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
↓ 1 callersFunctionget_env
(name)
VLMEvalKit/vlmeval/tools.py:293
↓ 1 callersFunctionget_eval
(judge, content)
VLMEvalKit/vlmeval/dataset/utils/llavabench.py:12
↓ 1 callersFunctionget_f1
(gt, pred)
VLMEvalKit/vlmeval/dataset/slidevqa.py:14
↓ 1 callersFunctionget_f1
(data)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:363
↓ 1 callersFunctionget_font
()
VLMEvalKit/vlmeval/dataset/mmlongbench.py:195
↓ 1 callersFunctionget_gpt4_ICE
()
VLMEvalKit/vlmeval/dataset/mmlongbench.py:14
↓ 1 callersFunctionget_gpt4_ICE
()
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:8
↓ 1 callersFunctionget_gpt4_ICE
()
VLMEvalKit/vlmeval/dataset/utils/mathv.py:38
↓ 1 callersFunctionget_gpu_num
(model_name)
VLMEvalKit/vlmeval/api/hf_chat_model.py:8
↓ 1 callersMethodget_image_token_len
(self, img_path, detail='low')
VLMEvalKit/vlmeval/api/gpt.py:207
↓ 1 callersMethodget_images
(self, return_pil=False)
vita/conversation.py:177
↓ 1 callersMethodget_index
(self, max_frame)
VLMEvalKit/vlmeval/dataset/mvbench.py:476
↓ 1 callersMethodget_index
(self, num_frames, num_segments)
VLMEvalKit/vlmeval/vlm/video_llm/pllava.py:61
↓ 1 callersMethodget_index
(self, bound, fps, max_frame, first_idx=0)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:214
↓ 1 callersMethodget_input_embeddings
(self)
vita/model/multimodal_encoder/internvit/modeling_intern_vit.py:351
↓ 1 callersFunctionget_mm_adapter_state_maybe_zero_3
(named_params, keys_to_match)
vita/train/train.py:149
↓ 1 callersFunctionget_modality_length_grouped_indices
(lengths, batch_size, world_size, generator=None)
vita/train/vita_trainer.py:62
↓ 1 callersMethodget_model
(self, model_path)
vita/model/vita_tts/decoder/llm2tts.py:41
↓ 1 callersMethodget_model
(self)
vita/model/language_model/vita_fo_qwen2.py:53
↓ 1 callersMethodget_model
(self)
vita/model/language_model/vita_nemo.py:136
↓ 1 callersMethodget_model
(self)
vita/model/language_model/vita_qwen2.py:138
↓ 1 callersMethodget_model_conf
(self, model_path)
vita/model/vita_tts/decoder/llm2tts.py:32
↓ 1 callersMethodget_model_output
(self, model, video_processor, tokenizer, video, qs)
VLMEvalKit/vlmeval/vlm/video_llm/chat_uni_vi.py:110
↓ 1 callersMethodget_model_output
(self, model, video_processor, tokenizer, video, qs)
VLMEvalKit/vlmeval/vlm/video_llm/llama_vid.py:66
↓ 1 callersMethodget_model_output
(self, model, video_processor, tokenizer, video, qs)
VLMEvalKit/vlmeval/vlm/video_llm/video_llava.py:109
↓ 1 callersMethodget_model_output
(self, model, video_processor, tokenizer, video, qs)
VLMEvalKit/vlmeval/vlm/video_llm/video_chatgpt.py:45
↓ 1 callersFunctionget_peft_state_maybe_zero_3
(named_params, bias)
vita/train/train.py:116
↓ 1 callersFunctionget_peft_state_non_lora_maybe_zero_3
(named_params, require_grad_only=True)
vita/train/train.py:141
↓ 1 callersFunctionget_prompt
(conv)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:22
↓ 1 callersFunctionget_prompt2
(conv)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:32
↓ 1 callersFunctionget_score
(model, dataset)
VLMEvalKit/scripts/summarize.py:4
↓ 1 callersFunctionget_seq_frames
Calculate the indices of frames to extract from a video. Parameters: total_num_frames (int): Total number of frames in the video. de
videomme/yt_video_inference_qa_imgs.py:95
↓ 1 callersMethodget_sinusoid_encoding_table
Sinusoid position encoding table
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:165
↓ 1 callersMethodget_supported_archs
()
web_demo/vllm_tools/vllm_file/__init__.py:177
↓ 1 callersMethodget_token_len
(self, inputs)
VLMEvalKit/vlmeval/api/gpt.py:227
↓ 1 callersFunctionget_version
()
VLMEvalKit/docs/en/conf.py:34
↓ 1 callersFunctionget_version
()
VLMEvalKit/docs/zh-CN/conf.py:34
↓ 1 callersFunctionget_video_frame
( video_path, max_frames=MAX_IMAGE_LENGTH, min_frames=MIN_IMAGE_LENGTH, video_framerate=1,
data_tools/statistics_token_num_patch_video.py:84
↓ 1 callersMethodget_vision_tower
(self)
vita/model/vita_arch.py:140
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/concat_data_frameCat.py:63
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/concat_data_patch_nemo.py:63
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/statistics_token_num_frameCat.py:74
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/check_audio_lost.py:30
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/statistics_token_num.py:37
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/concat_data_patch.py:63
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/concat_data_patch_qwen.py:64
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/concat_data.py:32
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/statistics_token_num_patch.py:68
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/statistics_token_num_patch_video.py:78
↓ 1 callersFunctionget_wav_duration
(file_path)
data_tools/statistics_audio_duration.py:26
↓ 1 callersFunctionh2r
(value)
VLMEvalKit/vlmeval/smp/misc.py:44
↓ 1 callersMethodimage_to_base64
(self, image_path)
VLMEvalKit/vlmeval/api/sensechat_vision.py:65
↓ 1 callersFunctionimg_root_map
(dataset)
VLMEvalKit/vlmeval/dataset/image_base.py:6
↓ 1 callersMethodinfer
(self, xs_pad, buffer, buffer_index, buffer_out, pe_index)
vita/model/vita_tts/encoder/encoder.py:149
↓ 1 callersMethodinfer
(self, hidden, top_k, prefix, penalty_window_size, penalty, max_tokens=1000)
vita/model/vita_tts/decoder/decoder.py:314
↓ 1 callersFunctioninfer_data
(model_name, work_dir, dataset, out_file, nframe=8, pack=False, verbose=False, api_nproc=4)
VLMEvalKit/vlmeval/inference_video.py:49
↓ 1 callersFunctioninfer_data
(model_name, work_dir, dataset, out_file, verbose=False, api_nproc=4)
VLMEvalKit/vlmeval/inference_mt.py:77
↓ 1 callersFunctioninfer_data
(model_name, work_dir, dataset, out_file, verbose=False, api_nproc=4)
VLMEvalKit/vlmeval/inference.py:69
↓ 1 callersFunctioninfer_data_api
(work_dir, model_name, dataset, nframe=8, pack=False, samples_dict={}, api_nproc=4)
VLMEvalKit/vlmeval/inference_video.py:21
↓ 1 callersFunctioninfer_data_api
(work_dir, model_name, dataset, index_set=None, api_nproc=4, ignore_failed=False)
VLMEvalKit/vlmeval/inference_mt.py:40
↓ 1 callersFunctioninfer_data_api
(work_dir, model_name, dataset, index_set=None, api_nproc=4, ignore_failed=False)
VLMEvalKit/vlmeval/inference.py:21
↓ 1 callersFunctioninfer_data_job
(model, work_dir, model_name, dataset, verbose=False, api_nproc=4, ignore_failed=False)
VLMEvalKit/vlmeval/inference.py:143
↓ 1 callersFunctioninfer_data_job_mt
(model, work_dir, model_name, dataset, verbose=False, api_nproc=4, ignore_failed=False)
VLMEvalKit/vlmeval/inference_mt.py:151
↓ 1 callersFunctioninfer_data_job_video
( model, work_dir, model_name, dataset, nframe=8, pack=False,
VLMEvalKit/vlmeval/inference_video.py:105
↓ 1 callersFunctioninit_encoder_llm
(configs)
vita/model/vita_tts/utils.py:29
↓ 1 callersMethodinit_kv_cache_prefix
(self, config)
vita/model/vita_tts/decoder/decoder.py:121
↓ 1 callersFunctioninit_model
(configs)
vita/model/multimodal_encoder/whale/init_model.py:177
↓ 1 callersFunctioninit_omni_lmm
(model_path)
VLMEvalKit/vlmeval/vlm/omnilmm.py:16
↓ 1 callersMethodinit_pre_nn
(self, config)
vita/model/vita_tts/decoder/decoder.py:156
↓ 1 callersFunctioninitialize
()
VLMEvalKit/vlmeval/dataset/vcr.py:12
↓ 1 callersFunctioninput_processor_for_qwen2_multimodal_base
( model_config: ModelConfig, hf_config, llm_inputs: LLMInputs, *, image_token_id: int,
web_demo/vllm_tools/vllm_file/qwen2.py:193
↓ 1 callersFunctioninsert_separator
(X, sep)
vita/util/mm_utils.py:50
↓ 1 callersFunctionis_api
(x)
VLMEvalKit/scripts/auto_run.py:5
↓ 1 callersMethodis_empty
Check if the queue is empty in a thread-safe manner. Parameters: - None Returns: - bool: Tr
web_demo/vita_html/web/queue.py:140
↓ 1 callersFunctionis_equal
(asw: str, gt_asw: str)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:11
↓ 1 callersFunctionis_float_equal
(reference, prediction, include_percentage: bool = False, is_close: float = False)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:112
↓ 1 callersFunctionis_image
(file_path)
web_demo/web_ability_demo.py:127
↓ 1 callersFunctionis_video
(file_path)
web_demo/web_ability_demo.py:122
↓ 1 callersFunctionis_wav
(file_path)
web_demo/web_ability_demo.py:132
↓ 1 callersFunctionisfloat
(num)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:187
↓ 1 callersMethodlength_ok
(self, inputs)
VLMEvalKit/vlmeval/api/hf_chat_model.py:159
↓ 1 callersFunctionlist_to_dict
(lst)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:70
↓ 1 callersFunctionlist_to_dict
(lst)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:96
↓ 1 callersFunctionload_balancing_loss_func
r""" Computes auxiliary load balancing loss as in Switch Transformer - implemented in Pytorch. See Switch Transformer (https://arxiv.org/abs/
vita/model/language_model/vita_mixtral.py:20
↓ 1 callersFunctionload_checkpoint
(model: torch.nn.Module, path: str)
vita/model/vita_tts/utils.py:10
↓ 1 callersFunctionload_clip_visual_state_dict
( checkpoint_path: str, map_location: str = "cpu", is_openai: bool = False, skip_list: list = [] )
vita/model/multimodal_encoder/eva_clip/eva_vit.py:849
↓ 1 callersFunctionload_cmvn
(cmvn_file, is_json)
vita/model/vita_tts/encoder/cmvn.py:102
↓ 1 callersFunctionload_cmvn
(filename, is_json)
vita/model/multimodal_encoder/whale/cmvn.py:84
↓ 1 callersFunctionload_cmvn_json
(json_cmvn_file)
vita/model/multimodal_encoder/whale/cmvn.py:35
↓ 1 callersFunctionload_cmvn_kaldi
(kaldi_cmvn_file)
vita/model/multimodal_encoder/whale/cmvn.py:52
↓ 1 callersMethodload_data
(self, dataset)
VLMEvalKit/vlmeval/dataset/image_base.py:133
↓ 1 callersMethodload_data
(self, dataset)
VLMEvalKit/vlmeval/dataset/text_base.py:65
↓ 1 callersFunctionload_from_hf
(repo_id, filename, subfolder=None)
vita/model/builder.py:79
↓ 1 callersMethodload_into_video_and_process
(self, line)
VLMEvalKit/vlmeval/dataset/mvbench.py:270
↓ 1 callersMethodload_model
(self)
vita/model/multimodal_encoder/siglip/siglip_encoder.py:22
↓ 1 callersMethodload_model
(self)
vita/model/multimodal_encoder/internvit/internvit_encoder.py:25
↓ 1 callersMethodload_model
(self)
vita/model/multimodal_encoder/eva_clip/eva_clip_encoder.py:22
↓ 1 callersFunctionload_model_embemding
(model_path)
web_demo/web_ability_demo.py:137
↓ 1 callersFunctionload_model_embemding
(model_path)
web_demo/server.py:96
↓ 1 callersMethodload_pack_answers
(self, data_raw)
VLMEvalKit/vlmeval/dataset/mmbench_video.py:172
← previousnext →501–600 of 1,650, ranked by callers