MCPcopy Create free account

hub / github.com/ML-GSAI/LLaDA / functions

Functions3,438 in github.com/ML-GSAI/LLaDA

⨍ Functions 3,438◇ Types & classes 889↳ Endpoints 19
↓ 2 callersMethodto_dict
(self)
opencompass/opencompass/datasets/medbench/constructions.py:21
↓ 2 callersMethodto_dict
(self)
opencompass/opencompass/datasets/medbench/constructions.py:61
↓ 2 callersMethodtrans_plus_minus_sign
(self, expr_list: list)
opencompass/opencompass/datasets/OlympiadBench.py:315
↓ 2 callersMethodtransform
(item)
opencompass/opencompass/datasets/livecodebench/livecodebench.py:211
↓ 2 callersFunctionvl_model_score
(model, pred_img, ori_prompt, judge_prompt)
opencompass/opencompass/datasets/cibench.py:187
↓ 2 callersFunctionwhite_space_fix
(text)
opencompass/opencompass/datasets/longbench/evaluators.py:21
↓ 2 callersFunctionwmt_postprocess
(text: str, lang: str)
opencompass/opencompass/datasets/PMMEval/flores.py:18
↓ 2 callersMethodwrite_to_json
Dump the result to a json file.
opencompass/opencompass/openicl/icl_inferencer/icl_inference_ppl_only_inferencer.py:230
↓ 2 callersMethodwrite_to_json
Dump the result to a json file.
opencompass/opencompass/openicl/icl_inferencer/icl_chat_inferencer.py:131
↓ 2 callersMethodwrite_to_json
Dump the result to a json file.
opencompass/opencompass/openicl/icl_inferencer/icl_mink_percent_inferencer.py:181
↓ 2 callersMethodwrite_to_json
Dump the result to a json file.
opencompass/opencompass/openicl/icl_inferencer/icl_sw_ce_loss_inferencer.py:342
↓ 2 callersMethodwrite_to_json
Dump the result to a json file.
opencompass/opencompass/openicl/icl_inferencer/icl_ppl_only_inferencer.py:180
↓ 2 callersMethodwrite_to_json
Dump the result to a json file.
opencompass/opencompass/openicl/icl_inferencer/icl_base_inferencer.py:170
↓ 1 callersFunctionEED
Computes the similarity score and distance metrics between two LaTeX expressions. This function evaluates the equivalence of two mathematical
opencompass/opencompass/datasets/phybench/EED.py:253
↓ 1 callersFunctionReCoRD_postprocess
(text: str)
opencompass/opencompass/datasets/record.py:77
↓ 1 callersFunctionXsum_postprocess
(text: str)
opencompass/opencompass/datasets/xsum.py:52
↓ 1 callersFunction__extract_entities_pred
(pred, entity_types)
opencompass/opencompass/datasets/lawbench/utils/comprehension_scores.py:71
↓ 1 callersFunction__extract_entities_ref
(ref)
opencompass/opencompass/datasets/lawbench/utils/comprehension_scores.py:54
↓ 1 callersFunction__find_substring_starts
(s, target)
opencompass/opencompass/datasets/lawbench/utils/comprehension_scores.py:11
↓ 1 callersMethod__init__
(self)
opencompass/opencompass/lagent/actions/python_interpreter.py:18
↓ 1 callersMethod__init__
(self, use_system_role: bool = True, first_system_role: bool = True,
opencompass/opencompass/lagent/agents/react.py:77
↓ 1 callersMethod__init__
( self, model: BaseModel, max_out_len: int, stopping_criteria:
opencompass/opencompass/openicl/icl_inferencer/icl_gen_inferencer.py:50
↓ 1 callersMethod__init__
(self, data: List[Any])
opencompass/opencompass/openicl/icl_retriever/icl_topk_retriever.py:149
↓ 1 callersMethod__init__
(self, model='gpt-3.5-turbo-16k', temperature=0, **kwargs)
opencompass/opencompass/openicl/icl_evaluator/icl_agent_evaluator.py:121
↓ 1 callersMethod__init__
(self, k: List[int] = [1, 10, 100])
opencompass/opencompass/datasets/humaneval.py:73
↓ 1 callersMethod__init__
(self, options)
opencompass/opencompass/datasets/custom.py:23
↓ 1 callersMethod__init__
(self, version='v1', pred_postprocessor=None)
opencompass/opencompass/datasets/math.py:207
↓ 1 callersMethod__init__
(self)
opencompass/opencompass/datasets/OlympiadBench.py:279
↓ 1 callersMethod__init__
(self, cmd)
opencompass/opencompass/datasets/ds1000.py:283
↓ 1 callersMethod__init__
(self)
opencompass/opencompass/datasets/leval/evaluators.py:117
↓ 1 callersMethod__init__
(self, path: str, hf_cache_dir: Optional[str] = None, max_s
opencompass/opencompass/models/dllm.py:116
↓ 1 callersMethod__init__
( self, path: str = 'LightllmAPI', url: str = 'http://localhost:8080/gener
opencompass/opencompass/models/lightllm_api.py:25
↓ 1 callersMethod__init__
( self, path: str, token: str, url: str, meta_template: Optional[Dict]
opencompass/opencompass/models/bailing_api_oc.py:55
↓ 1 callersMethod__init__
( self, path: str = 'gpt-3.5-turbo', max_seq_len: int = 16384, query_per_secon
opencompass/opencompass/models/openai_api.py:81
↓ 1 callersMethod__init__
( self, path: str, key: str, group_id: str, model_type: str = 'chat',
opencompass/opencompass/models/minimax_api.py:35
↓ 1 callersMethod__init__
(self, path: str, appid: str, api_secret: str,
opencompass/opencompass/models/xunfei_api.py:32
↓ 1 callersMethod__init__
(self, path: str, hf_cache_dir: Optional[str] = None, max_s
opencompass/opencompass/models/huggingface.py:91
↓ 1 callersFunction_aggregate_get_clipped_mean
( single_eval_results: list[SingleEvalResult], )
opencompass/opencompass/datasets/healthbench/healthbench.py:230
↓ 1 callersMethod_batch_generate
Support for batch prompts inference. Args: inputs (List[str]): A list of strings. max_out_len (int): The maximum leng
opencompass/opencompass/models/huggingface.py:256
↓ 1 callersMethod_bin_trim
Get a suffix of prompt which is no longer than num_token tokens. Args: prompt (str): Input string. num_token (int): T
opencompass/opencompass/models/openai_api.py:440
↓ 1 callersMethod_build_pipe
(self, model_path, backend, engine_config)
opencompass/opencompass/models/turbomind.py:231
↓ 1 callersMethod_build_pipe
(self, model_path, backend, engine_config)
opencompass/opencompass/models/turbomind_with_tf_above_v4_33.py:206
↓ 1 callersMethod_build_results
(self, extracted_predictions, metrics, eval_results, final_metadata)
opencompass/opencompass/datasets/livecodebench/evaluator.py:251
↓ 1 callersMethod_calculate_group_metrics
The function calculates the numerical results for each group based on the configuration in summary_groups, and updates the contents of
opencompass/opencompass/summarizers/default_subjective.py:175
↓ 1 callersMethod_call
(self, command: str)
opencompass/opencompass/lagent/actions/python_interpreter.py:139
↓ 1 callersFunction_check_data
(ms_dataset: Dataset | DatasetDict, oc_dataset: Dataset | DatasetDict, sample_
opencompass/tests/dataset/test_ms_datasets.py:176
↓ 1 callersFunction_check_dataset
(obj)
opencompass/opencompass/utils/types.py:34
↓ 1 callersMethod_check_revolve
(span_a, span_b)
opencompass/opencompass/datasets/lawbench/utils/modules/merger.py:30
↓ 1 callersFunction_check_str
(obj)
opencompass/opencompass/utils/types.py:50
↓ 1 callersMethod_check_template_legacy
(self)
opencompass/opencompass/openicl/icl_prompt_template.py:46
↓ 1 callersMethod_choose_flavor
(self, num_gpus)
opencompass/opencompass/runners/volc.py:254
↓ 1 callersMethod_clean_text
Performs invalid character removal and whitespace cleanup on text.
opencompass/opencompass/datasets/lawbench/utils/modules/tokenization.py:236
↓ 1 callersFunction_clean_up_code
Cleans up the generated code.
opencompass/opencompass/datasets/PMMEval/humanevalxl.py:151
↓ 1 callersMethod_code_eval_service
Send code to the remote evaluation service using gradio_client and get the results. Args: input_data: Can be one of:
opencompass/opencompass/openicl/icl_evaluator/code_evaluator.py:56
↓ 1 callersMethod_code_eval_service
(self, file_path)
opencompass/opencompass/datasets/humanevalx.py:143
↓ 1 callersMethod_code_eval_service
Access the code eval service. Args: file_path (str): The file path to the file to be evaluated. Returns: tup
opencompass/opencompass/datasets/ds1000.py:415
↓ 1 callersMethod_code_eval_service
(self, file_path)
opencompass/opencompass/datasets/humaneval_multi.py:108
↓ 1 callersMethod_code_eval_service
(self, file_path)
opencompass/opencompass/datasets/PMMEval/humanevalxl.py:123
↓ 1 callersMethod_compile_cpp
Compiles C++ source code.
opencompass/opencompass/datasets/codecompass/executor.py:41
↓ 1 callersFunction_compute_clipped_stats
Computes the mean (clipped to [0, 1]), bootstrap std for that mean, and n_samples for final HealthBench scoring.
opencompass/opencompass/datasets/healthbench/healthbench.py:208
↓ 1 callersMethod_compute_turn_score
(a_gold_list, a_pred)
opencompass/opencompass/datasets/lawbench/utils/rc_f1.py:85
↓ 1 callersMethod_convert_dtype
(self, default_dtype, model_dtype=None)
opencompass/opencompass/models/interntrain.py:290
↓ 1 callersMethod_create_evaluation_sample
( item: Dict[str, Any])
opencompass/opencompass/datasets/codecompass/CodeCompass.py:174
↓ 1 callersMethod_create_fresh_client
Create a fresh OpenAI client for each request to avoid concurrency issues.
opencompass/opencompass/models/openai_streaming.py:80
↓ 1 callersMethod_encode_pair
(self, context, continuation)
eval_llada.py:196
↓ 1 callersMethod_encode_speical_tokens
Encode the special tokens in the prompt. Now this is left for the future work
opencompass/opencompass/models/base.py:502
↓ 1 callersMethod_evaluate
Evaluate the response data sample.
opencompass/opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py:148
↓ 1 callersMethod_evaluate
Evaluate the response data sample.
opencompass/opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py:380
↓ 1 callersMethod_evaluate
(self, data_sample)
opencompass/opencompass/datasets/teval/evaluators/planning_evaluator.py:218
↓ 1 callersMethod_evaluate
(self, data_sample: dict)
opencompass/opencompass/datasets/teval/evaluators/instruct_evaluator.py:63
↓ 1 callersMethod_evaluate_predictions
Evaluate predictions using the configured evaluator.
opencompass/opencompass/tasks/openicl_eval.py:229
↓ 1 callersMethod_extract_limits
(problem_text: str)
opencompass/opencompass/datasets/codecompass/CodeCompass.py:94
↓ 1 callersFunction_fix_a_slash_b
(string)
opencompass/opencompass/datasets/agieval/math_equivalence.py:37
↓ 1 callersFunction_fix_a_slash_b
(string)
opencompass/opencompass/datasets/medbench/math_equivalence.py:37
↓ 1 callersFunction_fix_fracs
(string)
opencompass/opencompass/datasets/agieval/math_equivalence.py:5
↓ 1 callersFunction_fix_fracs
(string)
opencompass/opencompass/datasets/medbench/math_equivalence.py:5
↓ 1 callersFunction_fix_sqrt
(string)
opencompass/opencompass/datasets/agieval/math_equivalence.py:62
↓ 1 callersFunction_fix_sqrt
(string)
opencompass/opencompass/datasets/medbench/math_equivalence.py:62
↓ 1 callersMethod_fix_sqrt
(self, string)
opencompass/opencompass/datasets/math.py:286
↓ 1 callersMethod_fix_sqrt_v2
(self, string)
opencompass/opencompass/datasets/math.py:300
↓ 1 callersMethod_format_md_table
(table)
opencompass/opencompass/summarizers/default.py:316
↓ 1 callersMethod_format_raw_txt
(self, raw_results)
opencompass/opencompass/summarizers/default_subjective.py:324
↓ 1 callersMethod_format_table
(self, parsed_results, dataset_metrics, dataset_eval_mode, required_dataset_abbrs=None, skip_all_slash=False)
opencompass/opencompass/summarizers/default_subjective.py:272
↓ 1 callersMethod_format_table
(self, parsed_results, dataset_metrics, dataset_eval_mode)
opencompass/opencompass/summarizers/llm_compression.py:27
↓ 1 callersMethod_format_table
(self, parsed_results, dataset_metrics, dataset_eval_mode)
opencompass/opencompass/summarizers/needlebench.py:610
↓ 1 callersMethod_format_table_pivot
Format table as a pandas dataframe and pivot so that columns are datasets and rows are models. Args: table (List[List]):
opencompass/opencompass/summarizers/llm_compression.py:91
↓ 1 callersMethod_forward_process
(self, batch, prompt_index)
eval_llada.py:113
↓ 1 callersFunction_gaokao_register
(question_type)
opencompass/opencompass/datasets/GaokaoBench.py:152
↓ 1 callersMethod_generate
Generate results given a list of inputs. Args: inputs (PromptType): A string or PromptDict. The PromptDict should
opencompass/opencompass/models/openai_api.py:202
↓ 1 callersMethod_generate
( self, input: PromptType, max_out_len: int = 512, )
opencompass/opencompass/models/xunfei_api.py:282
↓ 1 callersMethod_generate_access_token
(self)
opencompass/opencompass/models/baidu_api.py:63
↓ 1 callersFunction_generic_llmjudge_postprocess
(judgement: str)
opencompass/opencompass/datasets/medmcqa.py:127
↓ 1 callersFunction_generic_llmjudge_postprocess
(judgement: str)
opencompass/opencompass/datasets/Medbullets.py:137
↓ 1 callersFunction_generic_llmjudge_postprocess
(judgement: str)
opencompass/opencompass/datasets/MedXpertQA.py:106
↓ 1 callersFunction_generic_llmjudge_postprocess
(judgement: str)
opencompass/opencompass/datasets/supergpqa/supergpqa.py:203
↓ 1 callersMethod_get_class_diff
d == 3 for equivalent semantics d == 0 for completely different semantics 根据大词林的信息，计算两个词的语义类别的差距
opencompass/opencompass/datasets/lawbench/utils/modules/alignment.py:111
↓ 1 callersMethod_get_cross_entropy
Calculate cross entropy based on given logits, targets and attention_mask for BPC loss calculation. Args: logits (np.ndar
opencompass/opencompass/openicl/icl_inferencer/icl_sw_ce_loss_inferencer.py:235
↓ 1 callersFunction_get_last_digit
(s)
opencompass/opencompass/datasets/PMMEval/mgsm.py:13
↓ 1 callersMethod_get_llm_correctness
Determine if the LLM judge considers the answer correct. Args: llm_detail: The evaluation details from the LLM judge. Re
opencompass/opencompass/evaluator/cascade_evaluator.py:101
↓ 1 callersFunction_get_meta_template
(meta_template)
opencompass/opencompass/models/huggingface_above_v4_33.py:115
← previousnext →501–600 of 3,438, ranked by callers