MCPcopy Create free account

hub / github.com/PKU-YuanGroup/Chat-UniVi / functions

Functions291 in github.com/PKU-YuanGroup/Chat-UniVi

⨍ Functions 291◇ Types & classes 52
↓ 1 callersFunctionget_peft_state_non_lora_maybe_zero_3
(named_params, require_grad_only=True)
ChatUniVi/train/train.py:150
↓ 1 callersMethodget_prompt
(self)
ChatUniVi/conversation.py:29
↓ 1 callersFunctionget_rank
()
ChatUniVi/model/multimodal_encoder/utils.py:47
↓ 1 callersFunctionget_tokenize_len
(prompts)
ChatUniVi/train/train.py:731
↓ 1 callersMethodget_vision_tower
(self)
ChatUniVi/model/arch.py:94
↓ 1 callersMethodinitialize_cluster_modules
(self, model_args)
ChatUniVi/model/arch.py:72
↓ 1 callersMethodinitialize_vision_modules
(self, model_args, fsdp=None)
ChatUniVi/model/arch.py:42
↓ 1 callersMethodinitialize_vision_tokenizer
(self, model_args, tokenizer)
ChatUniVi/model/arch.py:405
↓ 1 callersFunctioninsert_separator
(X, sep)
ChatUniVi/mm_utils.py:21
↓ 1 callersFunctioninterpolate_pos_embed
(model, checkpoint_model)
ChatUniVi/model/multimodal_encoder/eva_vit.py:379
↓ 1 callersFunctionis_main_process
()
ChatUniVi/model/multimodal_encoder/utils.py:53
↓ 1 callersFunctionload_from_hf
(repo_id, filename, subfolder=None)
ChatUniVi/model/builder.py:45
↓ 1 callersMethodload_model
(self)
ChatUniVi/model/multimodal_encoder/clip_encoder.py:26
↓ 1 callersFunctionmain
Main function to control the flow of the program.
ChatUniVi/eval/evaluate/evaluate_benchmark_4_temporal.py:83
↓ 1 callersFunctionmain
Main function to control the flow of the program.
ChatUniVi/eval/evaluate/evaluate_benchmark_1_correctness.py:84
↓ 1 callersFunctionmain
Main function to control the flow of the program.
ChatUniVi/eval/evaluate/evaluate_benchmark_2_detailed_orientation.py:84
↓ 1 callersFunctionmain
Main function to control the flow of the program.
ChatUniVi/eval/evaluate/evaluate_video_qa.py:83
↓ 1 callersFunctionmain
Main function to control the flow of the program.
ChatUniVi/eval/evaluate/evaluate_benchmark_3_context.py:84
↓ 1 callersFunctionmain
Main function to control the flow of the program.
ChatUniVi/eval/evaluate/evaluate_benchmark_5_consistency.py:89
↓ 1 callersFunctionmake_delta
(base_model_path, target_model_path, delta_path, hub_repo_id)
ChatUniVi/model/make_delta.py:13
↓ 1 callersFunctionmake_supervised_data_module
Make dataset and collator for supervised fine-tuning.
ChatUniVi/train/train.py:972
↓ 1 callersFunctionmaybe_zero_3
(param, ignore_status=False, name=None)
ChatUniVi/train/trainer.py:7
↓ 1 callersFunctionmerge_tokens
Merge tokens in the same cluster to a single cluster. Implemented by torch.index_add(). Flops: B*N*(C+2) Return: out_dict (dict): dict
ChatUniVi/model/cluster.py:174
↓ 1 callersFunctionparse_args
()
ChatUniVi/eval/evaluate/evaluate_benchmark_4_temporal.py:18
↓ 1 callersFunctionparse_args
()
ChatUniVi/eval/evaluate/evaluate_benchmark_1_correctness.py:18
↓ 1 callersFunctionparse_args
()
ChatUniVi/eval/evaluate/evaluate_benchmark_2_detailed_orientation.py:18
↓ 1 callersFunctionparse_args
()
ChatUniVi/eval/evaluate/evaluate_video_qa.py:18
↓ 1 callersFunctionparse_args
()
ChatUniVi/eval/evaluate/evaluate_benchmark_3_context.py:18
↓ 1 callersFunctionparse_args
()
ChatUniVi/eval/evaluate/evaluate_benchmark_5_consistency.py:18
↓ 1 callersFunctionparse_score
(review)
ChatUniVi/eval/evaluate/evaluate_gpt_review_visual.py:36
↓ 1 callersFunctionpreprocess_llama_2
( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False )
ChatUniVi/train/train.py:345
↓ 1 callersFunctionpreprocess_mpt
( sources, tokenizer: transformers.PreTrainedTokenizer, )
ChatUniVi/train/train.py:521
↓ 1 callersFunctionpreprocess_phi
( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False )
ChatUniVi/train/train.py:610
↓ 1 callersFunctionpreprocess_plain
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, )
ChatUniVi/train/train.py:588
↓ 1 callersFunctionpreprocess_v1
( sources, tokenizer: transformers.PreTrainedTokenizer, has_image: bool = False )
ChatUniVi/train/train.py:434
↓ 1 callersFunctionread_json
(file)
ChatUniVi/eval/model_video_qa.py:18
↓ 1 callersFunctionread_jsonl
(file)
ChatUniVi/eval/evaluate/evaluate_benchmark_4_temporal.py:10
↓ 1 callersFunctionread_jsonl
(file)
ChatUniVi/eval/evaluate/evaluate_benchmark_1_correctness.py:10
↓ 1 callersFunctionread_jsonl
(file)
ChatUniVi/eval/evaluate/evaluate_benchmark_2_detailed_orientation.py:10
↓ 1 callersFunctionread_jsonl
(file)
ChatUniVi/eval/evaluate/evaluate_video_qa.py:10
↓ 1 callersFunctionread_jsonl
(file)
ChatUniVi/eval/evaluate/evaluate_benchmark_3_context.py:10
↓ 1 callersFunctionread_jsonl
(file)
ChatUniVi/eval/evaluate/evaluate_benchmark_5_consistency.py:10
↓ 1 callersFunctionreplace_llama_attn_with_flash_attn
()
ChatUniVi/train/llama_flash_attn_monkey_patch.py:114
↓ 1 callersFunctionsafe_save_model_for_hf_trainer
Collects the state dict and dump to disk.
ChatUniVi/train/train.py:177
↓ 1 callersFunctionsave_video_to_local
(video_path)
main_demo_7B.py:25
↓ 1 callersFunctionsave_video_to_local
(video_path)
main_demo_13B.py:25
↓ 1 callersFunctionsetup_for_distributed
This function disables printing when not in master process
ChatUniVi/model/multimodal_encoder/utils.py:17
↓ 1 callersFunctionsmart_tokenizer_and_embedding_resize
Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.
ChatUniVi/train/train.py:215
↓ 1 callersFunctionsplit_list
Split a list into n (roughly) equal-sized chunks
ChatUniVi/eval/model_coco_vqa.py:61
↓ 1 callersFunctionsplit_list
Split a list into n (roughly) equal-sized chunks
ChatUniVi/eval/model_vqa_scienceqa.py:19
↓ 1 callersFunctionsplit_list
Split a list into n (roughly) equal-sized chunks
ChatUniVi/eval/model_video_consistency.py:18
↓ 1 callersFunctionsplit_list
Split a list into n (roughly) equal-sized chunks
ChatUniVi/eval/model_video_general.py:18
↓ 1 callersFunctionsplit_list
Split a list into n (roughly) equal-sized chunks
ChatUniVi/eval/model_vqa.py:16
↓ 1 callersFunctionsplit_list
Split a list into n (roughly) equal-sized chunks
ChatUniVi/eval/model_video_qa.py:23
Method__call__
(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)
ChatUniVi/mm_utils.py:62
Method__call__
Torch method for processing logits.
ChatUniVi/eval/model_coco_vqa.py:74
Method__call__
(self, instances: Sequence[Dict])
ChatUniVi/train/train.py:934
Method__getattr__
(self, attr)
ChatUniVi/utils.py:70
Method__getitem__
(self, i)
ChatUniVi/train/train.py:784
Method__init__
(self, logger, log_level=logging.INFO)
ChatUniVi/utils.py:64
Method__init__
(self, keywords, tokenizer, input_ids)
ChatUniVi/mm_utils.py:51
Method__init__
(self, model_path, conv_mode="simple")
ChatUniVi/demo.py:14
Method__init__
(self, config)
ChatUniVi/model/arch.py:12
Method__init__
(self, drop_prob=None)
ChatUniVi/model/cluster.py:83
Method__init__
(self, dim, num_heads, mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., dro
ChatUniVi/model/cluster.py:260
Method__init__
(self, config)
ChatUniVi/model/language_model/llama.py:26
Method__init__
(self, config)
ChatUniVi/model/language_model/phi.py:44
Method__init__
(self, config: PretrainedConfig)
ChatUniVi/model/language_model/language_model/modeling_phi.py:72
Method__init__
( self, dim: int, base: int = 10000, scale_base: Optional[float] = None,
ChatUniVi/model/language_model/language_model/modeling_phi.py:182
Method__init__
( self, causal: bool = True, softmax_scale: Optional[float] = None, attention_
ChatUniVi/model/language_model/language_model/modeling_phi.py:337
Method__init__
( self, causal: bool = True, softmax_scale: Optional[float] = None, attention_
ChatUniVi/model/language_model/language_model/modeling_phi.py:397
Method__init__
( self, config: PretrainedConfig, dtype: Optional[torch.dtype] = None, device:
ChatUniVi/model/language_model/language_model/modeling_phi.py:514
Method__init__
( self, config: PretrainedConfig, block_idx: Optional[int] = None, )
ChatUniVi/model/language_model/language_model/modeling_phi.py:751
Method__init__
(self, config: PretrainedConfig)
ChatUniVi/model/language_model/language_model/modeling_phi.py:800
Method__init__
(self, shift_labels: bool = True)
ChatUniVi/model/language_model/language_model/modeling_phi.py:822
Method__init__
(self, *inputs, **kwargs)
ChatUniVi/model/language_model/language_model/modeling_phi.py:846
Method__init__
(self, config: PhiConfig)
ChatUniVi/model/language_model/language_model/modeling_phi.py:897
Method__init__
(self, config: PhiConfig)
ChatUniVi/model/language_model/language_model/modeling_phi.py:940
Method__init__
( self, vocab_size: int = 50304, n_positions: int = 2048, n_embd: int = 1024,
ChatUniVi/model/language_model/language_model/configuration_phi.py:21
Method__init__
(self, channels)
ChatUniVi/model/multimodal_projector/builder.py:19
Method__init__
(self, drop_prob=None)
ChatUniVi/model/multimodal_encoder/eva_vit.py:35
Method__init__
( self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., w
ChatUniVi/model/multimodal_encoder/eva_vit.py:67
Method__init__
(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., dr
ChatUniVi/model/multimodal_encoder/eva_vit.py:155
Method__init__
(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)
ChatUniVi/model/multimodal_encoder/eva_vit.py:189
Method__init__
(self, window_size, num_heads)
ChatUniVi/model/multimodal_encoder/eva_vit.py:212
Method__init__
(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12, nu
ChatUniVi/model/multimodal_encoder/eva_vit.py:253
Method__init__
(self, image_size=224, mean=None, std=None, min_scale=0.5, max_scale=1.0)
ChatUniVi/model/multimodal_encoder/processor.py:17
Method__init__
(self, image_size=224, mean=None, std=None)
ChatUniVi/model/multimodal_encoder/processor.py:35
Method__init__
(self, image_size=224, mean=None, std=None)
ChatUniVi/model/multimodal_encoder/processor.py:53
Method__init__
(self, vision_tower, args, delay_load=False)
ChatUniVi/model/multimodal_encoder/eva_encoder.py:8
Method__init__
(self, vision_tower, args=None, delay_load=False)
ChatUniVi/model/multimodal_encoder/clip_encoder.py:8
Method__init__
(self, tokenizer: transformers.PreTrainedTokenizer, data_args: DataArguments)
ChatUniVi/train/train.py:755
Method__len__
(self)
ChatUniVi/train/train.py:781
Function_convert_weights_to_fp16
(l)
ChatUniVi/model/multimodal_encoder/eva_vit.py:406
Method_init_weights
(self, m)
ChatUniVi/model/cluster.py:265
Method_init_weights
(self, module: nn.Module)
ChatUniVi/model/language_model/language_model/modeling_phi.py:849
Method_init_weights
(self, m)
ChatUniVi/model/multimodal_encoder/eva_vit.py:313
Function_prepare_decoder_attention_mask
( self, attention_mask, input_shape, inputs_embeds, past_key_values_length )
ChatUniVi/train/llama_flash_attn_monkey_patch.py:107
Method_save_checkpoint
(self, model, trial, metrics=None)
ChatUniVi/train/trainer.py:28
Method_set_gradient_checkpointing
(self, module, value=False)
ChatUniVi/model/language_model/phi.py:56
← previousnext →101–200 of 291, ranked by callers