MCPcopy Create free account

hub / github.com/LLaVA-Annonymous/LLaVA / functions

Functions275 in github.com/LLaVA-Annonymous/LLaVA

⨍ Functions 275◇ Types & classes 38↳ Endpoints 9
Methodexpand2square
(pil_img, background_color=(122, 116, 104))
llava/conversation.py:75
Methodexpand2square
(pil_img, background_color)
llava/train/train.py:446
Functionflag_last_response
(state, model_selector, request: gr.Request)
llava/serve/gradio_web_server.py:119
Functionflash_attn_fn
(query, key, value, n_heads, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropo
llava/model/mpt/attention.py:61
Functionforward
Wraps original forward to enable PrefixLM attention.
llava/model/mpt/hf_prefixlm_converter.py:71
Functionforward
Input shape: Batch x Time x Channel attention_mask: [bsz, q_len]
llava/train/llama_flash_attn_monkey_patch.py:15
Methodforward
( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N
llava/model/llava.py:88
Methodforward
( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = N
llava/model/llava.py:203
Methodforward
(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_
llava/model/llava_mpt.py:92
Methodforward
(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_
llava/model/llava_mpt.py:200
Methodforward
(self, x)
llava/model/mpt/blocks.py:17
Methodforward
(self, x: torch.Tensor, past_key_value: Optional[Tuple[torch.Tensor]]=None, attn_bias: Optional[torch.Tensor]=
llava/model/mpt/blocks.py:34
Methodforward
(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_
llava/model/mpt/modeling_mpt.py:134
Methodforward
(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_
llava/model/mpt/modeling_mpt.py:255
Methodforward
(self, x)
llava/model/mpt/norm.py:19
Methodforward
(self, x)
llava/model/mpt/norm.py:43
Methodforward
(self, x)
llava/model/mpt/norm.py:51
Methodforward
(self, x, past_key_value=None, attn_bias=None, attention_mask=None, is_causal=True, needs_weights=False)
llava/model/mpt/attention.py:154
Methodforward
(self, x, past_key_value=None, attn_bias=None, attention_mask=None, is_causal=True, needs_weights=False)
llava/model/mpt/attention.py:214
Methodfsdp_wrap_fn
(self, module)
llava/model/mpt/modeling_mpt.py:214
Methodfsdp_wrap_fn
(self, module)
llava/model/mpt/modeling_mpt.py:275
Functiongenerate
Wraps original generate to enable PrefixLM attention.
llava/model/mpt/hf_prefixlm_converter.py:99
Functiongenerate_stream
(request: Request)
llava/serve/model_worker.py:334
Functionget_answer
(question_id: int, question: str, max_tokens: int)
llava/eval/qa_baseline_gpt35.py:16
Methodget_config
(self)
llava/serve/gradio_patch.py:74
Methodget_decoder
(self)
llava/model/mpt/modeling_mpt.py:252
Functionget_eval
(content: str, max_tokens: int)
llava/eval/eval_gpt_review.py:11
Functionget_eval
(content: str, max_tokens: int)
llava/eval/eval_gpt_review_visual.py:11
Methodget_input_embeddings
(self)
llava/model/mpt/modeling_mpt.py:237
Functionget_status
(request: Request)
llava/serve/model_worker.py:350
Functionget_worker_address
(request: Request)
llava/serve/controller.py:262
Functionheart_beat_controller
(controller)
llava/serve/controller.py:51
Functionheart_beat_worker
(controller)
llava/serve/model_worker.py:42
Functionhttp_bot
(state, model_selector, temperature, max_new_tokens, request: gr.Request)
llava/serve/gradio_web_server.py:177
Functioninit_empty_weights
Meta initialization context manager. A context manager under which models are initialized with all parameters on the meta device, therefore c
llava/model/mpt/meta_init_context.py:6
Methodinitialize_vision_modules
(self, vision_tower, mm_vision_select_layer, pretrain_mm_mlp_adapter=None, t
llava/model/llava_mpt.py:58
Methodinitialize_vision_tokenizer
(self, mm_use_im_start_end, tokenizer, device, tune_mm_mlp_adapter=False,
llava/model/llava_mpt.py:236
Functionkaiming_normal_param_init_fn_
(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, b
llava/model/mpt/param_init_fns.py:162
Functionkaiming_uniform_param_init_fn_
(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, b
llava/model/mpt/param_init_fns.py:155
Functionlist_models
()
llava/serve/controller.py:256
Functionload_demo
(url_params, request: gr.Request)
llava/serve/gradio_web_server.py:61
Functionload_demo_refresh_model_list
(request: gr.Request)
llava/serve/gradio_web_server.py:81
Functionmain
(task, **kwargs)
scripts/convert_sqa_to_llava.py:83
Functionneox_param_init_fn_
From section 2.3.1 of GPT-NeoX-20B: An Open-Source AutoregressiveLanguage Model — Black et. al. (2022) see https://github.com/EleutherAI/gpt-
llava/model/mpt/param_init_fns.py:142
Methodparam_init_fn
(self, module)
llava/model/mpt/modeling_mpt.py:210
Methodparam_init_fn
(self, module)
llava/model/mpt/modeling_mpt.py:271
FunctionpopulateModels
(models)
llava/eval/webpage/script.js:70
FunctionpopulateQuestions
(questions)
llava/eval/webpage/script.js:81
Methodpostprocess
Parameters: y: List of tuples representing the message and response pairs. Each message and response should be a string, which ma
llava/serve/gradio_patch.py:121
Functionprepare_inputs_for_generation
(self: BloomForCausalLM, input_ids: torch.LongTensor, past: Optional[torch.Tensor]=None, attention_mask: Optio
llava/model/mpt/hf_prefixlm_converter.py:255
Methodprepare_inputs_for_generation
( self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs )
llava/model/llava.py:263
Methodprepare_inputs_for_generation
(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs)
llava/model/llava_mpt.py:216
Methodprepare_inputs_for_generation
(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs)
llava/model/mpt/modeling_mpt.py:281
Functionreceive_heart_beat
(request: Request)
llava/serve/controller.py:269
Functionrefresh_all_workers
()
llava/serve/controller.py:251
Functionregenerate
(state, image_process_mode, request: gr.Request)
llava/serve/gradio_web_server.py:125
Functionregister_empty_buffer
(module, name, buffer)
llava/model/mpt/meta_init_context.py:67
Functionregister_empty_parameter
(module, name, param)
llava/model/mpt/meta_init_context.py:60
Functionregister_worker
(request: Request)
llava/serve/controller.py:243
Functionrelease_model_semaphore
(fn=None)
llava/serve/model_worker.py:327
Functionscaled_multihead_dot_product_attention
(query, key, value, n_heads, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropo
llava/model/mpt/attention.py:19
Methodset_decoder
(self, decoder)
llava/model/mpt/modeling_mpt.py:249
Methodset_input_embeddings
(self, value)
llava/model/mpt/modeling_mpt.py:75
Methodset_input_embeddings
(self, value)
llava/model/mpt/modeling_mpt.py:240
Methodset_output_embeddings
(self, new_embeddings)
llava/model/mpt/modeling_mpt.py:246
Functiontorch_default_param_init_fn_
(module: nn.Module, verbose: int=0, **kwargs)
llava/model/mpt/param_init_fns.py:10
Functiontrim_hanging_lines
(s: str, n: int)
llava/eval/generate_webpage_data_from_table.py:23
Functiontriton_flash_attn_fn
(query, key, value, n_heads, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropo
llava/model/mpt/attention.py:88
Functionupvote_last_response
(state, model_selector, request: gr.Request)
llava/serve/gradio_web_server.py:107
Functionworker_api_generate_stream
(request: Request)
llava/serve/controller.py:277
Functionworker_api_get_status
(request: Request)
llava/serve/controller.py:284
Functionwrap_func
(*args, **kwargs)
llava/train/train.py:646
Functionwrapper
(*args, **kwargs)
llava/model/mpt/meta_init_context.py:78
Functionxavier_normal_param_init_fn_
(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, b
llava/model/mpt/param_init_fns.py:176
Functionxavier_uniform_param_init_fn_
(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, b
llava/model/mpt/param_init_fns.py:169
← previous201–275 of 275, ranked by callers