MCPcopy Create free account

hub / github.com/InternScience/SciReason / functions

Functions3,711 in github.com/InternScience/SciReason

↓ 1 callersFunctiondispatch_tasks
(cfg, force=False)
tools/case_analyzer.py:168
↓ 1 callersFunctiondispatch_tasks
(cfg)
tools/prediction_merger.py:75
↓ 1 callersMethoddo_inference
(self, instruction, history=[])
opencompass/models/alaya.py:80
↓ 1 callersFunctiondo_setup
()
setup.py:107
↓ 1 callersFunctiondownload_and_extract_archive
(url, download_root, extract_root=None,
opencompass/utils/fileio.py:509
↓ 1 callersFunctiondownload_url
Download a file from a url and place it in root. Args: url (str): URL to download file from. root (str): Directory to place downl
opencompass/utils/fileio.py:420
↓ 1 callersMethoddpp_search
(self)
opencompass/openicl/icl_retriever/icl_dpp_retriever.py:44
↓ 1 callersMethoddraw_menu
(self, stdscr, selected_row_idx, offset, max_rows)
opencompass/utils/menu.py:29
↓ 1 callersFunctionds1000_postprocess
(text: str)
opencompass/datasets/ds1000.py:128
↓ 1 callersFunctioneb_ex
()
opencompass/datasets/musr/tree.py:566
↓ 1 callersFunctionedit_similarity_score
(predicted_text, original_text)
opencompass/datasets/benbench.py:49
↓ 1 callersMethodedp_check
Check if the edit distance solution is valid. :param instance: The instance dictionary with 'string_a' and 'string_b'. :param solutio
opencompass/datasets/NPHardEval/p_EDP.py:99
↓ 1 callersFunctionencode_base64_string
对字符串进行 Base64 编码. :param s: 字符串 :return: 编码后的字符串
opencompass/models/yayi_api.py:48
↓ 1 callersFunctionensure_directory
(path)
opencompass/summarizers/needlebench.py:368
↓ 1 callersFunctionentropy
(probs: np.array, label_dim: int = 0, mask=None)
opencompass/openicl/icl_retriever/icl_mdl_retriever.py:184
↓ 1 callersFunctionequal_with_timeout
(expr1, expr2)
opencompass/datasets/phybench/EED.py:134
↓ 1 callersMethodequation_equal
(expression1 is assumed to be Ground_Truth) Function: Check if two equations are mathematically equivalent Step 1: Simplify e
opencompass/datasets/OlympiadBench.py:494
↓ 1 callersFunctionescape_ansi
(line)
opencompass/lagent/actions/ipython_interpreter.py:273
↓ 1 callersMethodestimate_pass_at_k
Estimates pass@k of each problem and returns them in an array.
opencompass/datasets/LCBench.py:247
↓ 1 callersMethodestimate_pass_at_k
Estimates pass@k of each problem and returns them in an array.
opencompass/datasets/mbpp.py:448
↓ 1 callersMethodeval_code
(self, expr: str)
opencompass/lagent/actions/python_interpreter.py:29
↓ 1 callersFunctioneval_prompt_construct
(task, ref_answer, history)
opencompass/datasets/subjective/mtbench101.py:237
↓ 1 callersMethodevaluate
(self)
opencompass/tasks/llm_eval.py:34
↓ 1 callersFunctionevaluate_edits
(src, hyp_dict, ref_dict, best, sent_id, args)
opencompass/datasets/lawbench/utils/compare_m2_for_evaluation.py:242
↓ 1 callersFunctionevaluate_generations
We take the list of code generations and try to compile them and the run their corresponding unit tests which are retrieved from the APPS dataset.
opencompass/datasets/livecodebench/evaluator.py:117
↓ 1 callersMethodevaluate_generations
(self, generations, samples,
opencompass/datasets/apps.py:193
↓ 1 callersMethodevaluate_generations
(self, generations, samples,
opencompass/datasets/taco.py:142
↓ 1 callersMethodevaluate_response_vs_answer
Evaluates a single response against the answer. Args: response (str): The model's response. answer (str): The referen
opencompass/openicl/icl_evaluator/icl_korbench_evaluator.py:216
↓ 1 callersMethodevaluate_responses
Evaluates a list of responses. Args: data (list): List of records containing responses and answers. question_type (st
opencompass/openicl/icl_evaluator/icl_korbench_evaluator.py:132
↓ 1 callersFunctionexact_match_score
(predicted_text, original_text)
opencompass/datasets/benbench.py:46
↓ 1 callersFunctionexists
(path)
opencompass/utils/fileio.py:226
↓ 1 callersFunctionexp_frac
(s)
opencompass/datasets/phybench/latex_pre_process.py:215
↓ 1 callersMethodexpand_w_torsion
r""" Compute the global frame Lines 2-10 Algorithm 24, Page 31 of the AlphaFold 2 supplementary material Args:
opencompass/datasets/unconditional_protein_generation/omegafold/utils/protein_utils/aaframe.py:716
↓ 1 callersMethodexpanded_to_pos
Compute the full atom representation Args: fasta: the sequence to compute the atoms full: if to use safe ini
opencompass/datasets/unconditional_protein_generation/omegafold/utils/protein_utils/aaframe.py:836
↓ 1 callersFunctionextract_all_responses_from_json
(response_json)
opencompass/datasets/korbench/korbench_utils.py:319
↓ 1 callersFunctionextract_all_responses_from_json
(response_json)
opencompass/datasets/supergpqa/supergpqa_utils.py:319
↓ 1 callersFunctionextract_answer
Extract answer from toolbench format.
opencompass/openicl/icl_evaluator/icl_agent_evaluator.py:36
↓ 1 callersFunctionextract_answer
(answer, calid)
opencompass/datasets/MedCalc_Bench.py:73
↓ 1 callersFunctionextract_answer
(response_text: str)
opencompass/datasets/math.py:134
↓ 1 callersFunctionextract_answer
(model_response, item, prompt_style, type)
opencompass/datasets/calm/evaluation/labeling/Natural.py:13
↓ 1 callersFunctionextract_answer
(js)
opencompass/datasets/agieval/utils.py:27
↓ 1 callersFunctionextract_answer
(js)
opencompass/datasets/medbench/utils.py:27
↓ 1 callersMethodextract_answer
(cls, pred: str, extract_last_num=False)
opencompass/datasets/math_intern.py:137
↓ 1 callersFunctionextract_answer_part
(outputs, left_tag, right_tag, mode='tag')
opencompass/datasets/LLM4Chem/evaluator.py:52
↓ 1 callersFunctionextract_archive
(from_path, to_path=None, remove_finished=False)
opencompass/utils/fileio.py:480
↓ 1 callersFunctionextract_boxed_answer
(pred_str, strip_double_curly_brace=False)
opencompass/datasets/math_intern.py:51
↓ 1 callersFunctionextract_boxed_answer
(text)
opencompass/datasets/gaokao_math.py:66
↓ 1 callersFunctionextract_bracket_content
(s: str, bracket_position: int)
opencompass/datasets/phybench/latex_pre_process.py:35
↓ 1 callersFunctionextract_choice
r"""{ "answer": "A|B|C|D" }
opencompass/datasets/PMMEval/mlogiqa.py:27
↓ 1 callersFunctionextract_choice
r"""{ "answer": "A|B|C|D" }
opencompass/datasets/PMMEval/mhellaswag.py:27
↓ 1 callersFunctionextract_choice
r"""{ "answer": "A|B|C|D" }
opencompass/datasets/PMMEval/xnli.py:28
↓ 1 callersFunctionextract_choice
r"""{ "answer": "A|B|C|D" }
opencompass/datasets/PMMEval/mmmlu.py:27
↓ 1 callersFunctionextract_choice_fuzzy
(gen)
opencompass/datasets/PMMEval/mlogiqa.py:60
↓ 1 callersFunctionextract_choice_fuzzy
(gen, lang)
opencompass/datasets/PMMEval/mhellaswag.py:59
↓ 1 callersFunctionextract_choice_fuzzy
(gen, lang)
opencompass/datasets/PMMEval/xnli.py:60
↓ 1 callersFunctionextract_choice_fuzzy
(gen)
opencompass/datasets/PMMEval/mmmlu.py:59
↓ 1 callersMethodextract_code
(command: str)
opencompass/lagent/actions/python_interpreter.py:88
↓ 1 callersFunctionextract_code_execution
(model_output: str, cot: bool = False)
opencompass/datasets/livecodebench/extract_utils.py:43
↓ 1 callersFunctionextract_code_generation
(model_output: str, model_type: str = 'chat')
opencompass/datasets/livecodebench/extract_utils.py:6
↓ 1 callersFunctionextract_code_generation
(model_output: str, entrypoint: Optional[str] = None)
opencompass/datasets/bigcodebench/extractor.py:182
↓ 1 callersFunctionextract_code_generation_v2
(model_output: str, model_type: str = 'chat')
opencompass/datasets/livecodebench/extract_utils.py:22
↓ 1 callersFunctionextract_command
extract the command name from a bracket.
opencompass/datasets/phybench/latex_pre_process.py:79
↓ 1 callersFunctionextract_dicts
(data)
opencompass/openicl/icl_evaluator/lm_evaluator.py:18
↓ 1 callersFunctionextract_elements_from_prompt
Extract element symbols from diverse prompt instructions. Supported patterns include: - composed of - that has - characterized by
opencompass/datasets/composition_material.py:15
↓ 1 callersFunctionextract_json
(text)
opencompass/datasets/korbench/korbench_utils.py:305
↓ 1 callersFunctionextract_judge_label
(text)
opencompass/datasets/livemathbench/utils.py:4
↓ 1 callersFunctionextract_last_equal_content
Extract the content after the last occurrence of specific mathematical comparison or assignment operators. :param strip_whitespace: If True,
opencompass/datasets/phybench/latex_pre_process.py:334
↓ 1 callersMethodextract_matching_bracket
(cls, target_str: str)
opencompass/datasets/math_intern.py:116
↓ 1 callersFunctionextract_missing_rating
(text, search_type)
opencompass/summarizers/subjective/alignmentbench.py:53
↓ 1 callersFunctionextract_missing_rating
(text, search_type)
opencompass/datasets/subjective/alignbench.py:154
↓ 1 callersFunctionextract_modifications
(text)
opencompass/datasets/bioinstruction/evaluator.py:983
↓ 1 callersFunctionextract_modifications
(text)
opencompass/datasets/bio_instruction/bio_instrcution.py:871
↓ 1 callersFunctionextract_prediction
(output, options=None, option_inds='ABCDEFGH')
opencompass/datasets/tabmwp.py:106
↓ 1 callersFunctionextract_predictions_from_json
(input_folder)
tools/convert_alignmentbench.py:10
↓ 1 callersFunctionextract_prob
(model_response, prompt_style, type)
opencompass/datasets/calm/evaluation/labeling/Probability.py:14
↓ 1 callersMethodextract_python_script
(self, response: str)
opencompass/datasets/scicode.py:234
↓ 1 callersMethodextract_rate
This function is designed for calculating the extraction rate. Args: results (dict): The result dict, include the information
opencompass/tasks/openicl_eval.py:335
↓ 1 callersFunctionextract_rating
(text)
opencompass/summarizers/subjective/alignmentbench.py:89
↓ 1 callersFunctionextract_rating
(text)
opencompass/datasets/subjective/alignbench.py:172
↓ 1 callersFunctionextract_rating_plus
(text)
opencompass/summarizers/subjective/alignmentbench.py:71
↓ 1 callersFunctionextract_score
(text)
opencompass/datasets/subjective/alignbench.py:212
↓ 1 callersMethodextract_smiles_simple
(self,text: str)
opencompass/datasets/unconditional_molecule_generation/UMG.py:72
↓ 1 callersMethodextract_smiles_simple
(self,text: str)
opencompass/datasets/bioinstruction/evaluator.py:197
↓ 1 callersFunctionextract_strict_value
(text: str, property: str)
opencompass/datasets/LLM4Mat.py:71
↓ 1 callersFunctionextract_target_code_or_empty
(code: str, entrypoint: Optional[str] = None)
opencompass/datasets/bigcodebench/extractor.py:114
↓ 1 callersFunctionextract_test_output_code
(model_output: str)
opencompass/datasets/livecodebench/extract_utils.py:64
↓ 1 callersFunctionextract_theoremqa_answer
(pred: str, answer_flag: bool = True)
opencompass/datasets/TheoremQA/utils.py:19
↓ 1 callersMethodextract_toxicity_attributes
Given a response from PerspectiveAPI, return scores in dict. Args: text: Text to perform evaluation. Returns:
opencompass/openicl/icl_evaluator/icl_toxic_evaluator.py:79
↓ 1 callersMethodextract_winner
(self, s, lan)
opencompass/openicl/icl_evaluator/icl_judge_evaluator.py:264
↓ 1 callersFunctionfast_map_dpp
fast implementation of the greedy algorithm reference: https://github.com/laming-chen/fast-map-dpp/blob/master/dpp_test.py paper: Fast Greedy
opencompass/openicl/icl_retriever/icl_dpp_retriever.py:103
↓ 1 callersFunctionfill_eval_cfg
(cfg, args)
opencompass/utils/run.py:389
↓ 1 callersFunctionfill_infer_cfg
(cfg, args)
opencompass/utils/run.py:361
↓ 1 callersMethodfind_FinishAction
(self, text)
opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py:168
↓ 1 callersMethodfind_a_dot_b_structure
(self, text)
opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py:163
↓ 1 callersFunctionfirst_option_postprocess
Find first valid option for text.
opencompass/datasets/mathbench.py:154
↓ 1 callersFunctionfirst_pre_process
Perform the first stage of LaTeX string preprocessing. if not brackets_balanced(s): raise ValueError("The input string has unbalanced bra
opencompass/datasets/phybench/latex_pre_process.py:364
↓ 1 callersFunctionfirsttime_process
(args)
opencompass/datasets/lawbench/utils/parallel_to_m2.py:84
↓ 1 callersFunctionfit_bt
(matchups, outcomes, weights, n_models, alpha, tol=1e-6)
opencompass/summarizers/subjective/compass_arena_bradley_terry.py:260
↓ 1 callersFunctionfit_contextual_bt
( matchups, features, outcomes, models, idxs=None, alpha=math.
opencompass/summarizers/subjective/compass_arena_bradley_terry.py:411
↓ 1 callersFunctionfit_vectorized_elo
Fit multiple sets of Elo ratings on different samples of the data at the same time.
opencompass/summarizers/subjective/compass_arena_bradley_terry.py:172
← previousnext →1,001–1,100 of 3,711, ranked by callers