MCPcopy Create free account

hub / github.com/Fr0zenCrane/Cockatiel / functions

Functions1,946 in github.com/Fr0zenCrane/Cockatiel

⨍ Functions 1,946◇ Types & classes 311↳ Endpoints 7
↓ 1 callersMethodload_model
(self)
llava/model/multimodal_encoder/radio_encoder.py:116
↓ 1 callersMethodload_model
(self)
llava/model/multimodal_encoder/radio_torchhub_encoder.py:159
↓ 1 callersMethodload_pretrained
(cls, model_path_or_config, *args, **kwargs)
llava/model/llava_arch.py:93
↓ 1 callersFunctionload_results
(results_dir)
llava/eval/vision_niah_vila/eval_vision_niah.py:185
↓ 1 callersFunctionload_stopwords_file
(filename)
llava/eval/video/eval_video_nextqa.py:20
↓ 1 callersFunctionload_tarfile
(tar_path)
llava/data/simple_vila_webdataset.py:42
↓ 1 callersFunctionload_tarfile
(tar_path)
llava/data/vila_webdataset.py:24
↓ 1 callersFunctionload_tarfile
(tar_path)
llava/data/simple_video_dataset.py:43
↓ 1 callersFunctionload_video
(video_path, max_frames_num)
distributed_cockatiel_vidcap.py:175
↓ 1 callersFunctionload_video
(video_path, max_frames_num)
distributed_cockatiel_scoring.py:108
↓ 1 callersFunctionload_video
(video_path, jinfo, idx=0, num_video_frames=8, image_size=334)
llava/data/dataset_impl/panda70m.py:76
↓ 1 callersFunctionload_video_batches
(video_path, batch_size)
llava/eval/vision_niah_vila/produce_haystack_embedding.py:32
↓ 1 callersMethodloss
( self, advantages: torch.Tensor, clip_range: float, ratio: torch.Tensor,
llava/trl/trainer/ddpo_trainer.py:407
↓ 1 callersMethodloss
Calculate policy and value losses. Args: old_logprobs (`torch.FloatTensor`): Log probabilities of the mo
llava/trl/trainer/ppo_trainer.py:1159
↓ 1 callersFunctionmain
(args)
distributed_cockatiel_vidcap.py:188
↓ 1 callersFunctionmain
(args)
distributed_cockatiel_scoring.py:121
↓ 1 callersFunctionmain
()
llava/utils/merge_lora_weights_and_save_hf_model.py:62
↓ 1 callersFunctionmain
Computes the RankMe (http://arxiv.org/abs/2210.02885) and LiDAR (http://arxiv.org/abs/2312.04000) estimates of the rank of the produced embed
llava/model/multimodal_encoder/visualize_features.py:42
↓ 1 callersFunctionmain
()
llava/cli/run.py:7
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_loader.py:16
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_mmmu.py:45
↓ 1 callersFunctionmain
()
llava/eval/evaluate_vqa.py:16
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_mmmu_sharded.py:86
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_ego_schema.py:16
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_science.py:16
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_mathvista.py:16
↓ 1 callersFunctionmain
()
llava/eval/model_vqa_cinepile.py:32
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_video_nextqa.py:115
↓ 1 callersFunctionmain
()
llava/eval/video/eval_GPT4o.py:185
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_benchmark_3_context.py:95
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_benchmark_4_temporal.py:93
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_video_qa.py:93
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_benchmark_5_consistency.py:99
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_benchmark_2_detailed_orientation.py:94
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_video_perception.py:16
↓ 1 callersFunctionmain
Main function to control the flow of the program.
llava/eval/video/eval_benchmark_1_correctness.py:94
↓ 1 callersFunctionmain
(args)
llava/eval/vision_niah_vila/eval_vision_niah.py:382
↓ 1 callersFunctionmain
(args)
llava/eval/vision_niah_vila/produce_haystack_embedding.py:44
↓ 1 callersFunctionmain
(args)
llava/eval/vision_niah_vila/produce_needle_embedding.py:34
↓ 1 callersFunctionmain
Commands for manipulating the shard index.
llava/wids/wids_index.py:267
↓ 1 callersFunctionmain
(input_json, output_json, split)
scripts/convert_karpathy_to_anno.py:51
↓ 1 callersFunctionmain
(model_name)
scripts/v1_5/eval/copy_predictions.py:22
↓ 1 callersFunctionmain
(args)
scripts/v1_5/eval/convert_pred_to_csv.py:23
↓ 1 callersFunctionmain_wds
(args)
llava/wids/wids_bench.py:18
↓ 1 callersFunctionmain_wids
(args)
llava/wids/wids_bench.py:8
↓ 1 callersFunctionmake_delta
(base_model_path, target_model_path, delta_path, hub_repo_id)
llava/model/make_delta.py:32
↓ 1 callersFunctionmake_supervised_data_module
Make dataset and collator for supervised fine-tuning. This function is originally implemented by the LLaVA team and modified by Jason Lu, Haot
llava/data/dataset.py:2370
↓ 1 callersFunctionmaybe_read
(x)
llava/wids/wids_index.py:239
↓ 1 callersMethodnames
(self)
llava/wids/wids_tar.py:66
↓ 1 callersFunctionndgrid
generate N-D grid in dimension order. The ndgrid function is like meshgrid except that the order of the first two input arguments are switched.
llava/model/multimodal_encoder/intern/modeling_intern_vit.py:49
↓ 1 callersFunctionneed_to_modify_do_sample
(generation_config)
llava/train/train.py:519
↓ 1 callersFunctionnext_header
(offset, header)
llava/wids/wids_mmtar.py:36
↓ 1 callersFunctionnormalize_extracted_answer
Normalize the extracted answer to match the answer type
llava/eval/mathvista_utils/calculate_score.py:23
↓ 1 callersMethodnum_parameters
Get number of (optionally, trainable or non-embeddings) parameters in the module. Args: only_trainable (`bool`, *optiona
llava/train/transformers_replace/modeling_utils.py:1005
↓ 1 callersMethodpad_image
Pad an image to `(pad_size["height"], pad_size["width"])` to the right and bottom. Args: image (`np.ndarray`):
llava/model/multimodal_encoder/image_processor.py:181
↓ 1 callersFunctionparse_args
()
llava/eval/summarize_gpt_review.py:11
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_video_nextqa.py:105
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_GPT4o.py:12
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_benchmark_3_context.py:16
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_benchmark_4_temporal.py:15
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_video_qa.py:14
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_benchmark_5_consistency.py:15
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_benchmark_2_detailed_orientation.py:15
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_video_perception.py:8
↓ 1 callersFunctionparse_args
()
llava/eval/video/eval_benchmark_1_correctness.py:15
↓ 1 callersFunctionparse_args
()
scripts/convert_vizwiz_for_submission.py:24
↓ 1 callersFunctionparse_args
()
scripts/extract_mm_projector.py:25
↓ 1 callersFunctionparse_args
()
scripts/convert_vqav2_for_submission.py:24
↓ 1 callersFunctionparse_caption_template
(template_type)
llava/eval/model_vqa_videodemo.py:121
↓ 1 callersFunctionparse_config
()
llava/utils/merge_lora_weights_and_save_hf_model.py:27
↓ 1 callersFunctionparse_model_name_or_path
(config: PretrainedConfig, model_name="llm", suffix="_cfg")
llava/model/builder.py:202
↓ 1 callersFunctionparse_open_response
Parse the prediction from the generated response. Return a list of predicted strings or numbers.
llava/eval/mmmu_utils/eval_utils.py:129
↓ 1 callersFunctionparse_score
(review)
llava/eval/eval_gpt_review_bench.py:42
↓ 1 callersFunctionparse_score
(review)
llava/eval/eval_gpt_review.py:45
↓ 1 callersFunctionparse_score
(review)
llava/eval/eval_gpt_review_visual.py:41
↓ 1 callersMethodparse_tool_call
Parse request string. Expected format: <request><tool_name>query<call>
llava/trl/environment/base_environment.py:332
↓ 1 callersFunctionpatch_tensor_constructor
(fn)
llava/model/language_model/mpt/meta_init_context.py:99
↓ 1 callersFunctionpeft_module_casting_to_bf16
(model)
llava/trl/trainer/utils.py:651
↓ 1 callersFunctionpil2vertexIMG
(pil_imgs)
llava/3rd_party/gemini_video.py:77
↓ 1 callersFunctionpipeline_step
r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*): The prompt or prompts to guide t
llava/trl/models/modeling_sd_base.py:322
↓ 1 callersFunctionprepare_config_for_training
( config: PretrainedConfig, model_args: dataclass, training_args: dataclass, data_args: dataclass )
llava/train/utils.py:81
↓ 1 callersMethodprepare_dataloader
Prepare the dataloader for training. Args: dataset (Union[`torch.utils.data.Dataset`, `datasets.Dataset`]):
llava/trl/trainer/ppo_trainer.py:375
↓ 1 callersMethodprepare_model_inputs
(self, input_ids: torch.Tensor, attention_mask: torch.Tensor, labels: torch.Tensor)
llava/trl/trainer/iterative_sft_trainer.py:143
↓ 1 callersMethodprepare_model_inputs
(self, queries: torch.Tensor, responses: torch.Tensor)
llava/trl/trainer/ppo_trainer.py:919
↓ 1 callersFunctionprepare_wids_meta
(data_path, cache_dir="~/datasets/vila-webds-meta-2", idx=0, total=0)
llava/data/simple_vila_webdataset.py:159
↓ 1 callersFunctionprepare_wids_meta
(data_path, cache_dir="~/datasets/vila-webds-meta", overwrite=False)
llava/data/vila_webdataset.py:89
↓ 1 callersFunctionprepare_zigzag_ring_attn_inputs
(input_ids, position_ids, target_ids, rank, world_size, device)
llava/eval/vision_niah_vila/zigzag_ring_attn/prepare_inputs.py:27
↓ 1 callersFunctionpreprocess_conversation
( conversation: Sequence[Dict[str, str]], tokenizer: transformers.PreTrainedTokenizer, no_system_p
llava/utils/tokenizer.py:116
↓ 1 callersFunctionpreprocess_plain
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer, )
llava/data/dataset.py:98
↓ 1 callersFunctionprint_long_info
(data, filename)
llava/wids/wids_index.py:190
↓ 1 callersFunctionprocess_caption
(msg, task)
llava/data_aug/caption2qa.py:49
↓ 1 callersMethodprocess_digit_article
(self, in_text)
llava/eval/m4c_evaluator.py:196
↓ 1 callersMethodprocess_punctuation
(self, in_text)
llava/eval/m4c_evaluator.py:186
↓ 1 callersFunctionprocess_video
(video_path, seconds_per_frame=1, max_num_frames=20)
llava/eval/video/eval_GPT4o.py:32
↓ 1 callersFunctionprompt_processor
(prompt)
llava/eval/eval_textvqa.py:19
↓ 1 callersMethodprune_heads
Prunes heads of the base model. Arguments: heads_to_prune (`Dict[int, List[int]]`): Dictionary with keys
llava/train/transformers_replace/modeling_utils.py:1998
↓ 1 callersMethodpush_to_hub
(self, *args, **kwargs)
llava/trl/models/modeling_value_head.py:220
↓ 1 callersFunctionrandn_tensor
A helper function to create random tensors on the desired `device` with the desired `dtype`. When passing a list of generators, you can seed each
llava/trl/core.py:296
↓ 1 callersFunctionrank
()
llava/utils/distributed.py:25
↓ 1 callersFunctionrank_print
(*s)
llava/train/callbacks/autoresume_callback.py:17
← previousnext →701–800 of 1,946, ranked by callers