoner/utils/code_utils/python_executor.py:67
Methodeval_input_prediction
(self, code: str, gold_output: str, agent_input: str, imports: List[str] = [])
absolute_zero_reasoner/utils/code_utils/sandboxfusion_executor.py:202
Methodeval_k_input_prediction
(self, code: str, gold_output: str, k_agent_inputs: List[str], imports: List[str] = [])
absolute_zero_reasoner/utils/code_utils/sandboxfusion_executor.py:253
← previousnext →601–700 of 861, ranked by callers