( self, tokenizer_type: str = "13a", lowercase: bool = False, punctuation_remo

(self, simplified, traditional)

(self, power, simplified, traditional, big_s, big_t)

(self, value, simplified, traditional, big_s, big_t, alt_s=None, alt_t=None)

(self, simplified, traditional, symbol, expression=None)

(self, positive, negative, point)

(self, cardinal=None, chntext=None)

(self, digit=None, chntext=None)

(self, telephone=None, raw_chntext=None, chntext=None)

(self, fraction=None, chntext=None)

(self, money=None, chntext=None)

(self, percentage=None, chntext=None)

(self, to_banjiao:bool = False, to_upper:bool = False, to_lower:bool = False,

(self)

(self)

(self, remove_diacritics: bool = False, split_letters: bool = False)

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

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

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

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

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

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

(self, dataset, **kwargs)

(self, dataset)

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

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

(self, dataset, **kwargs)

(self, ref, gt)

(self, dataset, **kwargs)

(self, content)

(self, amount, original_string=None)

(self, size)

(self, size, groups=1)

(self, size)

(self, is_flow=False)

(self, mean, std)

(self, size, interpolation=Image.BILINEAR)

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

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

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

(self, size, interpolation=Image.BILINEAR)

(self, model_type)

(self, roll=False)

(self, div=True)

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

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

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

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

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

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

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

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

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

(self, model_path, root, **kwargs)

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

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

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

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

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

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

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

(self, name)

(self)

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

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

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

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

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

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

(self, model_path=None, **kwargs)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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