.gitignore
.pre-commit-config.yaml
LICENSE
README.md
pyproject.toml
setup.py
.github/issue_template.md
.github/pull_request_template.md
.github/workflows/black.yml
docs/README.md
docs/commands.md
docs/current_tasks.md
docs/model_guide.md
docs/task_guide.md
lmms_eval/__init__.py
lmms_eval/__main__.py
lmms_eval/evaluator.py
lmms_eval/logging_utils.py
lmms_eval/utils.py
lmms_eval.egg-info/PKG-INFO
lmms_eval.egg-info/SOURCES.txt
lmms_eval.egg-info/dependency_links.txt
lmms_eval.egg-info/entry_points.txt
lmms_eval.egg-info/requires.txt
lmms_eval.egg-info/top_level.txt
lmms_eval/api/__init__.py
lmms_eval/api/filter.py
lmms_eval/api/instance.py
lmms_eval/api/metrics.py
lmms_eval/api/model.py
lmms_eval/api/registry.py
lmms_eval/api/samplers.py
lmms_eval/api/task.py
lmms_eval/filters/__init__.py
lmms_eval/filters/decontamination.py
lmms_eval/filters/extraction.py
lmms_eval/filters/selection.py
lmms_eval/filters/transformation.py
lmms_eval/models/__init__.py
lmms_eval/models/batch_gpt4.py
lmms_eval/models/claude.py
lmms_eval/models/from_log.py
lmms_eval/models/fuyu.py
lmms_eval/models/gemini_api.py
lmms_eval/models/gpt4v.py
lmms_eval/models/idefics2.py
lmms_eval/models/instructblip.py
lmms_eval/models/internvl.py
lmms_eval/models/llama_vid.py
lmms_eval/models/llava.py
lmms_eval/models/llava_hf.py
lmms_eval/models/llava_sglang.py
lmms_eval/models/llava_vid.py
lmms_eval/models/minicpm_v.py
lmms_eval/models/mplug_owl_video.py
lmms_eval/models/phi3v.py
lmms_eval/models/qwen_vl.py
lmms_eval/models/qwen_vl_api.py
lmms_eval/models/reka.py
lmms_eval/models/video_chatgpt.py
lmms_eval/models/video_llava.py
lmms_eval/models/xcomposer2_4KHD.py
lmms_eval/models/xcomposer2_4khd.py
lmms_eval/models/model_utils/__init__.py
lmms_eval/models/model_utils/load_video.py
lmms_eval/models/model_utils/qwen/qwen_generate_utils.py
lmms_eval/models/mplug_owl_video/__init__.py
lmms_eval/models/mplug_owl_video/configuration_mplug_owl.py
lmms_eval/models/mplug_owl_video/modeling_mplug_owl.py
lmms_eval/models/mplug_owl_video/processing_mplug_owl.py
lmms_eval/models/mplug_owl_video/tokenization_mplug_owl.py
lmms_eval/models/video_chatgpt/__init__.py
lmms_eval/models/video_chatgpt/constants.py
lmms_eval/models/video_chatgpt/inference.py
lmms_eval/models/video_chatgpt/single_video_inference.py
lmms_eval/models/video_chatgpt/utils.py
lmms_eval/models/video_chatgpt/video_conversation.py
lmms_eval/models/video_chatgpt/eval/__init__.py
lmms_eval/models/video_chatgpt/eval/model_utils.py
lmms_eval/models/video_chatgpt/model/__init__.py
lmms_eval/models/video_chatgpt/model/consolidate.py
lmms_eval/models/video_chatgpt/model/make_delta.py
lmms_eval/models/video_chatgpt/model/utils.py
lmms_eval/models/video_chatgpt/model/video_chatgpt.py
lmms_eval/tasks/__init__.py
lmms_eval/tasks/_task_utils/file_utils.py
lmms_eval/tasks/_task_utils/gpt_eval_utils.py
lmms_eval/tasks/_task_utils/video_loader.py
lmms_eval/tasks/_task_utils/vqa_eval_metric.py
lmms_eval/tasks/activitynetqa/_default_template_yaml
lmms_eval/tasks/activitynetqa/activitynetqa_generation.yaml
lmms_eval/tasks/activitynetqa/utils.py
lmms_eval/tasks/ai2d/ai2d.yaml
lmms_eval/tasks/ai2d/upload_ai2d.py
lmms_eval/tasks/ai2d/utils.py
lmms_eval/tasks/chartqa/chartqa.yaml
lmms_eval/tasks/chartqa/upload_chartqa.py
lmms_eval/tasks/chartqa/utils.py
lmms_eval/tasks/cmmmu/_cmmmu.yaml
lmms_eval/tasks/cmmmu/_default_template_cmmmu_yaml
lmms_eval/tasks/cmmmu/cmmmu_test.yaml
lmms_eval/tasks/cmmmu/cmmmu_val.yaml
lmms_eval/tasks/cmmmu/utils.py
lmms_eval/tasks/coco_cap/coco2014_cap.yaml
lmms_eval/tasks/coco_cap/coco2014_cap_test.yaml
lmms_eval/tasks/coco_cap/coco2014_cap_val.yaml
lmms_eval/tasks/coco_cap/coco2017_cap.yaml
lmms_eval/tasks/coco_cap/coco2017_cap_test.yaml
lmms_eval/tasks/coco_cap/coco2017_cap_val.yaml
lmms_eval/tasks/coco_cap/coco_cap.yaml
lmms_eval/tasks/coco_cap/utils.py
lmms_eval/tasks/conbench/conbench.yaml
lmms_eval/tasks/conbench/utils.py
lmms_eval/tasks/cvrr/_cvrr.yaml
lmms_eval/tasks/cvrr/_default_template_yaml
lmms_eval/tasks/cvrr/cvrr_fine_grained_action_understanding.yaml
lmms_eval/tasks/cvrr/cvrr_interpretation_of_social_context.yaml
lmms_eval/tasks/cvrr/cvrr_interpretation_of_visual_context.yaml
lmms_eval/tasks/cvrr/cvrr_multiple_actions_in_a_single_video.yaml
lmms_eval/tasks/cvrr/cvrr_non_existent_actions_with_existent_scene_depictions.yaml
lmms_eval/tasks/cvrr/cvrr_non_existent_actions_with_non_existent_scene_depictions.yaml
lmms_eval/tasks/cvrr/cvrr_object_instance_count.yaml
lmms_eval/tasks/cvrr/cvrr_partial_actions.yaml
lmms_eval/tasks/cvrr/cvrr_time_order_understanding.yaml
lmms_eval/tasks/cvrr/cvrr_understanding_emotional_context.yaml
lmms_eval/tasks/cvrr/cvrr_unusual_and_physically_anomalous_activities.yaml
lmms_eval/tasks/cvrr/utils.py
lmms_eval/tasks/docvqa/_default_template_docvqa_yaml
lmms_eval/tasks/docvqa/docvqa.yaml
lmms_eval/tasks/docvqa/docvqa_test.yaml
lmms_eval/tasks/docvqa/docvqa_val.yaml
lmms_eval/tasks/docvqa/utils.py
lmms_eval/tasks/egoschema/README.md
lmms_eval/tasks/egoschema/_default_template_yaml
lmms_eval/tasks/egoschema/egoschema.yaml
lmms_eval/tasks/egoschema/egoschema_mcppl.yaml
lmms_eval/tasks/egoschema/egoschema_subset.yaml
lmms_eval/tasks/egoschema/egoschema_subset_mcppl.yaml
lmms_eval/tasks/egoschema/utils.py
lmms_eval/tasks/ferret/ferret.yaml
lmms_eval/tasks/ferret/rule.json
lmms_eval/tasks/ferret/utils.py
lmms_eval/tasks/flickr30k/flickr30k.yaml
lmms_eval/tasks/flickr30k/flickr30k_test.yaml
lmms_eval/tasks/flickr30k/utils.py
lmms_eval/tasks/gqa/gqa.yaml
lmms_eval/tasks/gqa/utils.py
lmms_eval/tasks/hallusion_bench/evaluate_hb.py
lmms_eval/tasks/hallusion_bench/hallusion_bench_image.yaml
lmms_eval/tasks/hallusion_bench/utils.py
lmms_eval/tasks/iconqa/_default_template_docvqa_yaml
lmms_eval/tasks/iconqa/iconqa.yaml
lmms_eval/tasks/iconqa/iconqa_test.yaml
lmms_eval/tasks/iconqa/iconqa_val.yaml
lmms_eval/tasks/iconqa/utils.py
lmms_eval/tasks/infovqa/_default_template_infovqa_yaml
lmms_eval/tasks/infovqa/infovqa.yaml
lmms_eval/tasks/infovqa/infovqa_test.yaml
lmms_eval/tasks/infovqa/infovqa_val.yaml
lmms_eval/tasks/infovqa/utils.py
lmms_eval/tasks/internal_eval/_default_template_internal_eval_yaml
lmms_eval/tasks/internal_eval/d170_cn.yaml
lmms_eval/tasks/internal_eval/d170_cn_utils.py
lmms_eval/tasks/internal_eval/d170_en.yaml
lmms_eval/tasks/internal_eval/d170_en_utils.py
lmms_eval/tasks/internal_eval/dc100_en.yaml
lmms_eval/tasks/internal_eval/dc100_en_utils.py
lmms_eval/tasks/internal_eval/dc200_cn.yaml
lmms_eval/tasks/internal_eval/dc200_cn_utils.py
lmms_eval/tasks/internal_eval/internal_eval.yaml
lmms_eval/tasks/internal_eval/utils.py
lmms_eval/tasks/llava-bench-coco/llava-bench-coco.yaml
lmms_eval/tasks/llava-bench-coco/rule.json
lmms_eval/tasks/llava-bench-coco/utils.py
lmms_eval/tasks/llava-in-the-wild/llava-in-the-wild.yaml
lmms_eval/tasks/llava-in-the-wild/rule.json
lmms_eval/tasks/llava-in-the-wild/utils.py
lmms_eval/tasks/llava_wilder/_default_template_wilder_yaml
lmms_eval/tasks/llava_wilder/llava_wilder_full.yaml
lmms_eval/tasks/llava_wilder/llava_wilder_medium.yaml
lmms_eval/tasks/llava_wilder/llava_wilder_small.yaml
lmms_eval/tasks/llava_wilder/utils.py
lmms_eval/tasks/mathverse/mathverse.yaml
lmms_eval/tasks/mathverse/mathverse_evals.py
lmms_eval/tasks/mathverse/mathverse_testmini.yaml
lmms_eval/tasks/mathverse/mathverse_testmini_text_dominant.yaml
lmms_eval/tasks/mathverse/mathverse_testmini_text_lite.yaml
lmms_eval/tasks/mathverse/mathverse_testmini_text_only.yaml
lmms_eval/tasks/mathverse/mathverse_testmini_vision_dominant.yaml
lmms_eval/tasks/mathverse/mathverse_testmini_vision_intensive.yaml
lmms_eval/tasks/mathverse/mathverse_testmini_vision_only.yaml
lmms_eval/tasks/mathverse/utils.py
lmms_eval/tasks/mathvista/mathvista.yaml
lmms_eval/tasks/mathvista/mathvista_evals.py
lmms_eval/tasks/mathvista/mathvista_test.yaml
lmms_eval/tasks/mathvista/mathvista_testmini.yaml
lmms_eval/tasks/mathvista/utils.py
lmms_eval/tasks/mmbench/_default_template_mmbench_cn_yaml
lmms_eval/tasks/mmbench/_default_template_mmbench_en_yaml
lmms_eval/tasks/mmbench/cc_utils.py
lmms_eval/tasks/mmbench/cn_utils.py
lmms_eval/tasks/mmbench/en_utils.py
lmms_eval/tasks/mmbench/mmbench.yaml
lmms_eval/tasks/mmbench/mmbench_cc.yaml
lmms_eval/tasks/mmbench/mmbench_cn.yaml
lmms_eval/tasks/mmbench/mmbench_cn_dev.yaml
lmms_eval/tasks/mmbench/mmbench_cn_test.yaml
lmms_eval/tasks/mmbench/mmbench_en.yaml
lmms_eval/tasks/mmbench/mmbench_en_dev.yaml
lmms_eval/tasks/mmbench/mmbench_en_test.yaml
lmms_eval/tasks/mmbench/mmbench_evals.py
lmms_eval/tasks/mme/mme.yaml
lmms_eval/tasks/mme/utils.py
lmms_eval/tasks/mmmu/arial.ttf
lmms_eval/tasks/mmmu/mmmu.yaml
lmms_eval/tasks/mmmu/mmmu_group_img.yaml
lmms_eval/tasks/mmmu/mmmu_group_img_test.yaml
lmms_eval/tasks/mmmu/mmmu_group_img_val.yaml
lmms_eval/tasks/mmmu/mmmu_test.yaml
lmms_eval/tasks/mmmu/mmmu_val.yaml
lmms_eval/tasks/mmmu/utils.py
lmms_eval/tasks/mmmu/utils_group_img.py
lmms_eval/tasks/mmupd/_default_template_mmupd_yaml
lmms_eval/tasks/mmupd/mmaad_base.yaml
lmms_eval/tasks/mmupd/mmaad_instruction.yaml
lmms_eval/tasks/mmupd/mmaad_option.yaml
lmms_eval/tasks/mmupd/mmiasd_base.yaml
lmms_eval/tasks/mmupd/mmiasd_instruction.yaml
lmms_eval/tasks/mmupd/mmiasd_option.yaml
lmms_eval/tasks/mmupd/mmivqd_base.yaml
lmms_eval/tasks/mmupd/mmivqd_instruction.yaml
lmms_eval/tasks/mmupd/mmivqd_option.yaml
lmms_eval/tasks/mmupd/mmupd.yaml
lmms_eval/tasks/mmupd/mmupd_base.yaml
lmms_eval/tasks/mmupd/mmupd_evals.py
lmms_eval/tasks/mmupd/mmupd_instruction.yaml
lmms_eval/tasks/mmupd/mmupd_option.yaml
lmms_eval/tasks/mmupd/utils.py
lmms_eval/tasks/mmvet/mmvet.yaml
lmms_eval/tasks/mmvet/utils.py
lmms_eval/tasks/multidocvqa/multidocvqa.yaml
lmms_eval/tasks/multidocvqa/multidocvqa_test.yaml
lmms_eval/tasks/multidocvqa/multidocvqa_val.yaml
lmms_eval/tasks/multidocvqa/utils.py
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/README.md
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/_default_template.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/arabic_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/bengali_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/chinese_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/french_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/hindi_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/japanese_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/rule.json
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/russian_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/spanish_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/urdu_llava_in_the_wild.yaml
lmms_eval/tasks/multilingual-llava-bench-in-the-wild/utils.py
lmms_eval/tasks/nextqa/_default_template_yaml
lmms_eval/tasks/nextqa/nextqa.yaml
lmms_eval/tasks/nextqa/nextqa_mc_test.yaml
lmms_eval/tasks/nextqa/nextqa_oe_test.yaml
lmms_eval/tasks/nextqa/nextqa_oe_val.yaml
lmms_eval/tasks/nextqa/stopwords.csv
lmms_eval/tasks/nextqa/utils.py
lmms_eval/tasks/nocaps/_default_template_nocaps_yaml
lmms_eval/tasks/nocaps/nocaps.yaml
lmms_eval/tasks/nocaps/nocaps_test.yaml
lmms_eval/tasks/nocaps/nocaps_val.yaml
lmms_eval/tasks/nocaps/utils.py
lmms_eval/tasks/ocrbench/ocrbench.yaml
lmms_eval/tasks/ocrbench/upload_ocrbench.py
lmms_eval/tasks/ocrbench/utils.py
lmms_eval/tasks/ok_vqa/_default_template_vqa_yaml
lmms_eval/tasks/ok_vqa/_generate_config.py
lmms_eval/tasks/ok_vqa/_ok_vqa.yaml
lmms_eval/tasks/ok_vqa/ok_vqa_val2014.yaml
lmms_eval/tasks/ok_vqa/utils.py
lmms_eval/tasks/olympiadbench/cn_utils.py
lmms_eval/tasks/olympiadbench/en_utils.py
lmms_eval/tasks/olympiadbench/olympiadbench.yaml
lmms_eval/tasks/olympiadbench/olympiadbench_evals.py
lmms_eval/tasks/olympiadbench/olympiadbench_test_cn.yaml
lmms_eval/tasks/olympiadbench/olympiadbench_test_en.yaml
lmms_eval/tasks/perceptiontest/test/_default_template_yaml
lmms_eval/tasks/perceptiontest/test/perceptiontest_mc.yaml
lmms_eval/tasks/perceptiontest/test/perceptiontest_mcppl.yaml
lmms_eval/tasks/perceptiontest/test/utils.py
lmms_eval/tasks/perceptiontest/val/_default_template_yaml
lmms_eval/tasks/perceptiontest/val/perceptiontest_mc.yaml
lmms_eval/tasks/perceptiontest/val/perceptiontest_mcppl.yaml
lmms_eval/tasks/perceptiontest/val/utils.py
lmms_eval/tasks/pope/pope.yaml
lmms_eval/tasks/pope/pope_adv.yaml
lmms_eval/tasks/pope/pope_full.yaml
lmms_eval/tasks/pope/pope_pop.yaml
lmms_eval/tasks/pope/pope_random.yaml
lmms_eval/tasks/pope/utils.py
lmms_eval/tasks/realworldqa/realworldqa.yaml
lmms_eval/tasks/realworldqa/utils.py
lmms_eval/tasks/refcoco/_default_template_bbox_yaml
lmms_eval/tasks/refcoco/_default_template_seg_yaml
lmms_eval/tasks/refcoco/_generate_config.py
lmms_eval/tasks/refcoco/_refcoco.yaml
lmms_eval/tasks/refcoco/refcoco_bbox_test.yaml
lmms_eval/tasks/refcoco/refcoco_bbox_testA.yaml
lmms_eval/tasks/refcoco/refcoco_bbox_testB.yaml
lmms_eval/tasks/refcoco/refcoco_bbox_val.yaml
lmms_eval/tasks/refcoco/refcoco_seg_test.yaml
lmms_eval/tasks/refcoco/refcoco_seg_testA.yaml
lmms_eval/tasks/refcoco/refcoco_seg_testB.yaml
lmms_eval/tasks/refcoco/refcoco_seg_val.yaml
lmms_eval/tasks/refcoco/utils.py
lmms_eval/tasks/refcoco+/_default_template_bbox_yaml
lmms_eval/tasks/refcoco+/_default_template_seg_yaml
lmms_eval/tasks/refcoco+/_generate_config.py
lmms_eval/tasks/refcoco+/_refcoco.yaml
lmms_eval/tasks/refcoco+/refcoco+_bbox_testA.yaml
lmms_eval/tasks/refcoco+/refcoco+_bbox_testB.yaml
lmms_eval/tasks/refcoco+/refcoco+_bbox_val.yaml
lmms_eval/tasks/refcoco+/refcoco+_seg_testA.yaml
lmms_eval/tasks/refcoco+/refcoco+_seg_testB.yaml
lmms_eval/tasks/refcoco+/refcoco+_seg_val.yaml
lmms_eval/tasks/refcoco+/utils.py
lmms_eval/tasks/refcocog/_default_template_bbox_yaml
lmms_eval/tasks/refcocog/_default_template_seg_yaml
lmms_eval/tasks/refcocog/_generate_config.py
lmms_eval/tasks/refcocog/_refcoco.yaml
lmms_eval/tasks/refcocog/refcocog_bbox_test.yaml
lmms_eval/tasks/refcocog/refcocog_bbox_val.yaml
lmms_eval/tasks/refcocog/refcocog_seg_test.yaml
lmms_eval/tasks/refcocog/refcocog_seg_val.yaml
lmms_eval/tasks/refcocog/utils.py
lmms_eval/tasks/scienceqa/scienceqa.yaml
lmms_eval/tasks/scienceqa/scienceqa_full.yaml
lmms_eval/tasks/scienceqa/scienceqa_img.yaml
lmms_eval/tasks/scienceqa/utils.py
lmms_eval/tasks/screenspot/README.md
lmms_eval/tasks/screenspot/_default_template_rec_yaml
lmms_eval/tasks/screenspot/_default_template_reg_yaml
lmms_eval/tasks/screenspot/_screenspot.yaml
lmms_eval/tasks/screenspot/screenspot_rec_test.yaml
lmms_eval/tasks/screenspot/screenspot_reg_test.yaml
lmms_eval/tasks/screenspot/utils.py
lmms_eval/tasks/screenspot/utils_rec.py
lmms_eval/tasks/seedbench/seedbench.yaml
lmms_eval/tasks/seedbench/seedbench_ppl.yaml
lmms_eval/tasks/seedbench/utils.py
lmms_eval/tasks/seedbench_2/seedbench_2.yaml
lmms_eval/tasks/seedbench_2/utils.py
lmms_eval/tasks/stvqa/stvqa.yaml
lmms_eval/tasks/stvqa/utils.py
lmms_eval/tasks/synthdog/donut_evaluator.py
lmms_eval/tasks/synthdog/synthdog.yaml
lmms_eval/tasks/synthdog/synthdog_en.yaml
lmms_eval/tasks/synthdog/synthdog_zh.yaml
lmms_eval/tasks/synthdog/utils.py
lmms_eval/tasks/tempcompass/_default_template_yaml
lmms_eval/tasks/tempcompass/_tempcompass.yaml
lmms_eval/tasks/tempcompass/tempcompass_caption_matching.yaml
lmms_eval/tasks/tempcompass/tempcompass_captioning.yaml
lmms_eval/tasks/tempcompass/tempcompass_mc.yaml
lmms_eval/tasks/tempcompass/tempcompass_yes_no.yaml
lmms_eval/tasks/tempcompass/utils.py
lmms_eval/tasks/textcaps/_default_template_textcaps_yaml
lmms_eval/tasks/textcaps/textcaps.yaml
lmms_eval/tasks/textcaps/textcaps_test.yaml
lmms_eval/tasks/textcaps/textcaps_train.yaml
lmms_eval/tasks/textcaps/textcaps_val.yaml
lmms_eval/tasks/textcaps/utils.py
lmms_eval/tasks/textvqa/_default_template_textvqa_yaml
lmms_eval/tasks/textvqa/_textvqa.yaml
lmms_eval/tasks/textvqa/textvqa_test.yaml
lmms_eval/tasks/textvqa/textvqa_val.yaml
lmms_eval/tasks/textvqa/utils.py
lmms_eval/tasks/vatex/_vatex.yaml
lmms_eval/tasks/vatex/utils.py
lmms_eval/tasks/vatex/vatex_test.yaml
lmms_eval/tasks/vatex/vatex_val_zh.yaml
lmms_eval/tasks/vcr_wiki/_default_template_vcr_yaml
lmms_eval/tasks/vcr_wiki/utils.py
lmms_eval/tasks/vcr_wiki/vcr_wiki_en_easy.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_en_easy_100.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_en_easy_500.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_en_hard.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_en_hard_100.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_en_hard_500.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_zh_easy.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_zh_easy_100.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_zh_easy_500.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_zh_hard.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_zh_hard_100.yaml
lmms_eval/tasks/vcr_wiki/vcr_wiki_zh_hard_500.yaml
lmms_eval/tasks/video_detail_description/README.md
lmms_eval/tasks/video_detail_description/_default_template_yaml
lmms_eval/tasks/video_detail_description/utils.py
lmms_eval/tasks/video_detail_description/video_detail_description.yaml
lmms_eval/tasks/videochatgpt/_default_template_yaml
lmms_eval/tasks/videochatgpt/_videochatgpt.yaml
lmms_eval/tasks/videochatgpt/utils.py
lmms_eval/tasks/videochatgpt/videochatgpt_consistency.yaml
lmms_eval/tasks/videochatgpt/videochatgpt_generic.yaml
lmms_eval/tasks/videochatgpt/videochatgpt_temporal.yaml
lmms_eval/tasks/videomme/utils.py
lmms_eval/tasks/videomme/videomme.yaml
lmms_eval/tasks/vizwiz_vqa/_default_template_vqa_yaml
lmms_eval/tasks/vizwiz_vqa/_generate_config.py
lmms_eval/tasks/vizwiz_vqa/_vizwiz_vqa.yaml
lmms_eval/tasks/vizwiz_vqa/utils.py
lmms_eval/tasks/vizwiz_vqa/vizwiz_vqa_test.yaml
lmms_eval/tasks/vizwiz_vqa/vizwiz_vqa_val.yaml
lmms_eval/tasks/vqav2/_default_template_vqav2_yaml
lmms_eval/tasks/vqav2/_vqav2.yaml
lmms_eval/tasks/vqav2/utils.py
lmms_eval/tasks/vqav2/vqav2_test.yaml
lmms_eval/tasks/vqav2/vqav2_val.yaml
lmms_eval/tasks/websrc/README.md
lmms_eval/tasks/websrc/utils.py
lmms_eval/tasks/websrc/websrc.yaml
lmms_eval/tasks/websrc/websrc_test.yaml
lmms_eval/tasks/websrc/websrc_val.yaml
lmms_eval/tasks/worldqa/_default_template_yaml
lmms_eval/tasks/worldqa/utils.py
lmms_eval/tasks/worldqa/worldqa.yaml
lmms_eval/tasks/worldqa/worldqa_generation.yaml
lmms_eval/tasks/worldqa/worldqa_mc.yaml
lmms_eval/tasks/worldqa/worldqa_mc_evaluator.py
lmms_eval/tasks/worldqa/worldqa_mcppl.yaml
lmms_eval/tasks/youcook2/_default_template_yaml
lmms_eval/tasks/youcook2/utils.py
lmms_eval/tasks/youcook2/youcook2_val.yaml
miscs/example_eval.yaml
miscs/llava_repr_requirements.txt
miscs/llava_result_check.md
miscs/llava_sglang_result_check.md
miscs/repr_scripts.sh
miscs/repr_torch_envs.txt
miscs/scienceqa_id.txt
miscs/script.sh
miscs/test_llava.py
miscs/test_scienceqa.py
tools/get_video_avg_time.py
tools/make_hf_dataset.ipynb
tools/makecvrr.ipynb