MCPcopy Create free account

hub / github.com/huggingface/smollm / functions

Functions1,907 in github.com/huggingface/smollm

⨍ Functions 1,907◇ Types & classes 810↳ Endpoints 7
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/03_02_dedup_laion.py:48
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/04_04_remove_opt_out_images_laion.py:51
Method__call__
(self)
vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/merge_on_image_individual_dataset.py:73
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_01_nsfw_image_filtering.py:78
Method__call__
(self, batch)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_01_nsfw_image_filtering.py:102
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_03_nsfw_image_removal.py:50
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/08_02_urldedup.py:51
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_04_remove_opt_out_images.py:50
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/12_02_remove_opt_out_images.py:50
Method__call__
(self, web_document)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/06_03_remove_image_duplicates.py:65
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_06_line_dedup.py:47
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_03_remove_opt_out_documents.py:50
Method__call__
(self, example)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/11_03_set_img_urls_dedup.py:54
Method__call__
(self)
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/02_01_generate_html_codes_prompt_1.py:70
Method__call__
(self)
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/02_02_generate_html_codes_prompt_2.py:67
Method__call__
(self)
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/04_screenshot_html_codes.py:45
Method__call__
(self, html_str: str)
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/03_filtering_html_codes.py:18
Method__call__
(self, html_str: str)
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/03_filtering_html_codes.py:62
Method__call__
Process input for Idefics3. If `allow_mismatch=True`, we skip the error when #<image> tokens != #images. See `Idefics3Proces
vision/smolvlm2/smolvlm/model/processing_smollmm.py:31
Method__call__
(self, examples: List[Dict[str, torch.Tensor]])
vision/smolvlm2/smolvlm/datasets/builder.py:259
Method__call__
(self, image, scale_up_factor=None)
vision/m4/training/utils.py:273
Method__call__
(self, bytes_)
vision/m4/training/dataset_utils.py:72
Method__call__
( self, html_str, type_return, )
vision/m4/sourcing/data_collection/processors/dom_tree_simplificator.py:52
Method__call__
(self, web_document)
vision/m4/sourcing/data_collection/processors/web_document_filtering.py:641
Method__call__
(self, web_document)
vision/m4/sourcing/data_collection/processors/web_document_filtering.py:979
Method__call__
(self, pair)
vision/m4/sourcing/data_collection/processors/laion_pair_filtering.py:49
Method__call__
(self, html_str, page_url)
vision/m4/sourcing/data_collection/processors/pair_extractor.py:27
Method__call__
(self, example)
vision/m4/sourcing/data_collection/processors/warc_downloader.py:14
Method__call__
(self, media_info)
vision/m4/sourcing/data_collection/processors/pair_filtering.py:63
Method__call__
(self, example)
vision/m4/sourcing/data_collection/processors/html_extractor.py:14
Method__call__
(self, selectolax_tree, page_url)
vision/m4/sourcing/data_collection/processors/pre_extraction_simplificator.py:93
Method__enter__
(self)
vision/m4/testing_utils.py:424
Method__enter__
(self)
vision/m4/testing_utils.py:513
Method__enter__
(self)
vision/m4/utils/progress.py:66
Method__enter__
(self)
vision/m4/sourcing/pmd/helpers.py:259
Method__exit__
(self, *exc)
vision/m4/testing_utils.py:437
Method__exit__
(self, *exc)
vision/m4/testing_utils.py:517
Method__exit__
(self, *args)
vision/m4/utils/progress.py:69
Method__exit__
(self, exc_type, exc_val, exc_tb)
vision/m4/sourcing/pmd/helpers.py:262
Method__getitem__
(self, i)
vision/smolvlm2/smolvlm/datasets/dataset.py:504
Method__getitem__
We ignore 'idx' because each call to __getitem__ gets the “next” packed sample, from self.packed_cursor onward.
vision/smolvlm2/smolvlm/datasets/builder.py:94
Method__getitem__
(self, i)
vision/smolvlm2/smolvlm/datasets/dataset_clip_sampling.py:636
Method__getitem__
(self, idx)
vision/m4/training/dataset.py:601
Method__init__
(self, root)
tools/smol_tools/demo_tkinter.py:18
Method__init__
(self)
tools/smol_tools/smol_tools/summarizer.py:14
Method__init__
(self, model_repo: str, model_filename: str, system_prompt: str, prefix_text: str = "", n_ctx: int = 8192)
tools/smol_tools/smol_tools/base.py:9
Method__init__
(self)
tools/smol_tools/smol_tools/chatter.py:31
Method__init__
(self)
tools/smol_tools/smol_tools/agent.py:64
Method__init__
(self)
tools/smol_tools/smol_tools/rewriter.py:5
Method__init__
(self)
tools/smol_tools/smol_tools/titler.py:5
Method__init__
(self, max_frames: int = 50)
tools/smolvlm_local_inference/SmolVLM_video_inference.py:13
Method__init__
(self, path_opt_out_image_urls)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/02_02_remove_opt_out.py:46
Method__init__
(self, path_laion_coco_imageurls_to_captions)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/make_laion_coco_1_4_dataset.py:42
Method__init__
(self, path_laion_coco_imageurls_to_captions)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/make_laion_coco_1_4_dataset.py:63
Method__init__
(self, path_laion_coco_imageurls_to_captions)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/make_laion_coco.py:41
Method__init__
(self, path_laion_coco_imageurls_to_captions)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/make_laion_coco.py:62
Method__init__
(self, freeze_siglip=True)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/train_bin_classif.py:20
Method__init__
(self, freeze_siglip=True)
vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/05_binary_classification.py:15
Method__init__
(self, num_docs, dom_viz_template_path)
vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/explore/global_visualization.py:22
Method__init__
(self, path_set_dup_md5)
vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/03_02_dedup_laion.py:43
Method__init__
(self, path_opt_out_image_urls)
vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/04_04_remove_opt_out_images_laion.py:46
Method__init__
(self, name_ds: str)
vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/merge_on_image_individual_dataset.py:70
Method__init__
(self, path_image_urls_to_keep)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_01_nsfw_image_filtering.py:73
Method__init__
( self, path_nsfw_classifier, )
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_01_nsfw_image_filtering.py:93
Method__init__
(self, path_nsfw_image_urls)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_03_nsfw_image_removal.py:45
Method__init__
(self, path_dup_urls)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/08_02_urldedup.py:46
Method__init__
(self, path_opt_out_urls)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_04_remove_opt_out_images.py:45
Method__init__
(self, path_opt_out_image_urls)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/12_02_remove_opt_out_images.py:45
Method__init__
(self, path_image_urls_to_remove)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/06_03_remove_image_duplicates.py:60
Method__init__
(self, path_domain_to_duplicated_texts)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_06_line_dedup.py:42
Method__init__
(self, path_opt_out_urls)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_03_remove_opt_out_documents.py:45
Method__init__
(self, path_ban_url_warc_filename)
vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/11_03_set_img_urls_dedup.py:49
Method__init__
( self, path_ideas_websites, model_name, chat_template, batch_size,
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/02_01_generate_html_codes_prompt_1.py:48
Method__init__
( self, path_ideas_websites, model_name, chat_template, batch_size,
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/02_02_generate_html_codes_prompt_2.py:45
Method__init__
( self, num_json_ideas_and_html_codes: int, num_processes: int, size_chunk_mul
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/04_screenshot_html_codes.py:27
Method__init__
(self, list_ban_substrings: List[str], threshold_min_num_words: int)
vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/03_filtering_html_codes.py:57
Method__init__
(self, config)
vision/smolvlm2/smolvlm/model/modeling_smolvlm.py:285
Method__init__
(self, config)
vision/smolvlm2/smolvlm/model/modeling_smollmm.py:337
Method__init__
A dataset class that loads text/images/multi-image/videos, tokenizes them via `processor`, and optionally masks user/system text.
vision/smolvlm2/smolvlm/datasets/dataset.py:393
Method__init__
( self, datasets: List, data_args, model_max_length: int = 2048 )
vision/smolvlm2/smolvlm/datasets/builder.py:73
Method__init__
( self, pad_token_id: int, model_max_length: Optional[int] = None, image_size:
vision/smolvlm2/smolvlm/datasets/builder.py:246
Method__init__
A dataset class that loads text/images/multi-image/videos, tokenizes them via `processor`, and optionally masks user/system text.
vision/smolvlm2/smolvlm/datasets/dataset_clip_sampling.py:525
Method__init__
(self, replay=True)
vision/m4/testing_utils.py:472
Method__init__
(self, replay=True)
vision/m4/testing_utils.py:479
Method__init__
(self, logger)
vision/m4/testing_utils.py:507
Method__init__
(self, returncode, stdout, stderr)
vision/m4/testing_utils.py:1041
Method__init__
(self, description, total_steps, *args, **kwargs)
vision/m4/utils/progress.py:51
Method__init__
(self, *args, **kwargs)
vision/m4/utils/progress.py:62
Method__init__
( self, model, abort_after_batch_num=None, )
vision/m4/utils/activation_tracker.py:52
Method__init__
(self)
vision/m4/utils/training/timer.py:23
Method__init__
(self)
vision/m4/utils/training/timer.py:49
Method__init__
(self, scale, always_apply=False, p=0.5)
vision/m4/training/utils.py:114
Method__init__
(self, scale, always_apply=False, p=0.5)
vision/m4/training/utils.py:148
Method__init__
( self, max_image_size, min_image_size=378, scale_up_frequency=0.7, sc
vision/m4/training/utils.py:251
Method__init__
(self)
vision/m4/training/utils.py:981
Method__init__
(self, dataset, transform_rng)
vision/m4/training/dataset.py:576
Method__init__
( self, dataset, tokenizer, image_transform, batch_size, seed,
vision/m4/training/dataset.py:620
Method__init__
( self, dataset, tokenizer, image_transform, batch_size, seed,
vision/m4/training/dataset.py:867
Method__init__
( self, datasets, num_workers, rank, accumulate_datasets=False, proba_interleaving_dataset=None, is_tr
vision/m4/training/dataset.py:1149
Method__init__
(self, dataset, seed, **kwargs)
vision/m4/training/dataset.py:1314
← previousnext →1,001–1,100 of 1,907, ranked by callers