Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/X-PLUG/mPLUG-Owl
/ functions
Functions
946 in github.com/X-PLUG/mPLUG-Owl
⨍
Functions
946
◇
Types & classes
168
↳
Endpoints
11
Function
downvote_last_response
(state, model_selector, request: gr.Request)
mPLUG-Owl2/mplug_owl2/serve/gradio_web_server.py:101
Function
downvote_last_response
(state, request: gr.Request)
mPLUG-Owl2/mplug_owl2/local_serve/local_web_server.py:64
Function
downvote_last_response
(state, model_selector, request: gr.Request)
mPLUG-Owl/serve/serve_utils.py:51
Method
encode_images
(self, images)
mPLUG-Owl2/mplug_owl2/model/modeling_mplug_owl2.py:225
Function
equalize_func
same output as PIL.ImageOps.equalize PIL's implementation is different from cv2.equalize
mPLUG-Owl/pipeline/data_utils/randaugment.py:44
Function
evaluate
Batch evaluation for multiple choice and open questions.
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:388
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/llava_interleave_bench.py:229
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:229
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:291
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:360
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:401
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/mmbench.py:453
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/mvbench.py:97
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/base.py:127
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/qbench.py:150
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:83
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:249
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:382
Method
evaluate
(self, merged_outputs, results_file=None, submission_file=None)
mPLUG-Owl3/evaluation/tasks/task_define/next_qa.py:557
Method
exists
(self, path)
mPLUG-Owl/serve/io_utils.py:84
Method
expand2square
(pil_img, background_color=(122, 116, 104))
mPLUG-Owl2/mplug_owl2/conversation.py:132
Method
expand2square
(pil_img, background_color)
mPLUG-Owl2/mplug_owl2/train/train.py:549
Function
fewshot_add_demonstration
(_image, _user_message, _assistant_message, _chat_bot, _app_cfg)
mPLUG-Owl3/gradio_demo.py:305
Function
flag_last_response
(state, model_selector, request: gr.Request)
mPLUG-Owl2/mplug_owl2/serve/gradio_web_server.py:107
Function
flag_last_response
(state, request: gr.Request)
mPLUG-Owl2/mplug_owl2/local_serve/local_web_server.py:70
Function
flag_last_response
(state, model_selector, request: gr.Request)
mPLUG-Owl/serve/serve_utils.py:55
Function
flushed
()
mPLUG-Owl3/gradio_demo.py:409
Function
forward
( self, hidden_states: torch.Tensor, modality_indicators: torch.Tensor, attention_mask: Option
mPLUG-Owl2/mplug_owl2/train/llama_flash_attn_monkey_patch.py:16
Method
forward
( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N
mPLUG-Owl2/mplug_owl2/model/modeling_mplug_owl2.py:233
Method
forward
( self, input_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[Tuple[
mPLUG-Owl2/mplug_owl2/model/modeling_mplug_owl2.py:377
Method
forward
(self, q, k, v, attention_mask=None)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:177
Method
forward
( self, hidden_states: Optional[Tuple[torch.FloatTensor]], modality_indicators=None,
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:406
Method
forward
(self, hidden_states)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:576
Method
forward
( self, hidden_states: Optional[Tuple[torch.FloatTensor]], modality_indicators=None,
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:602
Method
forward
( self, input_ids: Optional[torch.LongTensor] = None, modality_indicators = None,
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:752
Method
forward
( self, input_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[Tuple[
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:1036
Method
forward
(self, max_seq_len, ntk_alpha=1.0)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:1265
Method
forward
(self, x)
mPLUG-Owl2/mplug_owl2/model/modeling_qwen.py:1312
Method
forward
(self, pixel_values: torch.FloatTensor)
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:113
Method
forward
Input shape: Batch x Time x Channel
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:152
Method
forward
(self, hidden_states: torch.Tensor)
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:246
Method
forward
Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:262
Method
forward
r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Embedded rep
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:317
Method
forward
r""" Returns:
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:411
Method
forward
(self, hidden_states: torch.Tensor)
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:474
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:537
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:607
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = Non
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:650
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:691
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:725
Method
forward
r""" encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of h
mPLUG-Owl2/mplug_owl2/model/visual_encoder.py:844
Method
forward
(self, hidden_states, multiway_indices)
mPLUG-Owl2/mplug_owl2/model/multiway.py:14
Method
forward
( self, hidden_states: torch.Tensor, modality_indicators: torch.Tensor, attent
mPLUG-Owl2/mplug_owl2/model/modeling_llama2.py:92
Method
forward
Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (
mPLUG-Owl2/mplug_owl2/model/modeling_llama2.py:183
Method
forward
(self, pixel_values: torch.FloatTensor)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:145
Method
forward
(self, x: torch.Tensor)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:168
Method
forward
(self, x: torch.Tensor)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:180
Method
forward
(self, x)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:204
Method
forward
Input shape: Batch x Time x Channel
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:248
Method
forward
(self, hidden_states: torch.Tensor)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:336
Method
forward
Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, time, seq_len, embed_dim)` attention_
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:353
Method
forward
r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Embedded rep
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:578
Method
forward
r""" Returns:
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:671
Method
forward
(self, hidden_states: torch.Tensor)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:737
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:782
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:849
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = Non
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:882
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:923
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:957
Method
forward
r""" encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of h
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1076
Method
forward
r""" Returns: Examples: Image captioning (without providing a text prompt): ```python >>> from PIL import I
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1430
Method
forward
(self, pixel_values: torch.FloatTensor)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:139
Method
forward
(self, x: torch.Tensor)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:157
Method
forward
Input shape: Batch x Time x Channel
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:191
Method
forward
(self, x: torch.Tensor)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:272
Method
forward
(self, hidden_states: torch.Tensor)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:284
Method
forward
Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:300
Method
forward
r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Embedded rep
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:519
Method
forward
r""" Returns:
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:612
Method
forward
(self, hidden_states: torch.Tensor)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:673
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:718
Method
forward
(self, hidden_states: torch.Tensor, input_tensor: torch.Tensor)
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:785
Method
forward
( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.FloatTensor] = Non
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:818
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:859
Method
forward
( self, hidden_states, attention_mask=None, head_mask=None, encoder_hi
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:893
Method
forward
r""" encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, `optional`): Sequence of h
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1011
Method
forward
r""" Returns: SFT example: ```python >>> from PIL import Image >>> import requests >>> from transfor
mPLUG-Owl/mplug_owl/modeling_mplug_owl.py:1329
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
mPLUG-Owl2/mplug_owl2/model/configuration_mplug_owl2.py:305
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
mPLUG-Owl/mplug_owl_video/configuration_mplug_owl.py:110
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
mPLUG-Owl/mplug_owl_video/configuration_mplug_owl.py:152
Method
from_pretrained
(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs)
mPLUG-Owl/mplug_owl/configuration_mplug_owl.py:153
Method
from_vision_visual_abstractor_text_configs
r""" Instantiate a [`MplugOwlConfig`] (or a derived class) from a mPLUG-Owl vision model, Q-Former and language model configurations.
mPLUG-Owl/mplug_owl_video/configuration_mplug_owl.py:262
Method
from_vision_visual_abstractor_text_configs
r""" Instantiate a [`MplugOwlConfig`] (or a derived class) from a mPLUG-Owl vision model, Q-Former and language model configurations.
mPLUG-Owl/mplug_owl/configuration_mplug_owl.py:264
Method
generate
Overrides `generate` function to be able to use the model as a conditional generator. Args: pixel_values (`torch.FloatTe
mPLUG-Owl/mplug_owl_video/modeling_mplug_owl.py:1624
Function
generate_stream
(request: Request)
mPLUG-Owl2/mplug_owl2/serve/model_worker.py:227
Method
generate_with_callback
(callback=None, **kwargs)
mPLUG-Owl/serve/model_worker.py:103
Method
generate_with_streaming
(**kwargs)
mPLUG-Owl/serve/model_worker.py:111
Method
gentask
()
mPLUG-Owl/serve/model_utils.py:62
Method
getImgIds
Get image ids that satisfy given filter conditions. default skips that filter. :param quesIds (int array) : get image ids for gi
mPLUG-Owl2/mplug_owl2/evaluate/vqa.py:114
Method
getImgIds
Get image ids that satisfy given filter conditions. default skips that filter :param quesIds (int array) : get image ids for gi
mPLUG-Owl3/evaluation/vqa_utils/vqa.py:114
← previous
next →
701–800 of 946, ranked by callers