path # lines of code tools/smol_tools/smol_tools/base.py 55 tools/smol_tools/smol_tools/summarizer.py 35 tools/smol_tools/smol_tools/agent.py 84 tools/smol_tools/smol_tools/titler.py 15 tools/smol_tools/smol_tools/chatter.py 110 tools/smol_tools/smol_tools/rewriter.py 16 tools/smol_tools/demo_tkinter.py 534 tools/smollm_local_inference/mlc.py 12 tools/smollm_local_inference/transformers-js.js 12 tools/smollm_local_inference/llama-cpp-python.py 13 tools/smollm_local_inference/mlx.py 9 tools/smolvlm_local_inference/SmolVLM_video_inference.py 109 text/data/smoltalk/rewrite/pipeline/pipeline.py 28 text/data/smoltalk/rewrite/pipeline/__init__.py 1 text/data/smoltalk/rewrite/pipeline/dataset.py 90 text/data/smoltalk/constraints/pipeline/json_schemas.py 192 text/data/smoltalk/constraints/pipeline/pipeline.py 244 text/data/smoltalk/constraints/pipeline/__init__.py 1 text/data/smoltalk/constraints/pipeline/system_prompts.py 6 text/data/smoltalk/constraints/pipeline/ifeval_tasks.py 54 text/data/smoltalk/constraints/filter_ifeval_data.py 312 text/data/smoltalk/summarization/pipelines/email_summaries.py 80 text/data/smoltalk/summarization/pipelines/cnn_daily_summaries.py 64 text/data/smoltalk/magpie_ultra_v1/pipeline.py 498 text/evaluation/math_utils.py 346 text/evaluation/tasks.py 316 text/pretraining/continual-pretraining/finemath/160B-runs/fwedu-finemath-infiwebmath-4plus.yaml 110 text/pretraining/continual-pretraining/finemath/160B-runs/fwedu-finemath-infiwebmath-3plus.yaml 110 text/pretraining/continual-pretraining/finemath/60B-runs/finemath-infiwebmath-4plus.yaml 105 text/pretraining/continual-pretraining/finemath/60B-runs/finemath-3plus.yaml 104 text/pretraining/continual-pretraining/finemath/60B-runs/infiwebmath-4plus.yaml 104 text/pretraining/continual-pretraining/finemath/60B-runs/openwebmath.yaml 104 text/pretraining/continual-pretraining/finemath/60B-runs/finemath-4plus.yaml 104 text/pretraining/continual-pretraining/finemath/60B-runs/finemath-infiwebmath-3plus.yaml 105 text/pretraining/continual-pretraining/finemath/60B-runs/infiwebmath-3plus.yaml 104 text/pretraining/continual-pretraining/finemath/60B-runs/infiwebmath.yaml 104 text/pretraining/continual-pretraining/finemath/finemath-tokenize.py 48 text/pretraining/smollm1/config_smollm1_1B.yaml 126 text/pretraining/smollm1/config_smollm1_135M.yaml 106 text/pretraining/smollm1/config_smollm1_360M.yaml 106 text/pretraining/smollm2/config_smollm2_360M.yaml 99 text/pretraining/smollm2/config_smollm2_135M.yaml 99 text/pretraining/smollm2/config_smollm2_1B.yaml 99 text/finetuning/train.py 113 vision/smolvlm2/scripts/mixture_checker.py 67 vision/smolvlm2/scripts/mixtures/onevision_less_mammoth_more_videos_balanced.yaml 1011 vision/smolvlm2/scripts/mixtures/onevision_less_mammoth.yaml 860 vision/smolvlm2/scripts/mixtures/onevision_no_mammoth_more_image_balanced.yaml 983 vision/smolvlm2/scripts/mixtures/onevision_less_mammoth_more_videos.yaml 1011 vision/smolvlm2/scripts/mixtures/llava_onevision_config_qual.yaml 1012 vision/smolvlm2/scripts/mixtures/llava_onevision_config.yaml 581 vision/smolvlm2/scripts/create_mixture.py 115 vision/smolvlm2/scripts/sort.py 95 vision/smolvlm2/pyproject.toml 43 vision/smolvlm2/smolvlm/model/__init__.py 1 vision/smolvlm2/smolvlm/model/modeling_smolvlm.py 169 vision/smolvlm2/smolvlm/model/modeling_smollmm.py 201 vision/smolvlm2/smolvlm/model/processing_smollmm.py 133 vision/smolvlm2/smolvlm/model/varlen_packing.py 90 vision/smolvlm2/smolvlm/__init__.py 1 vision/smolvlm2/smolvlm/mm_utils.py 206 vision/smolvlm2/smolvlm/datasets/__init__.py 1 vision/smolvlm2/smolvlm/datasets/dataset_clip_sampling.py 611 vision/smolvlm2/smolvlm/datasets/builder.py 316 vision/smolvlm2/smolvlm/datasets/dataset.py 530 vision/smolvlm2/smolvlm/constants.py 8 vision/smolvlm2/smolvlm/train/args.py 165 vision/smolvlm2/smolvlm/train/train_mem.py 3 vision/smolvlm2/smolvlm/train/__init__.py 1 vision/smolvlm2/smolvlm/train/train.py 252 vision/smolvlm2/smolvlm/train/smolvlm_trainer.py 85 vision/smolvlm2/smolvlm/utils.py 20 vision/smolvlm2/smolvlm/conversation.py 302 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/viz_tool.py 57 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/merge_on_image_individual_dataset.py 129 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/build_concat_ds_sft.py 483 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/build_ds_sft.py 3203 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/create_set_hashes_test_images.py 32 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/build_the_cauldron.py 81 vision/data/datasets_processing_scripts/build_concatenation_datasets_sft/tar_dataset_pattern_check.py 40 vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/04_screenshot_html_codes.py 127 vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/02_02_generate_html_codes_prompt_2.py 142 vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/02_01_generate_html_codes_prompt_1.py 139 vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/01_generate_ideas_websites.py 51 vision/data/datasets_processing_scripts/build_websight_v02/python_scripts/03_filtering_html_codes.py 62 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_aokvqa.py 106 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_llavar.py 29 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_table_datasets.py 780 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_raven.py 96 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_m3it.py 62 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_pgm.py 77 vision/data/datasets_processing_scripts/create_fine_tuning_datasets/create_spot_difference.py 74 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_nlvr2.py 60 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_math_vista_mcq.py 49 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_math_vista.py 60 vision/data/datasets_processing_scripts/create_evaluation_datasets/ScienceQA/scienceqa.py 101 vision/data/datasets_processing_scripts/create_evaluation_datasets/ScienceQA/scienceqa_old_setup.py 96 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_imagenet1k_5ksupportset_subsets.py 12 vision/data/datasets_processing_scripts/create_evaluation_datasets/SEED/make_seed.py 51 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_scienceqa_old_setup.py 51 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_clevr.py 45 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_renderedsst2.py 39 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_visdial.py 233 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_imagenet1k_1ksupportset_subsets.py 12 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_mmbench.py 30 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_mmmu_open_ended.py 59 vision/data/datasets_processing_scripts/create_evaluation_datasets/dedup_val_mmbench.py 63 vision/data/datasets_processing_scripts/create_evaluation_datasets/NLVR2/NLVR2.py 106 vision/data/datasets_processing_scripts/create_evaluation_datasets/MMBench/make_mmbench.py 42 vision/data/datasets_processing_scripts/create_evaluation_datasets/Flickr30k/flickr30k.py 72 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_vqav2.py 39 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_scienceqa.py 51 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_fairface.py 39 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_vizwiz.py 43 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_coco.py 39 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_nocaps.py 61 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_mmmu_mcq.py 67 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_textvqa.py 39 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_textcaps.py 48 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_AI2D/create_ai2d.py 32 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_AI2D/create_ai2d_7_abcd.py 40 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_AI2D/create_ai2d_4.py 41 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_AI2D/create_ai2d_5_abcd.py 43 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_AI2D/create_ai2d_2.py 35 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_AI2D/create_ai2d_6_abcd.py 44 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_flickr30k.py 48 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_mmstar.py 64 vision/data/datasets_processing_scripts/create_evaluation_datasets/SugarCrepe/make_sugarcrepe.py 42 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_hateful_memes.py 46 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_vqav2_subsets.py 12 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_okvqa.py 35 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_mmmu.py 90 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_imagenet1k.py 49 vision/data/datasets_processing_scripts/create_evaluation_datasets/create_math_vista_open_ended.py 48 vision/data/datasets_processing_scripts/upload_rendered_text_dataset/upload_tar_to_s3.py 51 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/explore/assets/DOM_tree_viz.html 172 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/explore/explore.py 63 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/explore/global_visualization.py 201 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/python_scripts/03_clean_v2.py 81 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/python_scripts/get_modelling_metadata_dataset.py 118 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/python_scripts/05_filter_cm4.py 64 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/python_scripts/04_get_banned_urls.py 60 vision/data/datasets_processing_scripts/clean_m4_prelimenary_experiments/python_scripts/02_add_html_back.py 79 vision/data/datasets_processing_scripts/build_ethic_dataset/bias_generation_eval_idefics2.py 118 vision/data/datasets_processing_scripts/build_ethic_dataset/bias_generation_eval_idefics.py 144 vision/data/datasets_processing_scripts/build_image_website_code/01_generate_ideas_website.py 48 vision/data/datasets_processing_scripts/build_image_website_code/02_generate_html_css_codes.py 44 vision/data/datasets_processing_scripts/build_image_website_code/03_extraction_html_css_codes.py 42 vision/data/datasets_processing_scripts/build_image_website_code/04_screenshot_rendered_websites.py 58 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/gqa.py 35 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/mmbench_no_mcq.py 65 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/qbench.py 76 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/seed_img.py 54 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/scienceqa.py 52 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/vsr.py 39 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/llava_wild.py 45 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/pope.py 50 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/mmbench.py 66 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/mm_vet.py 42 vision/data/datasets_processing_scripts/integrate_evaluation_benchmarks_chatbot/scienceqa_no_mcq.py 67 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/08_01_prepare_urldedup.py 64 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/02_extract_html_get_image_urls.py 144 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_04_remove_opt_out_images.py 76 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/01_download_warc.py 89 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/06_02_merge_sets_image_urls_in_webdocs.py 48 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/02_parallel_extract_html_get_image_urls.py 113 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_07_merge_web_docs_texts_only_and_rest.py 64 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/11_02_get_docs_to_remove_by_set_img_urls_dedup.py 75 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/10_final_cleaning.py 113 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_05_merge_domain_to_duplicated_texts_sharded.py 86 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/03_parallel_dl_images_create_dataset.py 31 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_06_line_dedup.py 91 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_04_get_domain_to_duplicated_texts.py 90 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/04_merge_web_docs_with_images.py 140 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/05_filtering_web_docs.py 225 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/03_dl_images_create_dataset.py 163 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/14_01_filter_perplexity_with_language_model.py 121 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/06_01_create_set_image_urls_in_webdocs.py 90 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/02_bis_extract_html_get_image_urls_new_rules.py 140 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/08_02_urldedup.py 82 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/11_01_create_set_img_urls.py 50 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_02_find_opt_out.py 84 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_02_get_domain_to_positions.py 62 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/11_03_set_img_urls_dedup.py 94 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/12_01_find_opt_out_images.py 79 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_02_nsfw_image_visualization.py 68 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_01_find_urls_obelics.py 39 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_01_nsfw_image_filtering.py 175 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/07_03_nsfw_image_removal.py 77 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_01_create_web_docs_texts_only.py 49 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/12_02_remove_opt_out_images.py 74 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/13_final_processing.py 276 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/06_03_remove_image_duplicates.py 123 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/09_03_split_domain_to_positions.py 34 vision/data/datasets_processing_scripts/build_webdocs_dataset/python_scripts/15_03_remove_opt_out_documents.py 67 vision/data/datasets_processing_scripts/enwiki/python_scripts/02bis_get_stats.py 43 vision/data/datasets_processing_scripts/enwiki/python_scripts/08_save_dataset.py 32 vision/data/datasets_processing_scripts/enwiki/python_scripts/04_get_list_of_remaining_images.py 42 vision/data/datasets_processing_scripts/enwiki/python_scripts/01_extract_text_and_urls_from_wikipedia_web_documents.py 83 vision/data/datasets_processing_scripts/enwiki/python_scripts/02_load_wit_images_in_ds.py 103 vision/data/datasets_processing_scripts/enwiki/python_scripts/07_get_images_in_ds.py 48 vision/data/datasets_processing_scripts/enwiki/python_scripts/04bis_get_list_of_remaining_images.py 61 vision/data/datasets_processing_scripts/enwiki/python_scripts/03_extract_intermediary_dataset.py 21 vision/data/datasets_processing_scripts/enwiki/python_scripts/06_create_image_dataset.py 20 vision/data/datasets_processing_scripts/enwiki/python_scripts/05_download_remaining_urls.py 25 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/04_remove_small_images.py 65 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/02_01_find_opt_out.py 82 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/make_laion_coco.py 85 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/05_binary_classification.py 149 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/03_remove_nsfw_images.py 64 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/make_laion_coco_1_4_dataset.py 86 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/train_bin_classif.py 431 vision/data/datasets_processing_scripts/build_laion_coco_dataset/python_scripts/02_02_remove_opt_out.py 79 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/03_02_dedup_laion.py 71 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/04_04_remove_opt_out_images_laion.py 76 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/03_01_prepare_dedup_laion.py 15 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/01_02_template_loading_script_laion.py 80 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/04_03_find_opt_out_images_laion.py 77 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/02_filter_laion.py 79 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/04_02_create_ds_laion_urls.py 23 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/01_01_download_prepare_laion.py 62 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/04_01_find_laion_urls.py 45 vision/data/datasets_processing_scripts/build_laion_dataset/python_scripts/merge_1_4_laion_big_shards.py 68 vision/data/datasets_processing_scripts/create_valid_ds/create_coco_valid.py 10 vision/data/datasets_processing_scripts/create_valid_ds/create_wiki_valid.py 17 vision/data/datasets_processing_scripts/create_valid_ds/create_cm4_valid.py 16 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/02_convert_cm4_per_shard_idx.py 39 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/12_convert_llavar_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/18_convert_sft_per_shard_idx.py 41 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/05_convert_scaled_laion_per_shard_idx.py 44 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/19_convert_websight_mix_per_shard_idx.py 41 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/06_convert_lrv_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/07_convert_llava_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/10_convert_m3it_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/17_convert_websight_v02_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/01_convert_coco_per_shard_idx.py 39 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/14_convert_tikz_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/11_convert_spot_difference_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/09_convert_ultrachat_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/03_convert_laoin_per_shard_idx.py 44 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/08_convert_svit_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/04_convert_cm4_per_shard_idx.py 44 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/13_convert_vqav2_task_finetuning_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/15_convert_docvqa_per_shard_idx.py 37 vision/data/datasets_processing_scripts/01_tar_datasets_with_jpeg/python_scripts/16_convert_image_website_code_per_shard_idx.py 37 vision/m4/training/types.py 20 vision/m4/training/__init__.py 1 vision/m4/training/packing.py 1099 vision/m4/training/trainer.py 1513 vision/m4/training/dataset_utils.py 391 vision/m4/training/main.py 294 vision/m4/training/debug_utils.py 19 vision/m4/training/config.py 381 vision/m4/training/setup_language_model.py 26 vision/m4/training/utils.py 715 vision/m4/training/dataset.py 1086 vision/m4/training/setup_vision_model.py 22 vision/m4/utils/debug.py 9 vision/m4/utils/training/__init__.py 1 vision/m4/utils/training/timer.py 47 vision/m4/utils/__init__.py 1 vision/m4/utils/progress.py 59 vision/m4/utils/datasets/__init__.py 1 vision/m4/utils/datasets/create_webdataset_tar.py 316 vision/m4/utils/datasets/get_self_contained_ds.py 88 vision/m4/utils/logging.py 115 vision/m4/utils/check_valid_tokenizer.py 10 vision/m4/utils/activation_tracker.py 126 vision/m4/models/__init__.py 21 vision/m4/models/idefics/modeling_idefics.py 909 vision/m4/models/idefics/evaluation_captioning_in_context_idefics.py 191 vision/m4/models/idefics/configuration_idefics.py 148 vision/m4/models/idefics/evaluation_classification_in_context_idefics.py 3015 vision/m4/models/idefics/evaluation_perplexity_in_context_idefics.py 108 vision/m4/models/idefics/make_tiny_llama.py 30 vision/m4/models/idefics/evaluation_classification_vqa_in_context_idefics.py 23 vision/m4/models/idefics/evaluation_open_ended_vqa_in_context_idefics.py 221 vision/m4/models/idefics/evaluation_image_caption_matching_idefics.py 69 vision/m4/models/idefics/make_tiny_model.py 70 vision/m4/models/perceiver/perceiver.py 397 vision/m4/models/vgpt2/configuration_vgpt2.py 144 vision/m4/models/vgpt2/evaluation_open_ended_vqa_in_context_vgpt2.py 525 vision/m4/models/vgpt2/evaluation_image_caption_matching_vgpt2.py 237 vision/m4/models/vgpt2/__init__.py 1 vision/m4/models/vgpt2/evaluation_perplexity_in_context_vgpt2.py 313 vision/m4/models/vgpt2/modeling_vgpt2.py 970 vision/m4/models/vgpt2/evaluation_classification_in_context_vgpt2.py 2291 vision/m4/models/vgpt2/evaluation_classification_vqa_in_context_vgpt2.py 139 vision/m4/models/vgpt2/evaluation_captioning_in_context_vgpt2.py 456 vision/m4/models/custom_modules.py 192 vision/m4/models/zero_checkpoint_to_hf.py 98 vision/m4/models/vllama3/modeling_vllama3.py 1197 vision/m4/models/vllama3/configuration_vllama3.py 188 vision/m4/models/vllama3/__init__.py 1 vision/m4/models/vllama3/evaluation_classification_in_context_vllama3.py 3272 vision/m4/models/vllama3/evaluation_captioning_in_context_vllama3.py 193 vision/m4/models/vllama3/evaluation_open_ended_vqa_in_context_vllama3.py 580 vision/m4/models/vllama3/make_tiny_llama3.py 31 vision/m4/models/vllama3/make_tiny_model.py 81 vision/m4/models/vmistral/evaluation_captioning_in_context_vmistral.py 192 vision/m4/models/vmistral/evaluation_open_ended_vqa_in_context_vmistral.py 558 vision/m4/models/vmistral/evaluation_image_caption_matching_vmistral.py 69 vision/m4/models/vmistral/evaluation_classification_vqa_in_context_vmistral.py 23 vision/m4/models/vmistral/__init__.py 1 vision/m4/models/vmistral/make_tiny_mistral.py 31 vision/m4/models/vmistral/evaluation_perplexity_in_context_vmistral.py 109 vision/m4/models/vmistral/evaluation_classification_in_context_vmistral.py 3158 vision/m4/models/vmistral/modeling_vmistral.py 1088 vision/m4/models/vmistral/make_tiny_model.py 77 vision/m4/models/vmistral/configuration_vmistral.py 184 vision/m4/models/common.py 105 vision/m4/scripts/behead_unused_params.py 57 vision/m4/scripts/convert_vmistral_old_siglip_to_new_siglip.py 56 vision/m4/scripts/convert_vmistral_lm_head.py 34 vision/m4/scripts/s3_checkpoint_download_convert_upload.py 136 vision/m4/scripts/schedule-evals.py 56 vision/m4/scripts/update_siglip_model_pos_embeds.py 57 vision/m4/scripts/update_model_perceiver_latents.py 42 vision/m4/scripts/merge_lora_and_save.py 43 vision/m4/scripts/convert_zero_state_dict_for_new_siglip.py 39 vision/m4/scripts/convert-checkpoints.py 86 vision/m4/scripts/s3-upload-checkpoints.py 119 vision/m4/scripts/update_vision_model_position_embeds.py 61 vision/m4/scripts/clean_jsonl_evals.py 40 vision/m4/scripts/resize_embed_for_eou.py 55 vision/m4/scripts/update_model_embeds.py 53 vision/m4/scripts/cleanup-checkpoints.py 85 vision/m4/__init__.py 1 vision/m4/evaluation/generation/config.py 66 vision/m4/evaluation/generation/generate.py 195 vision/m4/evaluation/generation/deprecated_generation/log_generation.py 68 vision/m4/evaluation/generation/deprecated_generation/launch_generation.py 54 vision/m4/evaluation/generation/deprecated_generation/generate.py 83 vision/m4/evaluation/scripts/visualize_generations.py 134 vision/m4/evaluation/scripts/sync_evaluations_on_wandb.py 192 vision/m4/evaluation/scripts/mmbench_submission_format.py 77 vision/m4/evaluation/scripts/mmmu_submission_format.py 44 vision/m4/evaluation/scripts/copy_remote_sample_datasets.py 30 vision/m4/evaluation/scripts/create_sample_evaluation_datasets_simplified.py 102 vision/m4/evaluation/scripts/create_sample_evaluation_datasets.py 82 vision/m4/evaluation/__init__.py 1 vision/m4/evaluation/custom_metrics/unfolded_image_captioning_metrics.py 159 vision/m4/evaluation/custom_metrics/perplexity_metrics.py 47 vision/m4/evaluation/custom_metrics/doc_vqa_metrics.py 100 vision/m4/evaluation/custom_metrics/open_ended_vqa_metrics.py 296 vision/m4/evaluation/custom_metrics/__init__.py 7 vision/m4/evaluation/custom_metrics/classification_vqa_metrics.py 89 vision/m4/evaluation/custom_metrics/image_caption_matching_metrics.py 87 vision/m4/evaluation/custom_metrics/unfolded_classification_metrics.py 186 vision/m4/evaluation/custom_metrics/utils.py 443 vision/m4/evaluation/vqa_labels.py 2 vision/m4/evaluation/tasks/base.py 37 vision/m4/evaluation/tasks/__init__.py 651 vision/m4/evaluation/config.py 118 vision/m4/evaluation/utils.py 66 vision/m4/evaluation/launch.py 130 vision/m4/evaluation/evaluators/__init__.py 2 vision/m4/evaluation/evaluators/linear_prober.py 62 vision/m4/evaluation/evaluators/in_contexter.py 233 vision/m4/sourcing/processing/__init__.py 1 vision/m4/sourcing/processing/app.py 81 vision/m4/sourcing/processing/extracting_ngrams/__init__.py 1 vision/m4/sourcing/processing/extracting_ngrams/utils.py 61 vision/m4/sourcing/processing/extracting_ngrams/extract_documents_ngrams.py 44 vision/m4/sourcing/__init__.py 1 vision/m4/sourcing/data_collection/callers/get_reference_clip_distrib.py 75 vision/m4/sourcing/data_collection/callers/__init__.py 1 vision/m4/sourcing/data_collection/callers/extract_web_documents.py 176 vision/m4/sourcing/data_collection/callers/extract_html.py 53 vision/m4/sourcing/data_collection/callers/filter_web_documents.py 196 vision/m4/sourcing/data_collection/callers/extract_image_text_pairs.py 213 vision/m4/sourcing/data_collection/callers/filter_laion_pairs.py 86 vision/m4/sourcing/data_collection/callers/deduplicate_images_web_documents.py 115 vision/m4/sourcing/data_collection/callers/download_warc.py 63 vision/m4/sourcing/data_collection/callers/line_deduplicate_web_documents.py 65 vision/m4/sourcing/data_collection/configs/config_filter_text_image_pairs.yaml 26 vision/m4/sourcing/data_collection/configs/config_filter_laion_pairs.yaml 16 vision/m4/sourcing/data_collection/configs/config_extract_web_documents.yaml 23 vision/m4/sourcing/data_collection/configs/config_filter_web_documents.yaml 64 vision/m4/sourcing/data_collection/utils/tags_attributes.py 112 vision/m4/sourcing/data_collection/utils/fetching_utils.py 53 vision/m4/sourcing/data_collection/utils/__init__.py 28 vision/m4/sourcing/data_collection/utils/clip_utils.py 43 vision/m4/sourcing/data_collection/utils/simplification_utils.py 176 vision/m4/sourcing/data_collection/utils/kl_utils.py 7 vision/m4/sourcing/data_collection/utils/utils.py 16 vision/m4/sourcing/data_collection/utils/filtering_utils.py 427 vision/m4/sourcing/data_collection/__init__.py 1 vision/m4/sourcing/data_collection/processors/warc_downloader.py 36 vision/m4/sourcing/data_collection/processors/web_document_image_deduplication.py 202 vision/m4/sourcing/data_collection/processors/__init__.py 15 vision/m4/sourcing/data_collection/processors/pair_extractor.py 97 vision/m4/sourcing/data_collection/processors/pre_extraction_simplificator.py 159 vision/m4/sourcing/data_collection/processors/laion_pair_filtering.py 118 vision/m4/sourcing/data_collection/processors/dom_tree_simplificator.py 245 vision/m4/sourcing/data_collection/processors/html_extractor.py 52 vision/m4/sourcing/data_collection/processors/image_deduplicator.py 37 vision/m4/sourcing/data_collection/processors/web_document_extractor.py 374 vision/m4/sourcing/data_collection/processors/web_document_line_deduplication.py 121 vision/m4/sourcing/data_collection/processors/pair_filtering.py 307 vision/m4/sourcing/data_collection/processors/web_document_filtering.py 1002 vision/m4/sourcing/data_collection/visualization/web_document_visualization.py 59 vision/m4/sourcing/data_collection/visualization/web_document_and_filtering_visualization.py 675 vision/m4/sourcing/data_collection/visualization/__init__.py 1 vision/m4/sourcing/data_collection/visualization/pair_visualization.py 566 vision/m4/sourcing/data_collection/visualization/pair_stat_dashboard.py 359 vision/m4/sourcing/data_collection/visualization/get_stats_vis_choose_filtering_parameters_laion_pairs.py 101 vision/m4/sourcing/data_collection/visualization/assets/DOM_tree_viz.html 172 vision/m4/sourcing/data_collection/visualization/wikipedia/explore.py 58 vision/m4/sourcing/data_collection/visualization/wikipedia/global_visualization.py 322 vision/m4/sourcing/data_collection/visualization/wikipedia/explore_wiki_results.py 41 vision/m4/sourcing/data_collection/visualization/global_visualization.py 321 vision/m4/sourcing/data_collection/visualization/choose_filtering_parameters_laion_pairs.py 25 vision/m4/sourcing/data_collection/visualization/choose_filtering_parameters_web_documents_node_level.py 205 vision/m4/sourcing/data_collection/visualization/plot_clip_distrib.py 49 vision/m4/sourcing/data_collection/debug/get_intuition.py 249 vision/m4/sourcing/data_collection/debug/debug.py 23 vision/m4/sourcing/data_collection/debug/__init__.py 1 vision/m4/sourcing/get_modelling_metadata_dataset/get_modelling_metadata_dataset.py 118 vision/m4/sourcing/pmd/jz_loaders/__init__.py 1 vision/m4/sourcing/pmd/jz_loaders/jz_wit/__init__.py 1 vision/m4/sourcing/pmd/jz_loaders/jz_wit/jz_wit.py 186 vision/m4/sourcing/pmd/jz_loaders/jz_conceptual_captions/jz_conceptual_captions.py 151 vision/m4/sourcing/pmd/jz_loaders/jz_conceptual_captions/__init__.py 1 vision/m4/sourcing/pmd/fix_image_path.py 17 vision/m4/sourcing/pmd/scripts/jz_pmd.py 33 vision/m4/sourcing/pmd/scripts/pmd.py 142 vision/m4/sourcing/pmd/scripts/check_none_ims.py 43 vision/m4/sourcing/pmd/__init__.py 21 vision/m4/sourcing/pmd/loader_builder.py 276 vision/m4/sourcing/pmd/cache_path.py 248 vision/m4/sourcing/pmd/local_loaders/localized_narratives__coco/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/localized_narratives__coco/localized_narratives__coco.py 74 vision/m4/sourcing/pmd/local_loaders/coco/coco.py 105 vision/m4/sourcing/pmd/local_loaders/coco/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/localized_narratives__ADE20k/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/localized_narratives__ADE20k/localized_narratives__ADE20k.py 60 vision/m4/sourcing/pmd/local_loaders/laion_2b_en/laion_2b_en.py 78 vision/m4/sourcing/pmd/local_loaders/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/yfcc100m/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/yfcc100m/yfcc100m.py 44 vision/m4/sourcing/pmd/local_loaders/localized_narratives__flickr30k/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/localized_narratives__flickr30k/localized_narratives__flickr30k.py 80 vision/m4/sourcing/pmd/local_loaders/localized_narratives__openimages/__init__.py 1 vision/m4/sourcing/pmd/local_loaders/localized_narratives__openimages/localized_narratives__openimages.py 70 vision/m4/sourcing/pmd/helpers.py 190 vision/m4/testing_utils.py 504 vision/experiments/evaluation/vloom/common/accelerate_config.yaml 12 vision/experiments/pretraining/vloom/tr_346_vsmollm2_256M_3rd_stage/config.yaml 133 vision/experiments/pretraining/vloom/tr_346_vsmollm2_256M_3rd_stage/resize_embed_for_eou.py 47 vision/experiments/pretraining/vloom/tr_341_smolvlm_025b_1st_stage/config.yaml 136 vision/experiments/pretraining/vloom/tr_341_smolvlm_025b_1st_stage/resize_embed_for_eou.py 55 vision/experiments/pretraining/vloom/tr_349_vsmollm2_500M_3rd_stage/config.yaml 133 vision/experiments/pretraining/vloom/tr_349_vsmollm2_500M_3rd_stage/resize_embed_for_eou.py 47 vision/experiments/pretraining/vloom/tr_343_smolvlm_05b_1st_stage/config.yaml 136 vision/experiments/pretraining/vloom/tr_343_smolvlm_05b_1st_stage/resize_embed_for_eou.py 55 vision/experiments/pretraining/vloom/tr_348_smolvlm_2B/config.yaml 137 vision/experiments/pretraining/vloom/tr_348_smolvlm_2B/resize_embed_for_eou.py 55 vision/experiments/pretraining/vloom/tr_cron_template/config.yaml 94 vision/experiments/pretraining/vloom/tr_350_smolvlm_2B_2nd_stage/config.yaml 150 vision/experiments/pretraining/vloom/tr_350_smolvlm_2B_2nd_stage/resize_embed_for_eou.py 47 vision/experiments/pretraining/vloom/tr_345_vsmollm2_256M_2nd_stage/config.yaml 150 vision/experiments/pretraining/vloom/tr_345_vsmollm2_256M_2nd_stage/resize_embed_for_eou.py 47 vision/experiments/pretraining/vloom/tr_347_smolvlm_500M_2nd_stage/config.yaml 150 vision/experiments/pretraining/vloom/tr_347_smolvlm_500M_2nd_stage/resize_embed_for_eou.py 47 vision/experiments/pretraining/vloom/slurm_scripts_templates/accelerate_config_multi_node.yaml 15 vision/experiments/pretraining/vloom/slurm_scripts_templates/with_launcher/config.yaml 47 vision/experiments/pretraining/vloom/slurm_scripts_templates/with_launcher/accelerate_config.yaml 20 vision/experiments/pretraining/vloom/slurm_scripts_templates/accelerate_config_single_node.yaml 15 vision/experiments/pretraining/vloom/slurm_scripts_templates/hfc_with_launcher/config.yaml 94 vision/finetuning/Smol_VLM_FT.ipynb 646 vision/finetuning/SmolVLM2_Video_FT.ipynb 2909