MCPcopy Create free account

hub / github.com/NExT-GPT/NExT-GPT / functions

Functions923 in github.com/NExT-GPT/NExT-GPT

⨍ Functions 923◇ Types & classes 178↳ Endpoints 1
↓ 292 callersMethodappend
(self, key, val)
data/IT_data/T-T+X_data/construction/utils.py:20
↓ 50 callersMethodget_model
(self)
nextgpt/model/nextgpt_arch.py:295
↓ 27 callersMethodupdate
(self, **kwargs)
NExT-GPT-Lagacy/code/model/common/logger.py:87
↓ 19 callersMethoddevice
(self)
nextgpt/model/multimodal_projector/projector.py:32
↓ 15 callersMethodmax
(self)
NExT-GPT-Lagacy/code/model/common/logger.py:65
↓ 14 callersMethod__init__
(self, config, layer_num)
NExT-GPT-Lagacy/code/model/qformer.py:380
↓ 14 callersMethod__init__
(self, config, layer_num)
nextgpt/model/multimodal_projector/qformer.py:372
↓ 14 callersMethodappend
(self, key, val)
data/IT_data/MosIT_data/construction/utils.py:19
↓ 14 callersFunctiontokenizer_multiple_token
(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, video_token_index=VIDEO_TOKEN_INDEX, audio_token_inde
nextgpt/mm_utils.py:244
↓ 12 callersMethodget_input_embeddings
(self)
nextgpt/model/multimodal_projector/qformer.py:692
↓ 11 callersMethodget_audio_decoder
(self)
nextgpt/model/nextgpt_arch.py:122
↓ 10 callersMethodcopy
(self)
nextgpt/conversation.py:201
↓ 10 callersMethodget_image_decoder
(self)
nextgpt/model/nextgpt_arch.py:80
↓ 10 callersMethodget_video_decoder
(self)
nextgpt/model/nextgpt_arch.py:101
↓ 9 callersFunctiontokenizer_image_token
(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)
nextgpt/mm_utils.py:222
↓ 9 callersMethodwrite
(self, msg)
data/IT_data/MosIT_data/construction/utils.py:33
↓ 8 callersMethod__init__
(self, time_dim=2)
NExT-GPT-Lagacy/code/model/ImageBind/models/multimodal_preprocessors.py:410
↓ 8 callersMethod__init__
(self, time_dim=2)
nextgpt/model/multimodal_encoder/ImageBind/models/multimodal_preprocessors.py:410
↓ 8 callersMethod_train_with_mode
:param num_gen_tokens: the number of generation tokens :param modality: mode can be 'image' / 'video' / 'audio' / 'text' :par
NExT-GPT-Lagacy/code/model/anyToImageVideoAudio.py:346
↓ 8 callersMethodappend_message
(self, role, message)
nextgpt/conversation.py:125
↓ 7 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
nextgpt/model/multimodal_projector/group_vit.py:26
↓ 7 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
nextgpt/model/multimodal_projector/group.py:26
↓ 7 callersMethodget_multimodal_tower
(self)
nextgpt/model/nextgpt_arch.py:68
↓ 7 callersMethodtranspose_for_scores
(self, x)
NExT-GPT-Lagacy/code/model/qformer.py:162
↓ 7 callersMethodtranspose_for_scores
(self, x)
nextgpt/model/multimodal_projector/qformer.py:154
↓ 6 callersMethod__init__
( self, hidden_size: int, intermediate_size: int, hidden_act: str, )
NExT-GPT-Lagacy/code/model/modeling_llama.py:127
↓ 6 callersFunctionbuild_output_projector
(config, projector_type, out_features, num_query_token, delay_load=False, **kwargs)
nextgpt/model/multimodal_projector/builder.py:66
↓ 6 callersFunctionbuilder_decoder
(config, decoder_modality="image")
nextgpt/model/multimodal_decoder/builder.py:8
↓ 6 callersMethodgenerate
inputs = { 'image_paths': optional, 'audio_paths': optional 'video_paths': optional
NExT-GPT-Lagacy/code/model/anyToImageVideoAudio.py:898
↓ 6 callersMethodget_prompt
(self)
nextgpt/conversation.py:50
↓ 6 callersFunctionorder_pick_k
(lst, k)
nextgpt/dataset/base_dataset.py:21
↓ 6 callersMethodvalue
(self)
NExT-GPT-Lagacy/code/model/common/logger.py:69
↓ 6 callersMethodwrite
(self, msg)
data/IT_data/T-T+X_data/construction/utils.py:34
↓ 5 callersMethoddecode
(self, tokens)
nextgpt/model/multimodal_encoder/ImageBind/models/multimodal_preprocessors.py:577
↓ 5 callersMethodencode
(self, text)
nextgpt/model/multimodal_encoder/ImageBind/models/multimodal_preprocessors.py:567
↓ 5 callersMethodget_output_embeddings
(self)
nextgpt/model/multimodal_projector/qformer.py:974
↓ 5 callersMethodlog
(self, extra_msg='')
data/IT_data/T-T+X_data/construction/utils.py:24
↓ 5 callersMethodpreprocess
(self, audio)
nextgpt/dataset/audio_processor.py:309
↓ 5 callersMethodwrite
(self, buf)
nextgpt/utils.py:73
↓ 4 callersMethod__init__
(self, dim: int)
NExT-GPT-Lagacy/code/model/ImageBind/models/helpers.py:18
↓ 4 callersMethod__init__
(self, dim: int)
nextgpt/model/multimodal_encoder/ImageBind/models/helpers.py:18
↓ 4 callersMethoddecode
(self, tokens)
NExT-GPT-Lagacy/code/model/ImageBind/models/multimodal_preprocessors.py:577
↓ 4 callersMethodencode_image
(self, image_paths)
NExT-GPT-Lagacy/code/model/anyToImageVideoAudio.py:261
↓ 4 callersMethodflush
(self)
nextgpt/utils.py:87
↓ 4 callersMethodget_audio_noise_scheduler
(self)
nextgpt/model/nextgpt_arch.py:143
↓ 4 callersFunctionget_clip_timepoints
(clip_sampler, duration)
nextgpt/model/multimodal_encoder/ImageBind/data.py:68
↓ 4 callersMethodget_image_noise_scheduler
(self)
nextgpt/model/nextgpt_arch.py:98
↓ 4 callersFunctionget_length_grouped_indices
(lengths, batch_size, world_size, generator=None, merge=True)
nextgpt_trainer.py:105
↓ 4 callersMethodget_output_audio_projector
(self)
nextgpt/model/nextgpt_arch.py:158
↓ 4 callersMethodget_output_image_projector
(self)
nextgpt/model/nextgpt_arch.py:146
↓ 4 callersMethodget_output_video_projector
(self)
nextgpt/model/nextgpt_arch.py:152
↓ 4 callersMethodget_video_noise_scheduler
(self)
nextgpt/model/nextgpt_arch.py:119
↓ 4 callersMethodresample
(self, waveform, sr)
nextgpt/dataset/audio_processor.py:237
↓ 3 callersMethod__init__
(self, data_source, replacement=False, num_samples=None)
NExT-GPT-Lagacy/code/dataset/samplers.py:37
↓ 3 callersMethod__init__
( self, in_features, hidden_features=None, out_features=None, act_laye
NExT-GPT-Lagacy/code/model/ImageBind/models/transformer.py:73
↓ 3 callersMethod__init__
(self, data_source, replacement=False, num_samples=None)
nextgpt/dataset/sampler.py:37
↓ 3 callersMethod__init__
(self, in_features=None, out_features=None, num_layers=1)
nextgpt/model/multimodal_projector/projector.py:14
↓ 3 callersMethod__init__
( self, in_features, hidden_features=None, out_features=None, act_laye
nextgpt/model/multimodal_encoder/ImageBind/models/transformer.py:73
↓ 3 callersFunctionbuild_input_projector
(config, delay_load=False, **kwargs)
nextgpt/model/multimodal_projector/builder.py:49
↓ 3 callersMethodcompute_snr
Computes SNR as per https://github.com/TiankaiHang/Min-SNR-Diffusion-Training/blob/521b624bd70c67cee4bdf49225915f5945a872e3/guided_diffusion/
nextgpt/model/language_model/nextgpt_llama.py:278
↓ 3 callersMethodencode_audio
(self, audio_paths)
NExT-GPT-Lagacy/code/model/anyToImageVideoAudio.py:250
↓ 3 callersMethodencode_video
(self, video_paths)
NExT-GPT-Lagacy/code/model/anyToImageVideoAudio.py:239
↓ 3 callersMethodfeature_select
(self, image_forward_outs)
nextgpt/model/multimodal_encoder/clip_encoder.py:35
↓ 3 callersMethodforward
(self, x)
NExT-GPT-Lagacy/code/model/ImageBind/models/multimodal_preprocessors.py:414
↓ 3 callersMethodforward
(self, x)
nextgpt/model/multimodal_encoder/ImageBind/models/multimodal_preprocessors.py:414
↓ 3 callersMethodget_audio_vae
(self)
nextgpt/model/nextgpt_arch.py:134
↓ 3 callersMethodget_image_vae
(self)
nextgpt/model/nextgpt_arch.py:92
↓ 3 callersMethodget_input_embeddings
(self)
NExT-GPT-Lagacy/code/model/qformer.py:700
↓ 3 callersFunctionget_mm_adapter_state_maybe_zero_3
(named_params, keys_to_match)
train.py:97
↓ 3 callersMethodget_video_vae
(self)
nextgpt/model/nextgpt_arch.py:113
↓ 3 callersFunctionl2_loss
Args: u: (N, T_I_V_A.txt, D) tensor. v: (N, T_I_V_A.txt, D) tensor. Returns: l1_loss: (N,) tensor of summed L1 loss.
NExT-GPT-Lagacy/code/model/common/utils.py:356
↓ 3 callersFunctionl2_loss
Args: u: (N, T_I_V_A.txt, D) tensor. v: (N, T_I_V_A.txt, D) tensor. Returns: l1_loss: (N,) tensor of summed L1 loss.
nextgpt/model/language_model/nextgpt_llama.py:91
↓ 3 callersFunctionload_config
the configuration of each model can rewrite the base configuration
NExT-GPT-Lagacy/code/config/__init__.py:21
↓ 3 callersMethodload_model
(self, device_map=None)
nextgpt/model/multimodal_encoder/clip_encoder.py:24
↓ 3 callersFunctionload_pretrained_model
(model_path, model_base, model_name, load_8bit=False, load_4bit=False, device_map="auto", device="cuda", use_f
nextgpt/model/builder.py:26
↓ 3 callersFunctionmaybe_zero_3
(param, ignore_status=False, name=None)
train.py:49
↓ 3 callersFunctionprocess_caption
(caption)
NExT-GPT-Lagacy/code/dataset/utils.py:5
↓ 2 callersMethod__init__
(self, size=224, crop_size: Dict[str, int] = 224, image_m
nextgpt/model/multimodal_encoder/imagebind_processor.py:12
↓ 2 callersMethod__len__
(self)
NExT-GPT-Lagacy/code/dataset/samplers.py:75
↓ 2 callersMethod_batch
extracts samples only pertaining to this worker's batch
NExT-GPT-Lagacy/code/dataset/samplers.py:162
↓ 2 callersMethod_batch
extracts samples only pertaining to this worker's batch
nextgpt/dataset/sampler.py:162
↓ 2 callersFunction_tokenize_fn
Tokenize a list of strings.
nextgpt/dataset/dataset_utils.py:54
↓ 2 callersFunctionauto_upgrade
(config)
nextgpt/model/utils.py:4
↓ 2 callersFunctionbuild_directory
(path)
NExT-GPT-Lagacy/code/train.py:52
↓ 2 callersFunctionbuild_multimodal_tower
(vision_tower_cfg, **kwargs)
nextgpt/model/multimodal_encoder/builder.py:6
↓ 2 callersFunctionbytes_to_unicode
Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you
NExT-GPT-Lagacy/code/model/ImageBind/models/multimodal_preprocessors.py:448
↓ 2 callersFunctionbytes_to_unicode
Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you
nextgpt/model/multimodal_encoder/ImageBind/models/multimodal_preprocessors.py:448
↓ 2 callersFunctioncast_if_src_dtype
( tensor: torch.Tensor, src_dtype: torch.dtype, tgt_dtype: torch.dtype )
NExT-GPT-Lagacy/code/model/ImageBind/models/helpers.py:100
↓ 2 callersFunctioncast_if_src_dtype
( tensor: torch.Tensor, src_dtype: torch.dtype, tgt_dtype: torch.dtype )
nextgpt/model/multimodal_encoder/ImageBind/models/helpers.py:100
↓ 2 callersMethodencode_audios
(self, audios)
nextgpt/model/nextgpt_arch.py:380
↓ 2 callersMethodencode_images
(self, images)
nextgpt/model/nextgpt_arch.py:370
↓ 2 callersMethodencode_videos
(self, videos)
nextgpt/model/nextgpt_arch.py:375
↓ 2 callersFunctionexpand2square
(pil_img, background_color)
nextgpt/mm_utils.py:208
↓ 2 callersMethodforward
(self, x)
NExT-GPT-Lagacy/code/model/ImageBind/models/transformer.py:89
↓ 2 callersMethodforward
(self, x)
nextgpt/model/multimodal_encoder/ImageBind/models/transformer.py:89
↓ 2 callersMethodget_attn
(self, attn, gumbel=None, hard=None)
nextgpt/model/multimodal_projector/group_vit.py:116
↓ 2 callersMethodget_attn
(self, attn, gumbel=None, hard=None)
nextgpt/model/multimodal_projector/group.py:116
↓ 2 callersMethodget_audio_text_encoder
(self)
nextgpt/model/nextgpt_arch.py:128
↓ 2 callersMethodget_audio_tokenizer
(self)
nextgpt/model/nextgpt_arch.py:131
↓ 2 callersMethodget_audio_unet
(self)
nextgpt/model/nextgpt_arch.py:137
next →1–100 of 923, ranked by callers