Functions — github.com/VITA-MLLM/VITA

CodeHub MCPcopy Create free account

hub / github.com/VITA-MLLM/VITA / functions

Functions1,650 in github.com/VITA-MLLM/VITA

⨍ Functions 1,650◇ Types & classes 320↳ Endpoints 1

(self, keywords, tokenizer, input_ids)

vita/util/mm_utils.py:122

(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)

vita/util/data_utils_video_audio_patch_sf.py:688

(self, *args, skip_times=0, **kwargs)

VLMEvalKit/vlmeval/utils/mp_util.py:37

(self, dataset='Video-MME', use_subtitle=False)

VLMEvalKit/vlmeval/dataset/videomme.py:50

(self, dataset='MMBench-Video', pack=False)

VLMEvalKit/vlmeval/dataset/video_base.py:9

(self, dataset='MMBench', skip_noimg=True)

VLMEvalKit/vlmeval/dataset/image_base.py:32

(self, dataset='MVBench_MP4', pack=False)

VLMEvalKit/vlmeval/dataset/mvbench.py:389

(self, dataset='MMBench', **kwargs)

VLMEvalKit/vlmeval/dataset/text_base.py:10

(self, dataset, **kwargs)

VLMEvalKit/vlmeval/dataset/slidevqa.py:82

(self, dataset)

VLMEvalKit/vlmeval/dataset/__init__.py:37

(self, dataset='VCR_EN_EASY_500', skip_noimg=True)

VLMEvalKit/vlmeval/dataset/vcr.py:246

(self, dataset='MMBench-Video', pack=False)

VLMEvalKit/vlmeval/dataset/mmbench_video.py:62

(self, dataset, **kwargs)

VLMEvalKit/vlmeval/dataset/mmlongbench.py:446

(self, ref, gt)

VLMEvalKit/vlmeval/dataset/image_caption.py:6

(self, dataset, **kwargs)

VLMEvalKit/vlmeval/dataset/dude.py:63

(self, content)

VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:262

(self, amount, original_string=None)

VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:285

Create a new DateValue. Placeholders are marked as -1.

VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:340

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:51

(self, size, groups=1)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:78

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:107

(self, is_flow=False)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:118

(self, mean, std)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:135

(self, size, interpolation=Image.BILINEAR)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:159

(self, crop_size, scale_size=None, flip=True)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:167

(self, crop_size, scale_size=None, flip=True)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:208

(self, input_size, scales=None, max_distort=1, fix_crop=True, more_fix_crop=True)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:256

(self, size, interpolation=Image.BILINEAR)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:349

(self, model_type)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:392

(self, roll=False)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:407

(self, div=True)

VLMEvalKit/vlmeval/dataset/utils/mvbench.py:428

(self, model_path='DataCanvas/MMAlaya', **kwargs)

VLMEvalKit/vlmeval/vlm/mmalaya.py:21

( self, model_path='DataCanvas/MMAlaya2', load_in_8bit=False, **kwargs, )

VLMEvalKit/vlmeval/vlm/mmalaya.py:204

(self, model_path='nyu-visionx/cambrian-8b', **kwargs)

VLMEvalKit/vlmeval/vlm/cambrian.py:18

(self, model_path='facebook/chameleon-7b', **kwargs)

VLMEvalKit/vlmeval/vlm/chameleon.py:14

(self, model_path='01-ai/Yi-VL-6B', root=None, **kwargs)

VLMEvalKit/vlmeval/vlm/yi_vl.py:58

(self, name, mpt_pth=None, ckpt_pth=None,

VLMEvalKit/vlmeval/vlm/open_flamingo.py:16

(self, name, root=None, **kwargs)

VLMEvalKit/vlmeval/vlm/pandagpt.py:13

(self, root=None, revision='main', **kwargs)

VLMEvalKit/vlmeval/vlm/transcore_m.py:61

(self, model_path='OpenGVLab/InternVL-Chat-V1-5', load_in_8bit=False, version='V1.0', **kwargs)

VLMEvalKit/vlmeval/vlm/internvl_chat.py:134

(self, model_path, root, **kwargs)

VLMEvalKit/vlmeval/vlm/omnilmm.py:98

(self, model_path='AIDC-AI/Parrot-7B', **kwargs)

VLMEvalKit/vlmeval/vlm/parrot.py:15

(self, model_path='qihoo360/360VL-70B', **kwargs)

VLMEvalKit/vlmeval/vlm/qh_360vl.py:16

(self, model_path='openbmb/MiniCPM-V', **kwargs)

VLMEvalKit/vlmeval/vlm/minicpm_v.py:18

(self, model_path='openbmb/MiniCPM-Llama3-V-2_5', **kwargs)

VLMEvalKit/vlmeval/vlm/minicpm_v.py:96

(self, model_path='openbmb/MiniCPM-V', **kwargs)

VLMEvalKit/vlmeval/vlm/minicpm_v.py:261

(self, model_path='omlab/omchat-v2.0-13B-single-beta_hf', **kwargs)

VLMEvalKit/vlmeval/vlm/omchat.py:16

(self, model_name='XVERSE-V-13B', root=None, **kwargs)

VLMEvalKit/vlmeval/vlm/vxverse.py:42

VLMEvalKit/vlmeval/vlm/instructblip.py:14

VLMEvalKit/vlmeval/vlm/base.py:11

(self, model_path='microsoft/Phi-3-vision-128k-instruct', **kwargs)

VLMEvalKit/vlmeval/vlm/phi3_vision.py:13

(self, model_path='microsoft/Phi-3.5-vision-instruct', **kwargs)

VLMEvalKit/vlmeval/vlm/phi3_vision.py:109

(self, model_path, root=None, conv_mode='qwen', **kwargs)

VLMEvalKit/vlmeval/vlm/rbdash.py:20

(self, model_path='AIDC-AI/Ovis1.5-Llama3-8B', **kwargs)

VLMEvalKit/vlmeval/vlm/ovis.py:13

(self, model_path='THUDM/visualglm-6b', **kwargs)

VLMEvalKit/vlmeval/vlm/visualglm.py:11

(self, model_path='Zero-Vision/Llama-3-MixSenseV1_1', **kwargs)

VLMEvalKit/vlmeval/vlm/mixsense.py:16

(self, model_path=None, **kwargs)

VLMEvalKit/vlmeval/vlm/mplug_owl3.py:15

(self, model_path='Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5', **kwargs)

VLMEvalKit/vlmeval/vlm/xgen_mm.py:13

( self, model_path: str, min_pixels: int, max_pixels: int, **kwargs,

VLMEvalKit/vlmeval/vlm/qwen2_vl.py:13

(self, model_path='feipengma/WeMM', **kwargs)

VLMEvalKit/vlmeval/vlm/wemm.py:11

(self, model_path='TIGER-Lab/Mantis-8B-siglip-llama3', **kwargs)

VLMEvalKit/vlmeval/vlm/mantis.py:21

(self, model_path='THUDM/glm-4v-9b', **kwargs)

VLMEvalKit/vlmeval/vlm/cogvlm.py:14

(self, model_path='THUDM/cogvlm2-llama3-chat-19B', tokenizer_name=None, **kwargs)

VLMEvalKit/vlmeval/vlm/cogvlm.py:52

(self, model_path='Efficient-Large-Model/Llama-3-VILA1.5-8b', **kwargs)

VLMEvalKit/vlmeval/vlm/vila.py:16

(self, model_path='Qwen/Qwen-VL', **kwargs)

VLMEvalKit/vlmeval/vlm/qwen_vl.py:15

(self, model_path='Qwen/Qwen-VL-Chat', **kwargs)

VLMEvalKit/vlmeval/vlm/qwen_vl.py:81

(self, model_path, root=None, conv_mode='llava_v1', **kwargs)

VLMEvalKit/vlmeval/vlm/mgm.py:18

(self, model_path='BAAI/Emu2-Chat', **kwargs)

VLMEvalKit/vlmeval/vlm/emu.py:14

(self, mode='v2', root='/mnt/petrelfs/share_data/duanhaodong/MiniGPT-4/',

VLMEvalKit/vlmeval/vlm/minigpt4.py:14

(self, model_path='echo840/Monkey', **kwargs)

VLMEvalKit/vlmeval/vlm/monkey.py:13

(self, model_path='echo840/Monkey-Chat', **kwargs)

VLMEvalKit/vlmeval/vlm/monkey.py:91

(self, model_path='google/paligemma-3b-mix-448', **kwargs)

VLMEvalKit/vlmeval/vlm/paligemma.py:12

(self, model_path='HuggingFaceM4/idefics-9b-instruct', **kwargs)

VLMEvalKit/vlmeval/vlm/idefics.py:15

(self, model_path='HuggingFaceM4/idefics2-8b', **kwargs)

VLMEvalKit/vlmeval/vlm/idefics.py:64

(self, model_path='deepseek-ai/deepseek-vl-1.3b-chat', **kwargs)

VLMEvalKit/vlmeval/vlm/deepseek_vl.py:21

(self, model_path='BAAI/Bunny-v1_1-Llama-3-8B-V', **kwargs)

VLMEvalKit/vlmeval/vlm/bunnyllama3.py:17

(self, model_path='MAGAer13/mplug-owl2-llama2-7b', **kwargs)

VLMEvalKit/vlmeval/vlm/mplug_owl2.py:14

(self, model_path='VITA/vita', **kwargs)

VLMEvalKit/vlmeval/vlm/vita/vita_qwen2.py:20

(self, model_path='VITA/vita', **kwargs)

VLMEvalKit/vlmeval/vlm/vita/vita_mistral.py:20

(self, model_path='VITA/vita', **kwargs)

VLMEvalKit/vlmeval/vlm/vita/vita.py:20

(self, stops=[], encounters=1)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer.py:11

(self, model_path='internlm/internlm-xcomposer2-4khd-7b', **kwargs)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:105

(self, model_path='Lin-Chen/ShareCaptioner', **kwargs)

VLMEvalKit/vlmeval/vlm/xcomposer/sharecaptioner.py:13

(self, model_path='internlm/internlm-xcomposer2-vl-7b', **kwargs)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:85

(self, model_path='internlm/internlm-xcomposer2d5-7b', id_scale=1.5, beam=3, **kwargs)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:117

(self, model_path='Chat-UniVi/Chat-UniVi', **kwargs)

VLMEvalKit/vlmeval/vlm/video_llm/chat_uni_vi.py:90

(self, model_path='YanweiLi/llama-vid-7b-full-224-video-fps-1', **kwargs)

VLMEvalKit/vlmeval/vlm/video_llm/llama_vid.py:35

(self, model_path='LanguageBind/Video-LLaVA-7B-hf', **kwargs)

VLMEvalKit/vlmeval/vlm/video_llm/video_llava.py:30

(self, model_path='LanguageBind/Video-LLaVA-7B', **kwargs)

VLMEvalKit/vlmeval/vlm/video_llm/video_llava.py:85

(self, model_path='MBZUAI/Video-ChatGPT-7B', dir_root=None, **kwargs)

VLMEvalKit/vlmeval/vlm/video_llm/video_chatgpt.py:18

(self, model_path='ermu2001/pllava-13b', dir_root=None, **kwargs)

VLMEvalKit/vlmeval/vlm/video_llm/pllava.py:20

(self, stops=[], encounters=1)

VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:48

(self, model_path='liuhaotian/llava_v1.5_7b', **kwargs)

VLMEvalKit/vlmeval/vlm/llava/llava.py:17

(self, model_path='llava-hf/llava-v1.6-vicuna-7b-hf', **kwargs)

VLMEvalKit/vlmeval/vlm/llava/llava.py:180

(self, model_path='lmms-lab/llama3-llava-next-8b', **kwargs)

VLMEvalKit/vlmeval/vlm/llava/llava.py:326

(self, model_path='lmms-lab/llava-onevision-qwen2-7b-si', **kwargs)

VLMEvalKit/vlmeval/vlm/llava/llava.py:393

(self, llava_path, llm_path=None, visual_encoder_path='open

VLMEvalKit/vlmeval/vlm/llava/llava_xtuner.py:25

(self, model: str = 'claude-3-opus-20240229', key: str = None,

VLMEvalKit/vlmeval/api/claude.py:19

(self, model: str = 'gemini-1.0-pro', retry: int = 5, wait:

VLMEvalKit/vlmeval/api/gemini.py:11

Base Class for all APIs. Args: retry (int, optional): The retry times for `generate_inner`. Defaults to 10. wait (int

VLMEvalKit/vlmeval/api/base.py:15

← previous next →901–1,000 of 1,650, ranked by callers