MCPcopy Create free account

hub / github.com/FeiElysia/Tempo / functions

Functions7,449 in github.com/FeiElysia/Tempo

⨍ Functions 7,449◇ Types & classes 488↳ Endpoints 41
↓ 2 callersFunction_find_last_json_list
(text: str)
lmms_eval/tasks/uni_mmmu/utils.py:105
↓ 2 callersFunction_float_precision
(value: float)
lmms_eval/tasks/mmlongbench_doc/utils.py:97
↓ 2 callersMethod_forward
(self, images)
tempo/multimodal_encoder/base_encoder.py:52
↓ 2 callersMethod_generate_dataset
Generate a dataset from evaluation data. Args: data (List[Dict[str, Any]]): The data to generate a dataset for. confi
lmms_eval/logging_utils.py:239
↓ 2 callersMethod_generate_dataset
Generate a dataset from evaluation data. Args: data (List[Dict[str, Any]]): The data to generate a dataset for. confi
lmms_eval/loggers/wandb_logger.py:185
↓ 2 callersMethod_generate_nonoverlapping_excerpts
(self, analyzed_sentences: List[List[LexemeWithPositions]])
lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:100
↓ 2 callersFunction_get_cache_dir
()
lmms_eval/tasks/cover/utils.py:28
↓ 2 callersFunction_get_category_from_doc
Infer category from document. Note: This fallback method uses question_index thresholds and may not work correctly with HuggingFace datasets
lmms_eval/tasks/spatial457/utils.py:197
↓ 2 callersFunction_get_client
()
lmms_eval/tasks/charxiv/utils.py:31
↓ 2 callersMethod_get_complementary_model
Lazy-load the complementary model for Visual CoT.
lmms_eval/models/simple/qwen_image_edit.py:477
↓ 2 callersFunction_get_gt_counts
Get ground truth count list from document. Returns list of acceptable integer counts.
lmms_eval/tasks/pushupbench/utils.py:106
↓ 2 callersFunction_get_image
(doc: Dict[str, Any])
lmms_eval/tasks/screenspot_pro/utils.py:10
↓ 2 callersFunction_get_image
(doc: Dict[str, Any])
lmms_eval/tasks/screenspot_v2/utils.py:9
↓ 2 callersFunction_get_image_url
(row_idx: int)
lmms_eval/tasks/pointbench/utils.py:41
↓ 2 callersFunction_get_int_env
(name: str, default: int)
lmms_eval/tasks/kris_bench/utils.py:215
↓ 2 callersMethod_get_model_name
Extracts the model name from the model arguments.
lmms_eval/loggers/evaluation_tracker.py:61
↓ 2 callersFunction_get_target_count
(doc)
lmms_eval/tasks/countix/utils.py:118
↓ 2 callersFunction_get_target_count
(doc)
lmms_eval/tasks/repcount/utils.py:43
↓ 2 callersFunction_get_target_count
(doc)
lmms_eval/tasks/ovr_kinetics/utils.py:16
↓ 2 callersFunction_gold_letter
(doc)
lmms_eval/tasks/minerva/utils.py:64
↓ 2 callersMethod_image_to_base64
Convert PIL Image to base64 data URL.
lmms_eval/models/simple/llama4_scout.py:200
↓ 2 callersFunction_is_answerable
(value: Any)
lmms_eval/tasks/mmlongbench_doc/utils.py:194
↓ 2 callersFunction_is_exact_match_candidate
(text: str)
lmms_eval/tasks/mmlongbench_doc/utils.py:52
↓ 2 callersFunction_is_grid_of_ints
(value)
lmms_eval/tasks/arc_agi_1/utils.py:40
↓ 2 callersFunction_is_yesno_question
Check if question is a yes/no question.
lmms_eval/tasks/captionqa/utils.py:63
↓ 2 callersFunction_load_baseline_from_hf
Load baseline from HuggingFace Hub.
lmms_eval/baselines/loader.py:108
↓ 2 callersFunction_load_from_registry
Load baseline from registry by model and task name.
lmms_eval/baselines/loader.py:58
↓ 2 callersMethod_load_json
(file_path: str)
lmms_eval/tasks/megabench/evaluator.py:357
↓ 2 callersFunction_load_yaml_stripped
(path: Path)
lmms_eval/tasks/browsecomp/utils.py:15
↓ 2 callersFunction_load_yaml_stripped
(path: Path)
lmms_eval/tasks/corecognition/utils.py:23
↓ 2 callersMethod_log_samples_as_artifact
(self, data: List[Dict[str, Any]], task_name: str)
lmms_eval/logging_utils.py:305
↓ 2 callersMethod_log_samples_as_artifact
(self, data: List[Dict[str, Any]], task_name: str)
lmms_eval/loggers/wandb_logger.py:255
↓ 2 callersFunction_looks_like_image_ref
(value: str)
lmms_eval/evaluator.py:134
↓ 2 callersFunction_mask_zip_path
()
lmms_eval/tasks/pointbench/utils.py:81
↓ 2 callersFunction_maybe_consolidate_global_cache
(cache, surprise_threshold: float, consolidation_method: str, consolidation_mem_budget: int)
lmms_eval/models/simple/cambrians_vsr.py:80
↓ 2 callersMethod_maybe_resize_image
(self, img: Image.Image)
lmms_eval/models/simple/vllm.py:394
↓ 2 callersMethod_merge_class_path
( self, current_value: str | None, incoming_value: str | None, *, over
lmms_eval/models/registry_v2.py:220
↓ 2 callersFunction_motionbench_repo_id
()
lmms_eval/tasks/motionbench/utils.py:206
↓ 2 callersMethod_name_is_task
(self, name)
lmms_eval/tasks/__init__.py:167
↓ 2 callersFunction_normalize
( text: str, language: str, *, yue_languages: Collection[str], english_languages: Collecti
lmms_eval/tasks/asr_wer_utils.py:79
↓ 2 callersFunction_normalize
(text)
lmms_eval/tasks/av_asr/utils.py:6
↓ 2 callersFunction_normalize_answer
(text)
lmms_eval/tasks/mme_cc/utils.py:60
↓ 2 callersFunction_normalize_answer
Normalize the ground-truth answer to a single uppercase letter (A-D). Image-choice configs: answer is 0-indexed int -> map to A-D. Text-choic
lmms_eval/tasks/wm_abench/utils.py:40
↓ 2 callersFunction_normalize_count_answer
(answer)
lmms_eval/tasks/countbench/utils.py:27
↓ 2 callersFunction_normalize_for_exact_match
(text: str)
lmms_eval/tasks/browsecomp/utils.py:126
↓ 2 callersFunction_normalize_geometry_answer
(text: str)
lmms_eval/tasks/uni_mmmu/utils.py:117
↓ 2 callersFunction_normalize_grid
(grid: Any)
lmms_eval/tasks/arc_agi_2/utils.py:208
↓ 2 callersFunction_normalize_label
(text)
lmms_eval/tasks/vggsound/utils.py:6
↓ 2 callersFunction_normalize_math_answer
Normalize mathematical answer for comparison.
lmms_eval/tasks/auxsolidmath/utils.py:43
↓ 2 callersFunction_normalize_option
(text)
lmms_eval/tasks/vsisuper/recall/vsr_utils.py:46
↓ 2 callersFunction_normalize_str
(string)
lmms_eval/tasks/websrc/utils.py:118
↓ 2 callersFunction_normalize_text
Normalize text for comparison.
lmms_eval/tasks/videomme/revert_oe_mcq/utils.py:38
↓ 2 callersFunction_normalize_text
(text: Any)
lmms_eval/tasks/dude/utils.py:8
↓ 2 callersFunction_normalize_text
(text: Any)
lmms_eval/tasks/egotempo/utils.py:180
↓ 2 callersFunction_normalize_text
(s: str)
lmms_eval/tasks/unig2u/illusionbench/arshia_utils.py:57
↓ 2 callersFunction_normalize_text
(text)
lmms_eval/tasks/ssv2/utils.py:6
↓ 2 callersFunction_normalize_text
(text: str)
lmms_eval/tasks/zerobench/utils.py:21
↓ 2 callersFunction_normalize_text
(text: Any)
lmms_eval/tasks/mathcanvas/utils.py:22
↓ 2 callersFunction_normalize_text
(text: Any)
lmms_eval/tasks/officeqa/utils.py:8
↓ 2 callersFunction_normalize_text
(text: Any)
lmms_eval/tasks/mmlongbench/utils.py:13
↓ 2 callersFunction_normalize_text_for_matching
(text)
lmms_eval/tasks/neptune/utils.py:46
↓ 2 callersFunction_numeric_value
(text: str)
lmms_eval/tasks/hipho/utils.py:142
↓ 2 callersFunction_parse_choices
Args: raw_choices: A Python list literal or list/tuple from the CSV, e.g., ["A. foo", "B. bar"]. Returns: normalized_choices
lmms_eval/tasks/av_speakerbench/utils.py:18
↓ 2 callersFunction_parse_list
(value: Any)
lmms_eval/tasks/mmlongbench_doc/utils.py:118
↓ 2 callersFunction_patch_cambrian_qwen2
(model)
lmms_eval/models/simple/cambrians_vsc.py:31
↓ 2 callersFunction_percentile
(values: List[float], ratio: float)
lmms_eval/models/simple/dummy.py:47
↓ 2 callersMethod_post_check
(self, line: dict, prefetch: bool = False)
lmms_eval/tasks/seephys/seephys_evals.py:344
↓ 2 callersMethod_preprocess_str
(self, string)
lmms_eval/tasks/multidocvqa/utils.py:82
↓ 2 callersFunction_probe_video_metadata
(video_path: str)
lmms_eval/models/model_utils/load_video.py:24
↓ 2 callersFunction_process_job_status
Process job status and handle terminal states. Returns: Tuple of (should_continue, result_or_none). If should_continue is Fa
lmms_eval/entrypoints/client.py:31
↓ 2 callersMethod_reorder
Reorders the elements in the array based on the sorting function. Parameters: - arr (Union[List, Tuple[Tuple[int, Any], ...]
lmms_eval/utils.py:1229
↓ 2 callersMethod_require_model_id
(self, model_name: str)
lmms_eval/models/registry_v2.py:176
↓ 2 callersMethod_resize_image
(self, image)
lmms_eval/tasks/megabench/metrics/scoring/vlm_as_judge.py:73
↓ 2 callersFunction_resolve_hf_datasets_cache_dir
Pick a datasets cache directory that is safe for file locks.
lmms_eval/api/task.py:71
↓ 2 callersFunction_resolve_logs_root
(logs_path: str)
lmms_eval/tui/server.py:378
↓ 2 callersFunction_resolve_video_path
(video_path)
lmms_eval/tasks/neptune/utils.py:77
↓ 2 callersFunction_resolve_video_path
(clip_id: str)
lmms_eval/tasks/egotempo/utils.py:269
↓ 2 callersMethod_rgba_to_rgb
(image)
lmms_eval/tasks/megabench/metrics/scoring/vlm_as_judge.py:69
↓ 2 callersFunction_safe_literal_eval
(value: Any)
lmms_eval/tasks/mmlongbench_doc/utils.py:29
↓ 2 callersFunction_sanitize_run_id
(run_id: str)
lmms_eval/caching/response_cache.py:106
↓ 2 callersMethod_save_audio
Save audio to cache directory and return path.
lmms_eval/models/simple/baichuan_omni.py:249
↓ 2 callersMethod_save_image
Save image to cache directory and return path.
lmms_eval/models/simple/baichuan_omni.py:242
↓ 2 callersMethod_save_intermediate_artifacts
Save intermediate artifacts for debugging.
lmms_eval/models/simple/ovis_u1.py:280
↓ 2 callersMethod_save_intermediate_artifacts
Save intermediate artifacts for debugging.
lmms_eval/models/simple/illume_plus.py:1501
↓ 2 callersMethod_save_results
Safe-write a JSON file via temp file + replace. Since the results file is long, this avoid breaking the file in case of a crash.
lmms_eval/tasks/megabench/evaluator.py:362
↓ 2 callersFunction_serialize_response
(response: Any)
lmms_eval/caching/response_cache.py:343
↓ 2 callersFunction_sort_task_dict
Helper utility. Sorts the task dict at the current level of the hierarchy based on alphabetized task name. Required so that we end up
lmms_eval/evaluator_utils.py:319
↓ 2 callersFunction_split_analyzed_text_to_nonoverlapping_excerpts
(analyzed_lexemes: List[LexemeWithPositions], excerpt_len: int)
lmms_eval/tasks/mmsearch/retrieve_content/tokenization/tokenizers.py:265
↓ 2 callersFunction_split_lance_uris
(value)
lmms_eval/tasks/countix/utils.py:27
↓ 2 callersFunction_split_question_and_options
(question_with_options: str)
lmms_eval/tasks/motionbench/utils.py:29
↓ 2 callersMethod_strip_thinking
Strip <think>...</think> content from model output if enable_thinking is set.
lmms_eval/models/simple/qwen3_vl.py:261
↓ 2 callersMethod_tensor_to_pil
(self, tensor: torch.Tensor)
lmms_eval/models/simple/penguinvl.py:167
↓ 2 callersFunction_to_decimal
(text: str)
lmms_eval/tasks/zerobench/utils.py:29
↓ 2 callersFunction_to_float
(text: str)
lmms_eval/tasks/unig2u/chartqa100/utils.py:46
↓ 2 callersFunction_to_float
(text: str)
lmms_eval/tasks/officeqa/utils.py:14
↓ 2 callersFunction_to_float
(text: str)
lmms_eval/tasks/chartqa/utils.py:46
↓ 2 callersFunction_to_float
(value)
lmms_eval/models/simple/cambrians_vsc.py:47
↓ 2 callersFunction_to_int
(value: Any)
lmms_eval/tasks/fsc147/utils.py:17
↓ 2 callersFunction_to_rgb
(image_obj: Any)
lmms_eval/tasks/dude/utils.py:14
↓ 2 callersFunction_to_rgb
(image_obj: Any)
lmms_eval/tasks/omnidocbench/utils.py:45
← previousnext →601–700 of 7,449, ranked by callers