MCPcopy Create free account

hub / github.com/Feng-Hong/WINO-DLLM / functions

Functions4,510 in github.com/Feng-Hong/WINO-DLLM

⨍ Functions 4,510◇ Types & classes 452↳ Endpoints 18
↓ 1 callersFunction_padding_224
(frames)
MMaDA/lmms_eval/lmms_eval/models/internvideo2.py:117
↓ 1 callersFunction_padding_224
(frames)
MMaDA/lmms_eval/lmms_eval/models/videochat2.py:114
↓ 1 callersMethod_parse_response
Parse the raw response into a structured object, depending on the parser.
MMaDA/lmms_eval/lmms_eval/tasks/megabench/evaluator.py:297
↓ 1 callersMethod_post_request
(self, payload)
MMaDA/lmms_eval/lmms_eval/tasks/mathverse/mathverse_evals.py:98
↓ 1 callersMethod_post_request
(self, payload)
MMaDA/lmms_eval/lmms_eval/tasks/hrbench/hrbench_evals.py:36
↓ 1 callersMethod_post_request
(self, payload)
MMaDA/lmms_eval/lmms_eval/tasks/mmupd/mmupd_evals.py:400
↓ 1 callersMethod_post_request
(self, payload)
MMaDA/lmms_eval/lmms_eval/tasks/mmbench/mmbench_evals.py:131
↓ 1 callersMethod_post_request
(self, payload)
MMaDA/lmms_eval/lmms_eval/tasks/worldqa/worldqa_mc_evaluator.py:72
↓ 1 callersMethod_prepare_metric_and_aggregation
(self)
MMaDA/lmms_eval/lmms_eval/api/task.py:815
↓ 1 callersMethod_prepare_model_specific_config
(self)
MMaDA/lmms_eval/lmms_eval/api/task.py:790
↓ 1 callersMethod_preprocess_accelerate
r""" Some pre-processing hacks to make the model `accelerate` compatible. Check https://github.com/huggingface/transformers/pull/217
MMaDA/lmms_eval/lmms_eval/models/mplug_owl_video/modeling_mplug_owl.py:1357
↓ 1 callersFunction_remove_right_units
(string)
MMaDA/lmms_eval/lmms_eval/tasks/mathvision/eval_utils.py:292
↓ 1 callersFunction_rgba_to_rgb
(image)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/image_video_utils.py:22
↓ 1 callersMethod_sanitize_results_dict
Sanitize the results dictionary.
MMaDA/lmms_eval/lmms_eval/logging_utils.py:117
↓ 1 callersMethod_sanitize_results_dict
Sanitize the results dictionary.
MMaDA/lmms_eval/lmms_eval/loggers/wandb_logger.py:70
↓ 1 callersMethod_scaled_dot_product_attention
Computes scaled dot product attention on query, key and value tensors, using an optional attention mask if passed, and applying dropo
LLaDA/modeling_llada.py:629
↓ 1 callersMethod_scaled_dot_product_attention
Computes scaled dot product attention on query, key and value tensors, using an optional attention mask if passed, and applying dro
MMaDA/lmms_eval/lmms_eval/models/model_mmada/modeling_llada.py:629
↓ 1 callersMethod_scaled_dot_product_attention
Computes scaled dot product attention on query, key and value tensors, using an optional attention mask if passed, and applying dro
MMaDA/models/modeling_llada.py:629
↓ 1 callersFunction_search_by_image
(image_url, screenshot_path="search_results.png", delay=5.0, headless=True)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/utils/utils.py:378
↓ 1 callersMethod_should_omit_lexeme
(self, lexeme: str)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:245
↓ 1 callersMethod_split_long_sentences
(self, analyzed_sentences: List[List[LexemeWithPositions]])
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:156
↓ 1 callersFunction_strip_string
(string)
MMaDA/lmms_eval/lmms_eval/tasks/mathvision/eval_utils.py:328
↓ 1 callersFunction_take_fullpage_screenshot
(url: str, screenshot_path: str, timeout: int = FULLPAGE_TIMEOUT)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/utils/utils.py:197
↓ 1 callersMethod_task_needs_eval
(self, task: Dict)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/evaluator.py:61
↓ 1 callersMethod_temp_convert_self_to_deprecated_attention_blocks
(self)
MMaDA/lmms_eval/lmms_eval/models/model_mmada/modeling_utils.py:1106
↓ 1 callersMethod_temp_convert_self_to_deprecated_attention_blocks
(self)
MMaDA/models/modeling_utils.py:1106
↓ 1 callersFunction_tokenize_prompt
(prompt, tokenizer, add_BOS=False, media_info={"<image>": 65, "<|video|>": 65}, **kwargs)
MMaDA/lmms_eval/lmms_eval/models/mplug_owl_video/processing_mplug_owl.py:232
↓ 1 callersFunction_tokenize_prompts_and_batch
Given a set of prompts and number of tokens to generate: - tokenize prompts - set the sequence length to be the max of length of prompts
MMaDA/lmms_eval/lmms_eval/models/mplug_owl_video/processing_mplug_owl.py:190
↓ 1 callersMethod_tokens_match
(self, prev_tokens: torch.LongTensor, tokens: List[int])
MMaDA/lmms_eval/lmms_eval/models/model_utils/qwen/qwen_generate_utils.py:310
↓ 1 callersMethod_transform_lexeme
(self, lexeme: str)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:253
↓ 1 callersMethod_undo_temp_convert_self_to_deprecated_attention_blocks
(self)
MMaDA/lmms_eval/lmms_eval/models/model_mmada/modeling_utils.py:1133
↓ 1 callersMethod_undo_temp_convert_self_to_deprecated_attention_blocks
(self)
MMaDA/models/modeling_utils.py:1133
↓ 1 callersMethod_update_image_path
(image_path)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/vlm_as_judge.py:44
↓ 1 callersFunctionabs_dist_norm
(pred, target)
MMaDA/lmms_eval/lmms_eval/tasks/vsibench/utils.py:88
↓ 1 callersFunctionadaptive_pixel_slimming
(image_path, RESIZE_W=1024, RESIZE_H=5120, thresh_gradmap=200, thresh_gradsum=50, thresh_length=15)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/utils/image_utils.py:32
↓ 1 callersMethodaggregate
Aggregate the field scores.
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/aggregation_type.py:28
↓ 1 callersFunctionalibi_attention_bias
(seq_len: int, config: ModelConfig, device: torch.device)
LLaDA/modeling_llada.py:511
↓ 1 callersFunctionalibi_attention_bias
(seq_len: int, config: ModelConfig, device: torch.device)
MMaDA/lmms_eval/lmms_eval/models/model_mmada/modeling_llada.py:511
↓ 1 callersFunctionalibi_attention_bias
(seq_len: int, config: ModelConfig, device: torch.device)
MMaDA/models/modeling_llada.py:511
↓ 1 callersMethodanalyze_excerpts
(self, text: str)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:76
↓ 1 callersMethodanalyze_sentences
(self, text: str)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:141
↓ 1 callersMethodanswer
(self, img_list, input_text, max_new_tokens=300, num_beams=1, min_length=1, top_p=0.9, repetition_penalty=1.0,
MMaDA/lmms_eval/lmms_eval/models/moviechat.py:285
↓ 1 callersMethodapply
(self, resps, docs)
MMaDA/lmms_eval/lmms_eval/tasks/muirbench/utils.py:87
↓ 1 callersMethodapply
(self, resps, docs)
MMaDA/lmms_eval/lmms_eval/tasks/ai2d/utils.py:58
↓ 1 callersMethodapply
(self, resps, docs)
MMaDA/lmms_eval/lmms_eval/tasks/mmlu/flan_cot_zeroshot/utils.py:34
↓ 1 callersMethodapply_filters
Iterates over FilterEnsembles and applies them to instances
MMaDA/lmms_eval/lmms_eval/api/task.py:593
↓ 1 callersFunctionbacktrack
Using backtracking, determine if there is a sequence of pronunciations that is in iambic pentameter.
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/constrained_generation.py:209
↓ 1 callersFunctionbootstrap_std
Args: data: a list of values n_bootstrap: number of bootstrap samples ci: confidence interval Returns: a tupl
MMaDA/lmms_eval/lmms_eval/tasks/vcr_wiki/utils.py:254
↓ 1 callersFunctionbootstrap_stderr
(f, xs, iters)
MMaDA/lmms_eval/lmms_eval/api/metrics.py:505
↓ 1 callersFunctionbox_iou
(box1, box2)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/common/metrics.py:12
↓ 1 callersMethodbuild_all_requests
Build a set of Instances for a task, and store them in task.instances
MMaDA/lmms_eval/lmms_eval/api/task.py:382
↓ 1 callersFunctionbuild_mmecot_gpt4_prompt
(question_data)
MMaDA/lmms_eval/lmms_eval/tasks/mme_cot/utils.py:52
↓ 1 callersFunctionbuild_olympiadbench_gpt4_prompt
(question_data)
MMaDA/lmms_eval/lmms_eval/tasks/olympiadbench/testmini_utils.py:47
↓ 1 callersMethodbuild_option_str
(self, option_list)
MMaDA/lmms_eval/lmms_eval/tasks/mmbench/mmbench_evals.py:33
↓ 1 callersMethodbuild_option_str_w_gt
(self, option_list, gt_text, eval_type, question_type, upd_type)
MMaDA/lmms_eval/lmms_eval/tasks/mmupd/mmupd_evals.py:144
↓ 1 callersMethodbuild_prompt
(self, question, options, prediction)
MMaDA/lmms_eval/lmms_eval/tasks/hrbench/hrbench_evals.py:133
↓ 1 callersMethodbuild_prompt
(self, question, options, prediction, upd_type)
MMaDA/lmms_eval/lmms_eval/tasks/mmupd/mmupd_evals.py:259
↓ 1 callersMethodbuild_prompt
(self, question, options, prediction)
MMaDA/lmms_eval/lmms_eval/tasks/mmbench/mmbench_evals.py:59
↓ 1 callersMethodbuild_prompt
(self, question, options, prediction)
MMaDA/lmms_eval/lmms_eval/tasks/worldqa/worldqa_mc_evaluator.py:22
↓ 1 callersFunctionbuild_zh_exam_k12_gpt4_prompt
(question_data)
MMaDA/lmms_eval/lmms_eval/tasks/k12/utils.py:44
↓ 1 callersMethodcal_acc
Calculate normalized tree edit distance(nTED) based accuracy. 1) Construct tree from dict, 2) Get tree distance with insert/r
MMaDA/lmms_eval/lmms_eval/tasks/synthdog/donut_evaluator.py:190
↓ 1 callersMethodcalculate_aggregate_metric
(self, bootstrap_iters=100000)
MMaDA/lmms_eval/lmms_eval/evaluator_utils.py:106
↓ 1 callersMethodcalculate_dual_acc
(self, standard_df, upd_df)
MMaDA/lmms_eval/lmms_eval/tasks/mmupd/mmupd_evals.py:600
↓ 1 callersMethodcalculate_hit_rates
(self, data)
MMaDA/lmms_eval/lmms_eval/tasks/mmbench/mmbench_evals.py:223
↓ 1 callersFunctioncalculate_ins_level_acc
Calculate the instruction level accuracy for given Subject results https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c35
MMaDA/lmms_eval/lmms_eval/tasks/longvideobench/utils.py:265
↓ 1 callersFunctioncalculate_iou
(range_1, range_2)
MMaDA/lmms_eval/lmms_eval/tasks/plm_videobench/eval_utils.py:19
↓ 1 callersFunctioncalculate_model_summary
Re-calculate model performance summary statistics across core and open tasks. Args: task_results: List of task results with scores
MMaDA/lmms_eval/lmms_eval/tasks/megabench/breakdown/derive_breakdown_results.py:8
↓ 1 callersFunctioncalculate_proximity_score
Calculate the proximity score based on the location. Exponentially decreases depending on the distance. Args: guess_coords (float, f
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/geo_proximity.py:107
↓ 1 callersMethodcall_gpt
(self, system_prompt, user_prompt)
MMaDA/lmms_eval/lmms_eval/tasks/capability/utils.py:436
↓ 1 callersMethodcan_infer_option
(self, answer, choices)
MMaDA/lmms_eval/lmms_eval/tasks/hrbench/hrbench_evals.py:45
↓ 1 callersMethodcan_infer_option
(self, answer, option_dict, question_type=None, valid_option=None)
MMaDA/lmms_eval/lmms_eval/tasks/mmupd/mmupd_evals.py:329
↓ 1 callersMethodcan_infer_option
(self, answer, num_choice=5)
MMaDA/lmms_eval/lmms_eval/tasks/mmbench/mmbench_evals.py:81
↓ 1 callersMethodcan_infer_text
(self, answer, choices)
MMaDA/lmms_eval/lmms_eval/tasks/hrbench/hrbench_evals.py:81
↓ 1 callersMethodcan_infer_text
(self, answer, choices)
MMaDA/lmms_eval/lmms_eval/tasks/mmbench/mmbench_evals.py:109
↓ 1 callersFunctioncast_tuple
(t, length=1)
MMaDA/lmms_eval/lmms_eval/models/model_mmada/common_modules.py:235
↓ 1 callersFunctioncast_tuple
(t, length=1)
MMaDA/models/common_modules.py:235
↓ 1 callersFunctioncausal_attention_bias
(seq_len: int, device: torch.device)
LLaDA/modeling_llada.py:490
↓ 1 callersFunctioncausal_attention_bias
(seq_len: int, device: torch.device)
MMaDA/lmms_eval/lmms_eval/models/model_mmada/modeling_llada.py:490
↓ 1 callersFunctioncausal_attention_bias
(seq_len: int, device: torch.device)
MMaDA/models/modeling_llada.py:490
↓ 1 callersFunctionchased_dp_assignment
dp matching from https://github.com/fujiso/SODA/blob/master/soda.py.
MMaDA/lmms_eval/lmms_eval/tasks/plm_videobench/eval_utils.py:89
↓ 1 callersFunctionchat_compeletion_openai
(model, messages, temperature, max_tokens)
MMaDA/lmms_eval/lmms_eval/tasks/egothink/utils.py:84
↓ 1 callersFunctionchdir
(root)
LLaDA/dataset_utils/eval_correctness_mbpp/execution.py:645
↓ 1 callersFunctioncheck_ans
Check if the predicted answer matches the ground truth answer. Args: pred (str): The predicted answer. gt (str): The ground
MMaDA/lmms_eval/lmms_eval/tasks/plm_videobench/fgqa/fgqa_utils.py:84
↓ 1 callersFunctioncheck_constraint
(response, constraint, constraint_val)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/constrained_generation.py:276
↓ 1 callersFunctioncheck_is_number
(string)
MMaDA/lmms_eval/lmms_eval/tasks/videommmu/utils.py:445
↓ 1 callersFunctioncheck_is_number
(string)
MMaDA/lmms_eval/lmms_eval/tasks/cmmmu/utils.py:281
↓ 1 callersFunctioncheck_is_number
Check if the given string a number. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c3508794/eval/eval_utils.py#L
MMaDA/lmms_eval/lmms_eval/tasks/jmmmu/utils.py:354
↓ 1 callersFunctioncheck_is_number
Check if the given string a number. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c3508794/eval/eval_utils.py#L
MMaDA/lmms_eval/lmms_eval/tasks/mmmu_pro/utils.py:363
↓ 1 callersFunctioncheck_is_number
Check if the given string a number. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c3508794/eval/eval_utils.py#L
MMaDA/lmms_eval/lmms_eval/tasks/mmmu/utils.py:475
↓ 1 callersFunctioncheck_is_number
Check if the given string a number. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c3508794/eval/eval_utils.py#L
MMaDA/lmms_eval/lmms_eval/tasks/mmmu/utils_group_img.py:463
↓ 1 callersFunctioncheck_is_number
Check if the given string a number. https://github.com/MMMU-Benchmark/MMMU/blob/51ce7f3e829c16bb44bc5445782686b4c3508794/eval/eval_utils.py#L
MMaDA/lmms_eval/lmms_eval/tasks/mirb/utils.py:68
↓ 1 callersFunctioncheck_pre_conds_satisfy
(current_state, pre_conds, param_to_obj)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/symbolic_planning.py:173
↓ 1 callersMethodclass_impl
(self)
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/metric_type.py:121
↓ 1 callersFunctionclean_text
(text)
MMaDA/lmms_eval/lmms_eval/tasks/mmsearch/utils/web_content_utils.py:6
↓ 1 callersFunctionclean_units
Clean the units in the number.
MMaDA/lmms_eval/lmms_eval/tasks/megabench/metrics/scoring/general_numerical_match.py:88
↓ 1 callersFunctioncli_evaluate
(args: Union[argparse.Namespace, None] = None)
MMaDA/lmms_eval/lmms_eval/__main__.py:273
↓ 1 callersFunctioncli_evaluate_single
(args: Union[argparse.Namespace, None] = None)
MMaDA/lmms_eval/lmms_eval/__main__.py:372
↓ 1 callersFunctioncn_math_expression_evaluation
(predict, answers)
MMaDA/lmms_eval/lmms_eval/tasks/ocrbench_v2/vqa_metric.py:256
↓ 1 callersFunctioncn_vqa_evaluation
(predict, answers)
MMaDA/lmms_eval/lmms_eval/tasks/ocrbench_v2/vqa_metric.py:69
↓ 1 callersFunctioncollect_task_metadata
Collect task metadata for a model's results using the all_task_meta.json file
MMaDA/lmms_eval/lmms_eval/tasks/megabench/breakdown/analysis_utils.py:75
← previousnext →701–800 of 4,510, ranked by callers