MCPcopy Create free account

hub / github.com/Karine-Huang/T2I-CompBench / functions

Functions1,112 in github.com/Karine-Huang/T2I-CompBench

⨍ Functions 1,112◇ Types & classes 166↳ Endpoints 12
↓ 297 callersFunctionprint
(*args, **kwargs)
BLIPvqa_eval/utils.py:217
↓ 156 callersMethodload
Load model from file. Args: path (str): file path
UniDet_eval/experts/depth/base_model.py:5
↓ 92 callersMethodfrom_pretrained
See `AutoTokenizer.from_pretrained` docstring.
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/adapt_tokenizer.py:37
↓ 68 callersMethodget
(self)
UniDet_eval/experts/obj_detection/unidet/predictor.py:196
↓ 58 callersMethodstride
(self)
UniDet_eval/experts/obj_detection/unidet/modeling/backbone/resnest.py:529
↓ 37 callersMethodwrite
(self, buf)
MLLM_eval/ShareGPT4V-CoT_eval/llava/utils.py:73
↓ 35 callersMethodupdate
(self, **kwargs)
BLIPvqa_eval/utils.py:97
↓ 28 callersMethodget_input_embeddings
(self)
BLIPvqa_eval/models/med.py:594
↓ 28 callersMethodkeys
(self)
lora_diffusion/safe_open.py:21
↓ 26 callersFunction_n2p
(w, t=True)
BLIPvqa_eval/models/vit.py:207
↓ 25 callersFunctiontokenizer_image_token
(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)
MLLM_eval/ShareGPT4V-CoT_eval/llava/mm_utils.py:43
↓ 24 callersMethodappend_message
(self, role, message)
MLLM_eval/ShareGPT4V-CoT_eval/llava/conversation.py:106
↓ 23 callersMethodcopy
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/conversation.py:190
↓ 20 callersMethoddevice
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/multimodal_encoder/clip_encoder.py:62
↓ 18 callersMethodencode
(self, text)
CLIPScore_eval/clip/simple_tokenizer.py:121
↓ 15 callersFunctionprint
(*args, **kwargs)
BLIPvqa_eval/BLIP/utils.py:217
↓ 14 callersMethoddecode
(self, tokens)
CLIPScore_eval/clip/simple_tokenizer.py:129
↓ 14 callersMethodget_prompt
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/conversation.py:29
↓ 13 callersMethod__init__
(self, config, layer_num)
BLIPvqa_eval/models/med.py:321
↓ 13 callersMethodgenerate
(self, image, sample=False, num_beams=3, max_length=30, min_length=10, top_p=0.9, repetition_penalty=1.0)
BLIPvqa_eval/models/blip.py:128
↓ 12 callersMethodflush
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/utils.py:87
↓ 12 callersFunctionget_expert_labels
(data_path, label_path, image_path, dataset, experts)
UniDet_eval/dataset/utils.py:76
↓ 12 callersMethodkeys
(self)
GORS_finetune/lora_diffusion/safe_open.py:21
↓ 12 callersMethodto_gradio_chatbot
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/conversation.py:159
↓ 10 callersFunctionget_activation
(name)
UniDet_eval/experts/depth/vit.py:12
↓ 10 callersMethodmax
(self)
BLIPvqa_eval/utils.py:76
↓ 9 callersMethodget_model
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/llava_arch.py:88
↓ 9 callersFunctionload_pretrained_model
(model_path, model_base, model_name, load_8bit=False, load_4bit=False, device_map="auto", device="cuda", **kwa
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/builder.py:26
↓ 9 callersFunctionsafe_open
(filename, framework="pt", device="cpu")
GORS_finetune/lora_diffusion/safe_open.py:46
↓ 9 callersFunctionsafe_open
(filename, framework="pt", device="cpu")
lora_diffusion/safe_open.py:46
↓ 8 callersFunctiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
MLLM_eval/ShareGPT4V-CoT_eval/llava/utils.py:93
↓ 8 callersFunctionget_attention
(name)
UniDet_eval/experts/depth/vit.py:22
↓ 7 callersFunctionget_model_name_from_path
(model_path)
MLLM_eval/ShareGPT4V-CoT_eval/llava/mm_utils.py:65
↓ 7 callersMethodtranspose_for_scores
(self, x)
BLIPvqa_eval/models/med.py:138
↓ 6 callersMethod__init__
(self, embed_dim: int, # vision image_resolution: int,
CLIPScore_eval/clip/model.py:244
↓ 6 callersMethod__init__
Args: stem (nn.Module): a stem module stages (list[list[ResNetBlock]]): several (typically 4) stages,
UniDet_eval/experts/obj_detection/unidet/modeling/backbone/resnest.py:534
↓ 6 callersFunctionaffine_transform
(pair, affine_params)
UniDet_eval/dataset/randaugment.py:19
↓ 6 callersMethodbackward
(ctx, do)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/flash_attn_triton.py:475
↓ 6 callersFunctionextract_lora_ups_down
(model, target_replace_module=DEFAULT_TARGET_REPLACE)
GORS_finetune/lora_diffusion/lora.py:395
↓ 6 callersMethodget_tensor
(self, k)
GORS_finetune/lora_diffusion/safe_open.py:24
↓ 6 callersMethodget_tensor
(self, k)
lora_diffusion/safe_open.py:24
↓ 6 callersMethodget_vision_tower
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/llava_arch.py:36
↓ 6 callersFunctioninject_trainable_lora
inject lora into model, and returns lora parameter groups.
GORS_finetune/lora_diffusion/lora.py:255
↓ 6 callersFunctionprocess_images
(images, image_processor, model_cfg)
MLLM_eval/ShareGPT4V-CoT_eval/llava/mm_utils.py:28
↓ 6 callersFunctionsave_lora_weight
( model, path="./lora.pt", target_replace_module=DEFAULT_TARGET_REPLACE, )
GORS_finetune/lora_diffusion/lora.py:436
↓ 6 callersFunctionsetup_cfg
(args)
UniDet_eval/experts/obj_detection/utils.py:5
↓ 5 callersFunction_cast_if_autocast_enabled
(tensor)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/norm.py:3
↓ 5 callersMethod_parse
(self, args)
MLLM_eval/test_gpt4v_eval.py:73
↓ 5 callersFunctioncreate_vit
(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0)
BLIPvqa_eval/models/blip.py:194
↓ 5 callersMethoddict
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/conversation.py:201
↓ 5 callersFunctiongeneric_param_init_fn_
(module: nn.Module, init_fn_, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, flo
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/param_init_fns.py:28
↓ 5 callersMethodget_images
(self, return_pil=False)
MLLM_eval/ShareGPT4V-CoT_eval/llava/conversation.py:109
↓ 5 callersMethodget_input_embeddings
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/modeling_mpt.py:81
↓ 5 callersFunctionpatch_pipe
( pipe, maybe_unet_path, token: Optional[str] = None, r: int = 4, patch_unet=True, pat
GORS_finetune/lora_diffusion/lora.py:979
↓ 5 callersMethodrun
Wrapper function which calculates the results.
UniDet_eval/experts/obj_detection/unidet/evaluation/oideval.py:506
↓ 4 callersMethod__init__
Init. Args: scale_factor (float): scaling mode (str): interpolation mode
UniDet_eval/experts/depth/blocks.py:141
↓ 4 callersFunction_make_fusion_block
(features, use_bn)
UniDet_eval/experts/depth/models.py:15
↓ 4 callersMethod_make_layer
(self, planes, blocks, stride=1)
CLIPScore_eval/clip/model.py:129
↓ 4 callersFunction_make_scratch
(in_shape, out_shape, groups=1, expand=False)
UniDet_eval/experts/depth/blocks.py:67
↓ 4 callersFunction_make_vit_b16_backbone
( model, features=[96, 192, 384, 768], size=[384, 384], hooks=[2, 5, 8, 11], vit_feat
UniDet_eval/experts/depth/vit.py:221
↓ 4 callersFunction_text_lora_path
(path: str)
GORS_finetune/lora_diffusion/cli_lora_add.py:19
↓ 4 callersFunction_text_lora_path
(path: str)
lora_diffusion/cli_lora_add.py:19
↓ 4 callersFunctioncall_og_forward
()
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/hf_prefixlm_converter.py:74
↓ 4 callersFunctioncollapse_lora
(model, alpha=1.0)
GORS_finetune/lora_diffusion/lora.py:647
↓ 4 callersFunctioncollapse_lora
(model, alpha=1.0)
lora_diffusion/lora.py:647
↓ 4 callersFunctionenhance_level_to_args
(MAX_LEVEL)
BLIPvqa_eval/transform/randaugment.py:208
↓ 4 callersFunctionget_length_grouped_indices
(lengths, batch_size, world_size, generator=None, merge=True)
MLLM_eval/ShareGPT4V-CoT_eval/llava/train/llava_trainer.py:88
↓ 4 callersMethodget_output_embeddings
(self)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/modeling_mpt.py:261
↓ 4 callersFunctioninit_tokenizer
()
BLIPvqa_eval/models/blip.py:186
↓ 4 callersFunctioninject_trainable_lora
inject lora into model, and returns lora parameter groups.
lora_diffusion/lora.py:255
↓ 4 callersFunctioninspect_lora
(model)
GORS_finetune/lora_diffusion/lora.py:1049
↓ 4 callersFunctioninspect_lora
(model)
lora_diffusion/lora.py:1049
↓ 4 callersMethodmetadata
(self)
GORS_finetune/lora_diffusion/safe_open.py:18
↓ 4 callersMethodmetadata
(self)
lora_diffusion/safe_open.py:18
↓ 4 callersFunctionmonkeypatch_remove_lora
(model)
GORS_finetune/lora_diffusion/lora.py:833
↓ 4 callersFunctionmonkeypatch_remove_lora
(model)
lora_diffusion/lora.py:833
↓ 4 callersFunctionparse_safeloras_embeds
Converts a loaded safetensor file that contains Textual Inversion embeds into a dictionary of embed_token: Tensor
GORS_finetune/lora_diffusion/lora.py:611
↓ 4 callersFunctionparse_safeloras_embeds
Converts a loaded safetensor file that contains Textual Inversion embeds into a dictionary of embed_token: Tensor
lora_diffusion/lora.py:611
↓ 4 callersFunctionpost_label_process
(inputs, labels_info)
UniDet_eval/dataset/utils.py:119
↓ 4 callersMethodput
(self, image)
UniDet_eval/experts/obj_detection/unidet/predictor.py:192
↓ 4 callersFunctionread_jsonl
(path: str, key: str=None)
MLLM_eval/ShareGPT4V-CoT_eval/llava/eval/generate_webpage_data_from_table.py:10
↓ 4 callersFunctionsave_all
( unet, text_encoder, save_path, placeholder_token_ids=None, placeholder_tokens=None,
GORS_finetune/lora_diffusion/lora.py:1068
↓ 4 callersFunctionsave_all
( unet, text_encoder, save_path, placeholder_token_ids=None, placeholder_tokens=None,
lora_diffusion/lora.py:1068
↓ 4 callersFunctiontext2Markdown
(text)
MLLM_eval/ShareGPT4V-CoT_eval/llava/eval/webpage/script.js:35
↓ 3 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
BLIPvqa_eval/models/vit.py:26
↓ 3 callersMethod__init__
(self, start_index=1)
UniDet_eval/experts/depth/vit.py:58
↓ 3 callersMethod__init__
(self, *args, **kwargs)
UniDet_eval/experts/obj_detection/unidet/modeling/backbone/splat.py:23
↓ 3 callersFunction_flash_attn_backward
(do, q, k, v, o, lse, dq, dk, dv, bias=None, causal=False, softmax_scale=None)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/flash_attn_triton.py:366
↓ 3 callersFunction_flash_attn_forward
(q, k, v, bias=None, causal=False, softmax_scale=None)
MLLM_eval/ShareGPT4V-CoT_eval/llava/model/language_model/mpt/flash_attn_triton.py:329
↓ 3 callersMethod_mock_response
(self, score=3)
MLLM_eval/test_gpt4v_eval.py:175
↓ 3 callersFunction_text_lora_path
(path: str)
GORS_finetune/lora_diffusion/lora.py:910
↓ 3 callersFunction_text_lora_path
(path: str)
lora_diffusion/lora.py:910
↓ 3 callersFunctionanswer
(chatbot, chat_state, img_list, num_beams, temperature)
MLLM_eval/MiniGPT4-CoT_eval/mGPT_cot_general.py:138
↓ 3 callersFunctionanswer
(chatbot, chat_state, img_list, num_beams, temperature)
MLLM_eval/MiniGPT4-CoT_eval/mGPT_cot_attribute.py:138
↓ 3 callersFunctionapply_learned_embed_in_clip
( learned_embeds, text_encoder, tokenizer, token: Optional[Union[str, List[str]]] = None,
GORS_finetune/lora_diffusion/lora.py:920
↓ 3 callersFunctionapply_learned_embed_in_clip
( learned_embeds, text_encoder, tokenizer, token: Optional[Union[str, List[str]]] = None,
lora_diffusion/lora.py:920
↓ 3 callersFunctionask
(user_message, chatbot, chat_state)
MLLM_eval/MiniGPT4-CoT_eval/mGPT_cot_general.py:132
↓ 3 callersFunctionask
(user_message, chatbot, chat_state)
MLLM_eval/MiniGPT4-CoT_eval/mGPT_cot_attribute.py:132
↓ 3 callersFunctionbuild_logger
(logger_name, logger_filename)
MLLM_eval/ShareGPT4V-CoT_eval/llava/utils.py:17
↓ 3 callersFunctionbuild_resnest_backbone
Create a ResNet instance from config. Returns: ResNet: a :class:`ResNet` instance.
UniDet_eval/experts/obj_detection/unidet/modeling/backbone/resnest.py:612
next →1–100 of 1,112, ranked by callers