MCPcopy Create free account

hub / github.com/PKU-YuanGroup/Video-LLaVA / functions

Functions670 in github.com/PKU-YuanGroup/Video-LLaVA

⨍ Functions 670◇ Types & classes 125↳ Endpoints 14
↓ 2 callersFunctiongetRegion
(sceneGraph, objectId)
videollava/eval/eval_gqa.py:318
↓ 2 callersFunctionget_pred_idx
Get the index (e.g. 2) from the prediction (e.g. 'C')
videollava/eval/eval_science_qa_gpt4.py:28
↓ 2 callersFunctionget_pred_idx
Get the index (e.g. 2) from the prediction (e.g. 'C')
videollava/eval/eval_science_qa.py:28
↓ 2 callersMethodget_queue_length
(self)
videollava/serve/model_worker.py:108
↓ 2 callersMethodget_status
(self)
videollava/serve/model_worker.py:115
↓ 2 callersMethodget_worker_address
(self, model_name: str)
videollava/serve/controller.py:120
↓ 2 callersFunctionintersection
(r1, r2)
videollava/eval/eval_gqa.py:296
↓ 2 callersFunctionis_none
(value)
videollava/eval/model_vqa_mmbench.py:33
↓ 2 callersFunctionload_image_from_base64
(image)
videollava/mm_utils.py:10
↓ 2 callersFunctionneed_more_runs
()
scripts/eval_gpt_mmvet.py:136
↓ 2 callersFunctionneed_more_runs
()
videollava/eval/eval_gpt_mmvet.py:136
↓ 2 callersMethodprepare_inputs_labels_for_multimodal
( self, input_ids, position_ids, attention_mask, past_key_values, labels, images )
videollava/model/llava_arch.py:148
↓ 2 callersFunctionrank0_print
(*args)
videollava/train/train.py:46
↓ 2 callersMethodregister_to_controller
(self)
videollava/serve/model_worker.py:75
↓ 2 callersMethodregister_worker
(self, worker_name: str, check_heart_beat: bool, worker_status: dict)
videollava/serve/controller.py:69
↓ 2 callersMethodremove_worker
(self, worker_name: str)
videollava/serve/controller.py:101
↓ 2 callersFunctionrms_norm
(x, weight=None, eps=1e-05)
videollava/model/language_model/mpt/norm.py:27
↓ 2 callersMethodsend_heart_beat
(self)
videollava/serve/model_worker.py:87
↓ 2 callersFunctionswitchQuestionAndCategory
()
videollava/eval/webpage/script.js:203
↓ 2 callersFunctionupdateExpandButtonVisibility
(card)
videollava/eval/webpage/script.js:226
↓ 2 callersFunctionupdateModelSelect
()
videollava/eval/webpage/script.js:64
↓ 1 callersMethod__call__
(self, images=None, text=None, context_length=77, return_tensors=None, **kwargs)
videollava/model/multimodal_encoder/languagebind/image/processing_image.py:46
↓ 1 callersMethod__call__
(self, images=None, text=None, context_length=77, return_tensors=None, **kwargs)
videollava/model/multimodal_encoder/languagebind/video/processing_video.py:127
↓ 1 callersMethod__init__
(self, config: LlamaConfig)
videollava/model/language_model/llava_llama.py:36
↓ 1 callersMethod__init__
(self, config: MPTConfig)
videollava/model/language_model/llava_mpt.py:37
↓ 1 callersMethod__init__
(self, d_model: int, expansion_ratio: int, device: Optional[str]=None)
videollava/model/language_model/mpt/blocks.py:10
↓ 1 callersMethod__init__
(self, config: MPTConfig)
videollava/model/language_model/mpt/modeling_mpt.py:35
↓ 1 callersMethod__init__
(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False,
videollava/model/language_model/mpt/attention.py:158
↓ 1 callersMethod__init__
(self)
videollava/model/multimodal_projector/builder.py:7
↓ 1 callersMethod__init__
(self, config)
videollava/model/multimodal_encoder/languagebind/audio/processing_audio.py:32
↓ 1 callersMethod__init__
( self, max_depth=0, min_depth=0.01, )
videollava/model/multimodal_encoder/languagebind/depth/processing_depth.py:22
↓ 1 callersMethod__len__
(self)
videollava/train/train.py:693
↓ 1 callersFunction_add_speaker_and_signal
Add speaker and start/end signal on each round.
videollava/train/train.py:294
↓ 1 callersMethod_apply_prefix_mask
(self, attn_bias: torch.Tensor, prefix_mask: torch.Tensor)
videollava/model/language_model/mpt/modeling_mpt.py:119
↓ 1 callersMethod_apply_sequence_id
(self, attn_bias: torch.Tensor, sequence_id: torch.LongTensor)
videollava/model/language_model/mpt/modeling_mpt.py:134
↓ 1 callersMethod_attn_bias
(self, device, dtype, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]
videollava/model/language_model/mpt/modeling_mpt.py:88
↓ 1 callersMethod_compute_answer_scores
compute the accuracy (soft score) of human answers
videollava/eval/m4c_evaluator.py:225
↓ 1 callersFunction_convert_bloom_causal_lm_to_prefix_lm
Converts a BLOOM Causal LM to a Prefix LM. Supported HuggingFace model classes: - `BloomForCausalLM` See `convert_hf_causal_lm_to_pr
videollava/model/language_model/mpt/hf_prefixlm_converter.py:113
↓ 1 callersFunction_convert_gpt_causal_lm_to_prefix_lm
Converts a GPT-style Causal LM to a Prefix LM. Supported HuggingFace model classes: - `GPT2LMHeadModel` - `GPTNeoForCausalLM`
videollava/model/language_model/mpt/hf_prefixlm_converter.py:29
↓ 1 callersFunction_convert_opt_causal_lm_to_prefix_lm
Converts an OPT Causal LM to a Prefix LM. Supported HuggingFace model classes: - `OPTForCausalLM` See `convert_hf_causal_lm_to_prefi
videollava/model/language_model/mpt/hf_prefixlm_converter.py:269
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
videollava/model/multimodal_encoder/languagebind/image/modeling_image.py:441
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
videollava/model/multimodal_encoder/languagebind/audio/modeling_audio.py:441
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
videollava/model/multimodal_encoder/languagebind/depth/modeling_depth.py:441
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
videollava/model/multimodal_encoder/languagebind/thermal/modeling_thermal.py:441
↓ 1 callersFunction_make_causal_mask
Make causal mask used for bi-directional self-attention.
videollava/model/multimodal_encoder/languagebind/video/modeling_video.py:441
↓ 1 callersFunction_mask_targets
(target, tokenized_lens, speakers)
videollava/train/train.py:283
↓ 1 callersFunction_normal_init_
(std, mean=0.0)
videollava/model/language_model/mpt/param_init_fns.py:121
↓ 1 callersMethod_save
(self, output_dir: Optional[str] = None, state_dict=None)
videollava/train/llava_trainer.py:260
↓ 1 callersFunctionadapt_tokenizer_for_denoising
Adds sentinel tokens and padding token (if missing). Expands the tokenizer vocabulary to include sentinel tokens used in mixture-of-denoiser
videollava/model/language_model/mpt/adapt_tokenizer.py:6
↓ 1 callersFunctionapply_delta
(base_model_path, target_model_path, delta_path)
videollava/model/apply_delta.py:13
↓ 1 callersFunctionattn_bias_shape
(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal, use_sequence_id)
videollava/model/language_model/mpt/attention.py:258
↓ 1 callersFunctionbatch_infer
(model, tokenizer, prompts)
videollava/eval/eval_mmlu.py:185
↓ 1 callersFunctionbatch_split
(prompts, batch_num)
videollava/eval/eval_mmlu.py:172
↓ 1 callersFunctionbuild_alibi_bias
(n_heads, seq_len, full=False, alibi_bias_max=8, device=None, dtype=None)
videollava/model/language_model/mpt/attention.py:292
↓ 1 callersFunctionbuild_attn_bias
(attn_impl, attn_bias, n_heads, seq_len, causal=False, alibi=False, alibi_bias_max=8)
videollava/model/language_model/mpt/attention.py:272
↓ 1 callersMethodcall_for_batch
(self, output_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)
videollava/mm_utils.py:88
↓ 1 callersFunctioncapitalizeFirstChar
(str)
videollava/eval/webpage/script.js:41
↓ 1 callersFunctionchiSquare
(goldDist, predictedDist)
videollava/eval/eval_gqa.py:359
↓ 1 callersFunctioncomputeGroundingScore
(question, sceneGraph, attentionMap)
videollava/eval/eval_gqa.py:329
↓ 1 callersFunctioncompute_metric
(output_filename)
videollava/eval/eval_mmlu.py:75
↓ 1 callersFunctionconsolidate_ckpt
(src_path, dst_path)
videollava/model/consolidate.py:13
↓ 1 callersMethodconvert_to_lora
(self)
videollava/model/multimodal_encoder/languagebind/image/modeling_image.py:775
↓ 1 callersMethodconvert_to_lora
(self)
videollava/model/multimodal_encoder/languagebind/audio/modeling_audio.py:775
↓ 1 callersMethodconvert_to_lora
(self)
videollava/model/multimodal_encoder/languagebind/depth/modeling_depth.py:775
↓ 1 callersMethodconvert_to_lora
(self)
videollava/model/multimodal_encoder/languagebind/thermal/modeling_thermal.py:775
↓ 1 callersFunctioncreate_data_loader
(questions, image_folder, tokenizer, image_processor, model_config, batch_size=1, num_workers=4)
videollava/eval/model_vqa_loader.py:65
↓ 1 callersFunctioncreate_one_example_chatbot
(format, question, context, choice, answer, lecture, solution, test_example=True)
scripts/convert_sqa_to_llava_base_prompt.py:41
↓ 1 callersMethoddevice
(self)
videollava/model/multimodal_encoder/clip_encoder.py:62
↓ 1 callersMethodencode_images
(self, images)
videollava/model/llava_arch.py:137
↓ 1 callersMethodencode_videos
(self, videos)
videollava/model/llava_arch.py:142
↓ 1 callersFunctioneval_model
(args)
videollava/eval/model_vqa_loader.py:72
↓ 1 callersFunctioneval_model
(args)
videollava/eval/model_vqa_mmbench.py:54
↓ 1 callersFunctioneval_model
(args)
videollava/eval/model_vqa_qbench.py:28
↓ 1 callersFunctioneval_model
(args)
videollava/eval/model_vqa_science.py:29
↓ 1 callersFunctioneval_model
(model_name, questions_file, answers_file)
videollava/eval/model_qa.py:33
↓ 1 callersFunctioneval_model
(args)
videollava/eval/run_llava.py:51
↓ 1 callersFunctioneval_model
(args)
videollava/eval/model_vqa.py:29
↓ 1 callersFunctioneval_pope
(answers, label_file)
videollava/eval/eval_pope.py:5
↓ 1 callersMethodeval_pred_list
(self, pred_list)
videollava/eval/m4c_evaluator.py:248
↓ 1 callersFunctionfind_all_linear_names
(model)
videollava/train/train.py:176
↓ 1 callersFunctionformat_subject
(subject)
videollava/eval/eval_mmlu.py:92
↓ 1 callersMethodfrom_str
(cls, name)
videollava/serve/controller.py:33
↓ 1 callersFunctionfused_init_helper_
(module: nn.Module, init_fn_)
videollava/model/language_model/mpt/param_init_fns.py:17
↓ 1 callersFunctiongen_prompt
(train_df, subject, k=-1)
videollava/eval/eval_mmlu.py:111
↓ 1 callersFunctiongen_slopes
(n_heads, alibi_bias_max=8, device=None)
videollava/model/language_model/mpt/attention.py:283
↓ 1 callersMethodgenerate_stream
(self, params)
videollava/serve/model_worker.py:123
↓ 1 callersMethodgenerate_stream_gate
(self, params)
videollava/serve/model_worker.py:194
↓ 1 callersFunctiongetCell
(i, j)
videollava/eval/eval_gqa.py:312
↓ 1 callersFunctiongetStepsNum
(question)
videollava/eval/eval_gqa.py:220
↓ 1 callersFunctiongetWordsNum
(question)
videollava/eval/eval_gqa.py:215
↓ 1 callersMethodget_anls
(self, s1, s2)
videollava/eval/m4c_evaluator.py:282
↓ 1 callersFunctionget_args
()
scripts/convert_mmbench_for_submission.py:6
↓ 1 callersFunctionget_args
()
scripts/convert_seed_for_submission.py:6
↓ 1 callersFunctionget_args
()
videollava/eval/eval_textvqa.py:9
↓ 1 callersFunctionget_args
()
videollava/eval/eval_science_qa_gpt4.py:9
↓ 1 callersFunctionget_args
()
videollava/eval/eval_science_qa.py:8
↓ 1 callersFunctionget_args
()
videollava/eval/eval_science_qa_gpt4_requery.py:9
↓ 1 callersFunctionget_audio_transform
(config)
videollava/model/multimodal_encoder/languagebind/audio/processing_audio.py:132
↓ 1 callersFunctionget_chunk
(lst, n, k)
videollava/eval/model_vqa_loader.py:25
↓ 1 callersFunctionget_chunk
(lst, n, k)
videollava/eval/model_vqa_mmbench.py:28
← previousnext →101–200 of 670, ranked by callers