MCPcopy Create free account

hub / github.com/X-PLUG/mPLUG-Owl / functions

Functions946 in github.com/X-PLUG/mPLUG-Owl

⨍ Functions 946◇ Types & classes 168↳ Endpoints 11
↓ 2 callersMethodclose
Dummy method for compatibility.
mPLUG-Owl/serve/io_utils.py:376
↓ 2 callersMethodcreateIndex
(self)
mPLUG-Owl2/mplug_owl2/evaluate/vqa.py:55
↓ 2 callersMethodcreateIndex
(self)
mPLUG-Owl3/evaluation/vqa_utils/vqa.py:53
↓ 2 callersFunctioncreate_soft_link
(src, dst)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:147
↓ 2 callersMethoddecode
This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this
mPLUG-Owl/mplug_owl_video/processing_mplug_owl.py:91
↓ 2 callersFunctiondequantize_cache_torch
(qdata, scale, zero)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:140
↓ 2 callersMethodencode_images
(self, images)
mPLUG-Owl2/mplug_owl2/model/modeling_mplug_owl2.py:61
↓ 2 callersMethodevaluate
(self, quesIds=None)
mPLUG-Owl2/mplug_owl2/evaluate/vqa_eval.py:194
↓ 2 callersFunctionevaluate_exact_match_accuracy
(entries, post_process=False)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:151
↓ 2 callersFunctionevaluate_exact_match_accuracy
(entries)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:408
↓ 2 callersFunctionevaluate_in_match_accuracy
(entries, post_process=False)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:181
↓ 2 callersMethodexists
(self, path)
mPLUG-Owl/serve/io_utils.py:211
↓ 2 callersFunctionextract_answer
(model_output)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:343
↓ 2 callersFunctionextract_choice
(model_output: str)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:68
↓ 2 callersFunctionextract_choice
(model_output: str)
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:26
↓ 2 callersFunctionextract_choice
(model_output: str)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:324
↓ 2 callersMethodformat_question
(self, question, question_type, dataset)
mPLUG-Owl3/evaluation/tasks/task_define/llava_interleave_bench.py:71
↓ 2 callersMethodformat_question
(self, exampler)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:154
↓ 2 callersMethodgetQuesIds
Get question ids that satisfy given filter conditions. default skips that filter. :param imgIds (int array) : get question ids
mPLUG-Owl2/mplug_owl2/evaluate/vqa.py:81
↓ 2 callersMethodgetQuesIds
Get question ids that satisfy given filter conditions. default skips that filter :param imgIds (int array) : get question ids f
mPLUG-Owl3/evaluation/vqa_utils/vqa.py:79
↓ 2 callersFunctionget_2d_sincos_pos_embed
grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:34
↓ 2 callersFunctionget_conv_log_filename
()
mPLUG-Owl2/mplug_owl2/serve/gradio_web_server.py:32
↓ 2 callersFunctionget_conv_log_filename
()
mPLUG-Owl2/mplug_owl2/local_serve/local_web_server.py:26
↓ 2 callersFunctionget_file_extension
(filename)
mPLUG-Owl3/gradio_demo.py:70
↓ 2 callersFunctionget_frame_indices
(num_frames, vlen, sample='rand', fix_start=None, input_fps=1, max_num_frames=-1)
mPLUG-Owl3/evaluation/tasks/task_define/video_utils.py:17
↓ 2 callersMethodget_input_embeddings
(self)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:737
↓ 2 callersMethodget_input_embeddings
(self)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1230
↓ 2 callersMethodget_input_embeddings
(self)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1383
↓ 2 callersMethodget_input_embeddings
(self)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1282
↓ 2 callersFunctionget_media_indices
(my_list)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1317
↓ 2 callersFunctionget_media_indices
(my_list)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1234
↓ 2 callersFunctionget_media_types
(tensors, positions)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1328
↓ 2 callersMethodget_model
(self)
mPLUG-Owl2/mplug_owl2/model/modeling_mplug_owl2.py:230
↓ 2 callersFunctionget_model_list
()
mPLUG-Owl2/mplug_owl2/serve/gradio_web_server.py:38
↓ 2 callersMethodget_ntk_alpha
(self, true_seq_len)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:746
↓ 2 callersMethodget_queue_length
(self)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:108
↓ 2 callersMethodget_status
(self)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:115
↓ 2 callersMethodget_vqa_image_name
(self, image)
mPLUG-Owl3/evaluation/tasks/task_define/vqa.py:139
↓ 2 callersMethodget_worker_address
(self, model_name: str)
mPLUG-Owl2/mplug_owl2/serve/controller.py:120
↓ 2 callersMethodlistdir
(self, path, recursive=False, full_path=False, contains=None)
mPLUG-Owl/serve/io_utils.py:276
↓ 2 callersMethodloadRes
Load result file and return a result object. :param resFile (str) : file name of result file :return: res (obj) : resul
mPLUG-Owl2/mplug_owl2/evaluate/vqa.py:168
↓ 2 callersFunctionload_image_from_base64
(image)
mPLUG-Owl2/mplug_owl2/mm_utils.py:11
↓ 2 callersFunctionload_jsonl
(filename)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:219
↓ 2 callersMethodmd5
(self, path: str)
mPLUG-Owl/serve/io_utils.py:57
↓ 2 callersMethodmove
(self, src: str, dst: str)
mPLUG-Owl/serve/io_utils.py:30
↓ 2 callersFunctionmute_stderr
()
mPLUG-Owl/serve/io_utils.py:443
↓ 2 callersFunctionpost_process_output
(text)
mPLUG-Owl/serve/model_utils.py:12
↓ 2 callersMethodprepare_inputs_labels_for_multimodal
( self, input_ids, attention_mask, past_key_values, labels, images )
mPLUG-Owl2/mplug_owl2/model/modeling_mplug_owl2.py:66
↓ 2 callersMethodprocessPunctuation
(self, inText)
mPLUG-Owl2/mplug_owl2/evaluate/vqa_eval.py:254
↓ 2 callersMethodprocessPunctuation
(self, inText)
mPLUG-Owl3/evaluation/vqa_utils/vqa_eval.py:249
↓ 2 callersFunctionquantize_cache_v
(fdata, bits, qmax, qmin)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:118
↓ 2 callersFunctionrank0_print
(*args)
mPLUG-Owl2/mplug_owl2/train/train.py:44
↓ 2 callersMethodregister_to_controller
(self)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:75
↓ 2 callersMethodregister_worker
(self, worker_name: str, check_heart_beat: bool, worker_status: dict)
mPLUG-Owl2/mplug_owl2/serve/controller.py:69
↓ 2 callersMethodremove_worker
(self, worker_name: str)
mPLUG-Owl2/mplug_owl2/serve/controller.py:101
↓ 2 callersFunctionreplace_llama_modality_adaptive
()
mPLUG-Owl2/mplug_owl2/model/modeling_llama2.py:464
↓ 2 callersMethodsend_heart_beat
(self)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:87
↓ 2 callersFunctionshear_level_to_args
(MAX_LEVEL, replace_value)
mPLUG-Owl/pipeline/data_utils/randaugment.py:215
↓ 2 callersMethodstyle
This method can be used to change the appearance of the Chatbot component.
mPLUG-Owl/serve/gradio_patch.py:154
↓ 2 callersMethodto_causal_4d
Creates a causal 4D mask of (bsz, head_dim=1, query_length, key_value_length) shape and adds large negative bias to upper right hand
mPLUG-Owl2/mplug_owl2/model/modeling_attn_mask_utils.py:44
↓ 2 callersFunctiontrain
()
mPLUG-Owl2/mplug_owl2/train/train.py:635
↓ 2 callersFunctiontranslate_level_to_args
(translate_const, MAX_LEVEL, replace_value)
mPLUG-Owl/pipeline/data_utils/randaugment.py:224
↓ 2 callersFunctiontune_channel
(ch)
mPLUG-Owl/pipeline/data_utils/randaugment.py:17
↓ 2 callersFunctionviolates_moderation
Check whether the text violates OpenAI moderation API.
mPLUG-Owl2/mplug_owl2/utils.py:102
↓ 2 callersMethodwrite
(self, content)
mPLUG-Owl/serve/io_utils.py:352
↓ 1 callersMethod__init__
(self, config: LlamaConfig)
mPLUG-Owl2/mplug_owl2/model/modeling_llama2.py:36
↓ 1 callersMethod_add_children
Add children for a registry. The ``registry`` will be added as children based on its scope. The parent registry could build objects f
mPLUG-Owl3/evaluation/tasks/task_define/registry.py:321
↓ 1 callersMethod_add_children
Add children for a registry. The ``registry`` will be added as children based on its scope. The parent registry could build objects f
mPLUG-Owl/pipeline/data_utils/registry.py:321
↓ 1 callersFunction_add_speaker_and_signal
Add speaker and start/end signal on each round.
mPLUG-Owl2/mplug_owl2/train/train.py:255
↓ 1 callersMethod_attn
(self, query, key, value, causal_mask=None, attention_mask=None, head_mask=None)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:325
↓ 1 callersMethod_extract_text_token_from_conversation
(self, data, max_length, index)
mPLUG-Owl/pipeline/data_utils/xgpt3_dataset.py:129
↓ 1 callersMethod_file_exists
(self, bucket, path)
mPLUG-Owl/serve/io_utils.py:227
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mme.py:261
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmbench.py:155
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_vqa.py:119
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_mmmu.py:402
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
mPLUG-Owl2/mplug_owl2/evaluate/evaluate_caption.py:86
↓ 1 callersMethod_init_rope
(self)
mPLUG-Owl2/mplug_owl2/model/modeling_llama2.py:62
↓ 1 callersMethod_load_img
(self, images)
mPLUG-Owl/pipeline/data_utils/xgpt3_dataset.py:63
↓ 1 callersMethod_load_video
(self, video_url, num_frames=8)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:69
↓ 1 callersFunction_mask_targets
(target, tokenized_lens, speakers)
mPLUG-Owl2/mplug_owl2/train/train.py:244
↓ 1 callersMethod_merge_heads
(self, tensor, num_heads, attn_head_size)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:401
↓ 1 callersMethod_norm
(self, x)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:1309
↓ 1 callersMethod_preprocess_accelerate
r""" Some pre-processing hacks to make the model `accelerate` compatible. Check https://github.com/huggingface/transformers/pull/21707
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1406
↓ 1 callersMethod_preprocess_accelerate
r""" Some pre-processing hacks to make the model `accelerate` compatible. Check https://github.com/huggingface/transformers/pull/21707
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1305
↓ 1 callersMethod_process_chat_messages
( self, chat_message: str | Tuple | List | Dict | None )
mPLUG-Owl/serve/gradio_patch.py:98
↓ 1 callersMethod_rope_scaling_validation
Validate the `rope_scaling` configuration.
mPLUG-Owl2/mplug_owl2/model/configuration_mplug_owl2.py:152
↓ 1 callersFunction_rotate_half
(x)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:1271
↓ 1 callersMethod_save
(self, output_dir: Optional[str] = None, state_dict=None)
mPLUG-Owl2/mplug_owl2/train/mplug_owl2_trainer.py:242
↓ 1 callersFunction_tokenize_prompt
( prompt, tokenizer, add_BOS=False, media_info={"<image>": 65, "<|video|>": 65}, **kw
mPLUG-Owl/mplug_owl_video/processing_mplug_owl.py:221
↓ 1 callersFunction_tokenize_prompt
(prompt, tokenizer, add_BOS=False, media_info={"<image>": 65}, **kwargs)
mPLUG-Owl/mplug_owl/processing_mplug_owl.py:183
↓ 1 callersFunction_tokenize_prompts_and_batch
Given a set of prompts and number of tokens to generate: - tokenize prompts - set the sequence length to be the max of length of prompts
mPLUG-Owl/mplug_owl_video/processing_mplug_owl.py:179
↓ 1 callersFunction_tokenize_prompts_and_batch
Given a set of prompts and number of tokens to generate: - tokenize prompts - set the sequence length to be the max of length of prompts plus
mPLUG-Owl/mplug_owl/processing_mplug_owl.py:143
↓ 1 callersFunctionaccuracy_metric
(sample_list, preds)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:94
↓ 1 callersMethodbatch_decode
This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of
mPLUG-Owl/mplug_owl/processing_mplug_owl.py:53
↓ 1 callersFunctionbuild_demo
(embed_mode)
mPLUG-Owl2/mplug_owl2/serve/gradio_web_server.py:298
↓ 1 callersFunctionbuild_demo
(embed_mode)
mPLUG-Owl2/mplug_owl2/local_serve/local_web_server.py:246
↓ 1 callersFunctionbuild_demo
()
mPLUG-Owl/serve/web_server.py:271
↓ 1 callersFunctionbuild_evaluation_from_jsonl
(task_path)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:203
↓ 1 callersFunctionbuild_evaluation_from_yaml
(task_paths)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:210
← previousnext →101–200 of 946, ranked by callers