MCPcopy Create free account

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

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

↓ 190 callersMethodget
Retrieve a specified number of elements from the buffer in a thread-safe manner. Parameters: - length (int): The num
web_demo/vita_html/web/queue.py:40
↓ 137 callersMethodsize
Get the current size of the queue in a thread-safe manner. Parameters: - None Returns: - in
web_demo/vita_html/web/queue.py:153
↓ 136 callersFunctionlistinstr
(lst, s)
VLMEvalKit/vlmeval/smp/misc.py:108
↓ 122 callersFunctiontokenizer_image_audio_token
( prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, audio_token_index=AUDIO_TOKEN_INDEX,
vita/util/mm_utils.py:73
↓ 120 callersMethodfrom_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
web_demo/vllm_tools/vllm_file/whale.py:134
↓ 112 callersFunctionload
(f, fmt=None)
VLMEvalKit/vlmeval/smp/file.py:148
↓ 97 callersFunctiontokenizer_image_token
( prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None )
vita/util/mm_utils.py:45
↓ 95 callersFunctionDATASET_TYPE
(dataset)
VLMEvalKit/vlmeval/dataset/__init__.py:137
↓ 88 callersMethodpreprocess
(self, images, return_tensors)
vita/model/multimodal_encoder/eva_clip/eva_clip_processors.py:53
↓ 84 callersMethodappend_message
(self, role, message)
vita/conversation.py:174
↓ 76 callersFunctiondump
(data, f, **kwargs)
VLMEvalKit/vlmeval/smp/file.py:122
↓ 62 callersMethodcopy
(self)
vita/conversation.py:253
↓ 53 callersMethodget_prompt
(self, modality=None)
vita/conversation.py:32
↓ 42 callersMethodprocess
(self, wav_path)
vita/model/multimodal_encoder/whale/init_model.py:35
↓ 38 callersMethodgenerate
Generate the output message. Args: message (list[dict]): The input message. dataset (str, optional): The name of the
VLMEvalKit/vlmeval/vlm/base.py:100
↓ 37 callersFunctioncn_string
(s)
VLMEvalKit/vlmeval/smp/misc.py:118
↓ 33 callersMethodfrom_pretrained
( cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs )
vita/model/multimodal_encoder/internvit/configuration_intern_vit.py:107
↓ 29 callersMethoddump_image
(self, line, dataset)
VLMEvalKit/vlmeval/vlm/base.py:42
↓ 26 callersMethodmessage_to_promptimg
(self, message, dataset=None)
VLMEvalKit/vlmeval/vlm/omchat.py:96
↓ 22 callersMethodwrite
(self, buf)
vita/util/utils.py:82
↓ 20 callersMethodgenerate
(self, message, dataset=None)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:148
↓ 20 callersFunctionget_logger
(name, log_file=None, log_level=logging.INFO, file_mode='w')
VLMEvalKit/vlmeval/smp/log.py:6
↓ 19 callersFunctionload_pretrained_model
( model_path, model_base, model_name, model_type, load_8bit=False, load_4bit=False,
vita/model/builder.py:14
↓ 18 callersMethodget_vision_tower
(self)
vita/model/vita_arch.py:28
↓ 17 callersFunctionget_model_name_from_path
(model_path)
vita/util/mm_utils.py:112
↓ 17 callersFunctiontoliststr
(s)
VLMEvalKit/vlmeval/smp/misc.py:196
↓ 16 callersMethodget_model
(self)
vita/model/vita_arch.py:137
↓ 15 callersMethodgenerate
(self, message, dataset=None)
VLMEvalKit/vlmeval/api/reka.py:59
↓ 15 callersFunctionmd5
(s)
VLMEvalKit/vlmeval/smp/file.py:261
↓ 15 callersFunctionread_ok
(img_path)
VLMEvalKit/vlmeval/smp/vlm.py:128
↓ 14 callersFunctionLMUDataRoot
()
VLMEvalKit/vlmeval/smp/file.py:68
↓ 14 callersFunctionbuild_judge
(**kwargs)
VLMEvalKit/vlmeval/dataset/utils/judge_util.py:8
↓ 14 callersFunctiondecode_base64_to_image_file
(base64_string, image_path, target_size=-1)
VLMEvalKit/vlmeval/smp/vlm.py:111
↓ 13 callersFunctionget_rank_and_world_size
()
VLMEvalKit/vlmeval/smp/misc.py:100
↓ 13 callersFunctiontrack_progress_rich
Track the progress of parallel task execution with a progress bar. The built-in :mod:`multiprocessing` module is used for process pools and tasks
VLMEvalKit/vlmeval/utils/mp_util.py:54
↓ 12 callersMethodchat
The main function for multi-turn chatting. Will call `chat_inner` with the preprocessed input messages.
VLMEvalKit/vlmeval/vlm/base.py:117
↓ 12 callersMethoddevice
(self)
vita/model/multimodal_encoder/clip/clip_encoder.py:62
↓ 12 callersFunctionget_padding
(kernel_size, dilation=1)
vita/model/vita_tts/decoder/ticodec/models.py:14
↓ 11 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
vita/util/data_utils_video_audio_neg_patch.py:1499
↓ 11 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
vita/util/data_utils_video_patch_audio.py:1407
↓ 11 callersFunctionget_cache_path
(repo_id, branch=None)
VLMEvalKit/vlmeval/smp/misc.py:74
↓ 10 callersMethod__init__
(self, h)
vita/model/vita_tts/decoder/ticodec/models.py:430
↓ 10 callersMethod__init__
( self, in_features, hidden_features=None, out_features=None, act_laye
vita/model/multimodal_encoder/eva_clip/eva_vit.py:196
↓ 10 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
vita/util/data_utils_video_audio_patch.py:1357
↓ 10 callersMethodencode
(self, x)
vita/model/vita_tts/decoder/ticodec/vqvae.py:44
↓ 10 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_audio.py:252
↓ 10 callersMethodworking
If the API model is working, return True, else return False. Returns: bool: If the API model is working, return True, else return
VLMEvalKit/vlmeval/api/base.py:59
↓ 9 callersMethod__init__
(self, config: WhaleConfig, quant_config=None)
web_demo/vllm_tools/vllm_file/whale.py:438
↓ 9 callersMethodbuild_prompt
(self, line, dataset=None)
VLMEvalKit/vlmeval/vlm/ovis.py:49
↓ 9 callersFunctionencode_image_to_base64
(img, target_size=-1)
VLMEvalKit/vlmeval/smp/vlm.py:82
↓ 9 callersMethodget_audio_encoder
(self)
vita/model/vita_arch.py:34
↓ 9 callersMethodmessage_to_promptvideo
(self, message)
VLMEvalKit/vlmeval/vlm/base.py:154
↓ 8 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
vita/util/data_utils_video_audio_neg_patch_fo.py:1508
↓ 8 callersFunctiondynamic_preprocess
( image, min_num=1, max_num=6, image_size=448, use_thumbnail=False, img_mean=0 )
vita/util/data_utils_video_audio_neg_frameCat.py:1236
↓ 8 callersFunctiondynamic_preprocess
(image, min_num=1, max_num=6, image_size=448, use_thumbnail=False)
vita/util/data_utils_video_audio_patch_sf.py:1375
↓ 8 callersFunctionfind_closest_aspect_ratio
(aspect_ratio, target_ratios, width, height, image_size)
vita/util/data_utils_video_audio_neg_patch.py:1482
↓ 8 callersFunctionload_image
(image_file, input_size=448, max_num=6, upscale=False)
VLMEvalKit/vlmeval/vlm/mmalaya.py:147
↓ 8 callersMethodload_model
(self)
vita/model/multimodal_encoder/clip/clip_encoder.py:20
↓ 7 callersFunctionLOCALIZE
(fname, new_fname=None)
VLMEvalKit/vlmeval/tools.py:273
↓ 7 callersMethod__init__
( self, hidden_size: int, intermediate_size: int, hidden_act: str, qua
web_demo/vllm_tools/vllm_file/qwen2.py:404
↓ 7 callersMethodchat
The main function for multi-turn chatting. Will call `chat_inner` with the preprocessed input messages.
VLMEvalKit/vlmeval/api/base.py:153
↓ 7 callersMethodcheck_content
Check the content type of the input. Four types are allowed: str, dict, liststr, listdict.
VLMEvalKit/vlmeval/vlm/base.py:49
↓ 7 callersMethodcheck_content
Check the content type of the input. Four types are allowed: str, dict, liststr, listdict. Args: msgs: Raw input messages.
VLMEvalKit/vlmeval/api/base.py:83
↓ 7 callersMethodclear
Clear the buffer in a thread-safe manner. Parameters: - None Returns: - None
web_demo/vita_html/web/queue.py:57
↓ 7 callersMethodprepare_inputs_labels_for_multimodal
( self, input_ids, position_ids, attention_mask, past_key_values, labels, images, audios, sf_masks, sh
vita/model/vita_arch.py:308
↓ 7 callersMethodput
Add items to the buffer in a thread-safe manner. Parameters: - items (list or array-like): The items to be added to
web_demo/vita_html/web/queue.py:26
↓ 7 callersMethodrelease
(self)
web_demo/vita_html/web/parms.py:51
↓ 7 callersMethodsample
( self, logits: torch.Tensor, sampling_metadata: SamplingMetadata, )
web_demo/vllm_tools/vllm_file/qwen2.py:735
↓ 7 callersFunctionsplitlen
(s, sym='/')
VLMEvalKit/vlmeval/smp/misc.py:105
↓ 6 callersMethod__init__
Initialize Conv1dLinear module. Args: in_chans (int): Number of input channels. hidden_chans (int): Number of hidden
vita/model/multimodal_encoder/whale/module/layer/attention.py:217
↓ 6 callersMethod__init__
(self, config: InternVisionConfig)
vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:206
↓ 6 callersFunctioncan_infer
(answer, choices)
VLMEvalKit/vlmeval/utils/matching_util.py:66
↓ 6 callersFunctiondownload_file
(url, filename=None)
VLMEvalKit/vlmeval/smp/file.py:180
↓ 6 callersMethodembed
(self, x)
vita/model/vita_tts/decoder/ticodec/models.py:661
↓ 6 callersFunctionfile_size
(f, unit='GB')
VLMEvalKit/vlmeval/smp/file.py:301
↓ 6 callersFunctionget_clean_string
(s)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:142
↓ 6 callersMethodinfer
(self, xs, buffer, buffer_index, buffer_out)
vita/model/multimodal_encoder/whale/module/component/transformer.py:397
↓ 6 callersFunctionistype
(s, type)
VLMEvalKit/vlmeval/smp/misc.py:60
↓ 6 callersFunctionload_image
(image_file, input_size=448, max_num=6, upscale=False)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:88
↓ 6 callersFunctionmodel_gen
(model, text, images, need_bos=True, padding=False, beams=3, max_token=500)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:34
↓ 6 callersMethodparse
Try to parse into a date. Return: tuple (year, month, date) if successful; otherwise None.
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:385
↓ 6 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_audio_patch.py:540
↓ 6 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_audio_neg_patch.py:681
↓ 6 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_audio_neg_patch_fo.py:679
↓ 6 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_patch_audio.py:548
↓ 6 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_audio_neg_frameCat.py:416
↓ 6 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False,
vita/util/data_utils_video_audio_patch_sf.py:540
↓ 6 callersFunctionpreprocess_multimodal
( sources: Sequence[str], data_args: DataArguments, image_token_num=1, patch_num=[1], audi
vita/util/data_utils_video_audio_patch.py:43
↓ 6 callersFunctionpreprocess_multimodal
( sources: Sequence[str], data_args: DataArguments, image_token_num=1, patch_num=[1], audi
vita/util/data_utils_video_audio_neg_patch.py:43
↓ 6 callersFunctionpreprocess_multimodal
( sources: Sequence[str], data_args: DataArguments, image_token_num=1, patch_num=[1], audi
vita/util/data_utils_video_audio_neg_patch_fo.py:43
↓ 6 callersFunctionpreprocess_multimodal
( sources: Sequence[str], data_args: DataArguments, image_token_num=1, patch_num=[1], audi
vita/util/data_utils_video_patch_audio.py:43
↓ 6 callersFunctionpreprocess_multimodal
( sources: Sequence[str], data_args: DataArguments, image_token_num=1, patch_num=[1], audi
vita/util/data_utils_video_audio_neg_frameCat.py:44
↓ 6 callersFunctionpreprocess_multimodal
( sources: Sequence[str], data_args: DataArguments, image_token_num=1, patch_num=[1], audi
vita/util/data_utils_video_audio_patch_sf.py:43
↓ 6 callersFunctionprocess_images
(images, image_processor, model_cfg)
vita/util/mm_utils.py:30
↓ 6 callersMethodprocess_images
(self, images, model_cfg)
vita/model/language_model/vita_qwen2.py:279
↓ 6 callersFunctionremap
(data_in, tup, off)
VLMEvalKit/vlmeval/tools.py:197
↓ 5 callersMethod__init__
Initialize Conv1dLinear module. Args: in_chans (int): Number of input channels. hidden_chans (int): Number of hidden
vita/model/vita_tts/encoder/attention.py:205
↓ 5 callersMethod__init__
(self, config=None, projector_type="v1")
vita/model/multimodal_projector/builder.py:115
↓ 5 callersFunctionclear_queue
(queue)
web_demo/server.py:89
↓ 5 callersFunctionexpand2square
(pil_img, background_color)
vita/util/data_utils_video_audio_patch.py:640
next →1–100 of 1,650, ranked by callers