Functions — github.com/InternScience/SciReason

hub / github.com/InternScience/SciReason / functions

Functions3,711 in github.com/InternScience/SciReason

⨍ Functions 3,711◇ Types & classes 923↳ Endpoints 23

↓ 2 callersFunctionextract_score

(text)

opencompass/summarizers/subjective/alignmentbench.py:124

↓ 2 callersFunctionfind_all

(s, sub_str, allow_overlap=True)

opencompass/datasets/phybench/latex_pre_process.py:246

↓ 2 callersFunctionfind_files_by_regex

(directory, pattern)

opencompass/utils/result_station.py:378

↓ 2 callersFunctionfind_first_capital_letter

(answer)

opencompass/datasets/agieval/post_process.py:73

↓ 2 callersFunctionfind_first_capital_letter

(answer)

opencompass/datasets/medbench/post_process.py:73

↓ 2 callersFunctionfind_first_unescaped_brace

(s: str)

opencompass/datasets/phybench/latex_pre_process.py:67

↓ 2 callersFunctionfind_sub_sequence

(whole, sub)

opencompass/datasets/LLM4Chem/utils/core_tagger.py:5

↓ 2 callersFunctionformat_float

(v)

opencompass/summarizers/multi_model.py:32

↓ 2 callersMethodformat_load

r''' ensure evaluator can work correctly under any data input

opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py:67

↓ 2 callersMethodformat_load

r''' ensure evaluator can work correctly under any data input

opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py:291

↓ 2 callersMethodformat_load

r''' ensure evaluator can work correctly under any data input

opencompass/datasets/teval/evaluators/planning_evaluator.py:66

↓ 2 callersMethodforward

Args: tensor: the tensor to apply rope onto seq_dim: the dimension that represents the sequence dimension R

opencompass/datasets/unconditional_protein_generation/omegafold/embedders.py:165

↓ 2 callersMethodgenerate

Generate results given a list of inputs. Args: inputs (List[str]): A list of strings. max_out_len (int): The maximum

opencompass/models/huggingface.py:223

↓ 2 callersFunctiongenerate_depth_percents

(intervals, interval_type)

opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_single_4k.py:24

↓ 2 callersFunctiongenerate_depth_percents

(intervals, interval_type)

opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_retrieval_compare_batch_8k.py:24

↓ 2 callersFunctiongenerate_depth_percents

(intervals, interval_type)

opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_single_8k.py:24

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_multi_reasoning_200k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_single_200k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_multi_retrieval_200k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_multi_retrieval_128k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_multi_reasoning_128k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_single_128k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_multi_retrieval_1000k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_multi_reasoning_1000k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_single_1000k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_multi_retrieval_256k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_single_256k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_multi_reasoning_256k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_single_32k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_multi_retrieval_32k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_multi_reasoning_32k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_multi_retrieval_4k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_single_4k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_multi_reasoning_4k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_base/needlebench_single.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_reasoning_8k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_retrieval_8k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_retrieval_compare_batch_8k.py:15

↓ 2 callersFunctiongenerate_linear_space

(start, end, num)

opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_single_8k.py:15

↓ 2 callersMethodgenerate_prompt_for_adv_generate_task

Generate the prompt for one test example in generative evaluation with `prompt_template`. If `prompt_template` is not provided, the `i

opencompass/openicl/icl_retriever/icl_base_retriever.py:263

↓ 2 callersMethodget_action

(self, step)

opencompass/datasets/gsm8k.py:112

↓ 2 callersMethodget_action

(self, step)

opencompass/datasets/math.py:536

↓ 2 callersFunctionget_answer_type_text

(answer_type, is_chinese, multiple_answer)

opencompass/datasets/OlympiadBench.py:146

↓ 2 callersMethodget_children

(self)

opencompass/datasets/phybench/EED.py:212

↓ 2 callersMethodget_children

(node)

opencompass/datasets/phybench/extended_zss.py:22

↓ 2 callersFunctionget_circular_example

For given example, generate four circular examples.

opencompass/datasets/mathbench.py:21

↓ 2 callersFunctionget_command_template

Format command template given available gpu ids.

opencompass/runners/local.py:24

↓ 2 callersFunctionget_current_numbers

(y: str)

opencompass/datasets/game24.py:157

↓ 2 callersFunctionget_files

Get all file paths in the folder with specified extensions.

tools/compare_configs.py:9

↓ 2 callersFunctionget_final_results

(judged_answers, references, origial_responses,

opencompass/datasets/generic.py:6

↓ 2 callersMethodget_generation_prompt_list_from_retriever_indices

( self, ice_idx_list: List[List[int]], retriever: BaseRetriever,

opencompass/openicl/icl_inferencer/icl_gen_inferencer.py:214

↓ 2 callersMethodget_generation_prompt_list_from_retriever_indices

( self, ice_idx_list: List[List[int]], retriever: BaseRetriever,

opencompass/openicl/icl_inferencer/icl_sc_inferencer.py:173

↓ 2 callersMethodget_instruction_args

Returns the keyword args of `build_description`.

opencompass/datasets/IFEval/instructions.py:905

↓ 2 callersMethodget_judge_result

(self, judge, dataset_name)

opencompass/datasets/subjective/judgerbench.py:352

↓ 2 callersMethodget_logits

(self, inputs: List[str])

opencompass/models/glm.py:287

↓ 2 callersMethodget_logits

(self, inputs: List[str])

opencompass/models/huggingface.py:431

↓ 2 callersFunctionget_matchups_models

(df)

opencompass/summarizers/subjective/compass_arena_bradley_terry.py:41

↓ 2 callersFunctionget_number

(options)

opencompass/datasets/wikibench.py:12

↓ 2 callersFunctionget_origin_patterns

(option_keys)

opencompass/datasets/circular.py:22

↓ 2 callersFunctionget_pred_label

(model_response, item, prompt_style, type)

opencompass/datasets/calm/evaluation/labeling/AS.py:11

↓ 2 callersMethodget_rank_dict

(self, score_dict)

opencompass/openicl/icl_evaluator/icl_judge_evaluator.py:257

↓ 2 callersMethodget_size

(self, dataset: ConfigDict)

opencompass/partitioners/sub_num_worker.py:188

↓ 2 callersMethodget_size

(self, dataset: ConfigDict)

opencompass/partitioners/num_worker.py:134

↓ 2 callersMethodget_token_len

Get lengths of the tokenized strings. Args: prompt (str): Input string. Returns: int: Length of the input to

opencompass/models/base.py:139

↓ 2 callersMethodget_token_len

Get lengths of the tokenized string. Only English and Chinese characters are counted for now. Users are encouraged to override this me

opencompass/models/openai_api.py:380

↓ 2 callersMethodget_tokens

(s)

opencompass/datasets/lawbench/utils/rc_f1.py:60

↓ 2 callersMethodget_total_scores

(self, exact_scores, f1_scores)

opencompass/datasets/lawbench/utils/rc_f1.py:150

↓ 2 callersFunctionhumaneval_postprocess_v2

(text: str)

opencompass/datasets/humaneval.py:182

↓ 2 callersMethodinitialize

(self)

opencompass/lagent/actions/ipython_interpreter.py:107

↓ 2 callersFunctioninitialize_core_metric_evaluation_components

Loads the labeling and accuracy functions dynamically based on the specified task for core metric computation. Parameters: - task: The sp

opencompass/datasets/calm/evaluation/core_metrics.py:127

↓ 2 callersMethodis_change

Check if there is change in the response in the form of *change me*.

opencompass/datasets/IFEval/instructions.py:709

↓ 2 callersFunctionis_equiv

(str1, str2, verbose=False)

opencompass/datasets/medbench/math_equivalence.py:147

↓ 2 callersMethodis_interval

(self, epr)

opencompass/datasets/OlympiadBench.py:375

↓ 2 callersFunctionis_section_row

(row: List[str])

opencompass/summarizers/multi_model.py:43

↓ 2 callersMethodjudge

(self, expression1, expression2, precision=1e-8)

opencompass/datasets/OlympiadBench.py:326

↓ 2 callersFunctionlaunch

Launch a single task. Args: task (BaseTask): Task to launch. tokens (SyncManager.Semaphore): Multiprocessing semaphore

opencompass/runners/local_api.py:95

↓ 2 callersMethodload

(path: str, name: str, local_mode: bool = False)

opencompass/datasets/ceval.py:18

↓ 2 callersMethodload

(path: str)

opencompass/datasets/triviaqa.py:20

↓ 2 callersMethodload

(path)

opencompass/datasets/piqa.py:35

↓ 2 callersMethodload

(path)

opencompass/datasets/winogrande.py:18

↓ 2 callersMethodload

(path: str, name: str)

opencompass/datasets/arc.py:17

↓ 2 callersMethodload

(path: str, name: str, **kwargs)

opencompass/datasets/mmlu.py:18

↓ 2 callersMethodload

(path)

opencompass/datasets/siqa.py:35

↓ 2 callersMethodload

Load dataset. Args: path(str): Data path of the dataset. libs(Optional[Union[str, list]]): All the libraries to be

opencompass/datasets/ds1000.py:89

↓ 2 callersMethodload

(path: str, name: str)

opencompass/datasets/chembench.py:16

↓ 2 callersMethodload

(path: str, index: str)

opencompass/datasets/lawbench/lawbench.py:21

↓ 2 callersMethodload

(path: str, dataset_splits: List[str] = [ 'CNMO', 'CCEE',

opencompass/datasets/livemathbench/livemathbench.py:31

↓ 2 callersMethodload

( path: str, dataset: str = 'squad', max_seq_length: int = 4096, tokenizer_mod

opencompass/datasets/ruler/ruler_qa.py:22

↓ 2 callersMethodload_contamination_annotations

(path, split='val')

opencompass/datasets/ceval.py:46

↓ 2 callersMethodload_contamination_annotations

(path, split='val')

opencompass/datasets/mmlu.py:64

↓ 2 callersFunctionload_dataset

(dataset_name, setting_name, parent_path, prompt_path=None,

opencompass/datasets/medbench/dataset_loader.py:228

↓ 2 callersFunctionload_datasets

(source, conf)

tests/dataset/test_ms_datasets.py:94

↓ 2 callersFunctionload_datasets

(source, conf)

tests/dataset/test_local_datasets.py:94

↓ 2 callersFunctionload_datasets_conf

(source)

tests/dataset/test_ms_datasets.py:88

↓ 2 callersFunctionload_json

Load JSON data from a file.

opencompass/datasets/opi/utils/accuracy4fold_type.py:6

↓ 2 callersMethodload_single

(src_path, tgt_path, src_lang, tgt_lang)

opencompass/datasets/flores.py:17

↓ 2 callersFunctionload_yaml

Load a YAML file.

opencompass/datasets/korbench/korbench_utils.py:10

↓ 2 callersFunctionload_yaml

Load a YAML file.

opencompass/datasets/supergpqa/supergpqa_utils.py:10

↓ 2 callersFunctionlower

(text)

opencompass/datasets/longbench/evaluators.py:28

↓ 2 callersFunctionmain

()

opencompass/cli/main.py:247

← previous next →401–500 of 3,711, ranked by callers