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
↓ 51 callersMethodfrom_pretrained
See `AutoTokenizer.from_pretrained` docstring.
llava/model/mpt/adapt_tokenizer.py:37
↓ 20 callersMethodupdate
( value: Any | Literal[_Keywords.NO_VALUE] | None = _Keywords.NO_VALUE, label: str | None = No
llava/serve/gradio_patch.py:82
↓ 14 callersMethodappend_message
(self, role, message)
llava/conversation.py:62
↓ 13 callersMethodcopy
(self)
llava/conversation.py:144
↓ 12 callersMethodto_gradio_chatbot
(self)
llava/conversation.py:114
↓ 10 callersMethodget_model
(self)
llava/model/llava.py:200
↓ 10 callersMethodget_prompt
(self)
llava/conversation.py:27
↓ 9 callersMethodwrite
(self, buf)
llava/utils.py:73
↓ 7 callersMethodget_input_embeddings
(self)
llava/model/mpt/modeling_mpt.py:72
↓ 5 callersFunction_cast_if_autocast_enabled
(tensor)
llava/model/mpt/norm.py:3
↓ 5 callersFunctiongeneric_param_init_fn_
(module: nn.Module, init_fn_, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, flo
llava/model/mpt/param_init_fns.py:28
↓ 5 callersFunctionget_answer
(problem, options)
scripts/convert_sqa_to_llava_base_prompt.py:25
↓ 5 callersFunctionget_choice_text
(probelm, options)
scripts/convert_sqa_to_llava_base_prompt.py:15
↓ 5 callersFunctionget_context_text
(problem, use_caption)
scripts/convert_sqa_to_llava_base_prompt.py:6
↓ 5 callersFunctionget_lecture_text
(problem)
scripts/convert_sqa_to_llava_base_prompt.py:29
↓ 5 callersMethodget_output_embeddings
(self)
llava/model/mpt/modeling_mpt.py:243
↓ 5 callersFunctionget_question_text
(problem)
scripts/convert_sqa_to_llava_base_prompt.py:1
↓ 5 callersFunctionget_solution_text
(problem)
scripts/convert_sqa_to_llava_base_prompt.py:35
↓ 4 callersFunctioncall_og_forward
()
llava/model/mpt/hf_prefixlm_converter.py:74
↓ 4 callersFunctiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
llava/utils.py:93
↓ 4 callersMethodget_images
(self, return_pil=False)
llava/conversation.py:65
↓ 4 callersFunctionread_jsonl
(path: str, key: str=None)
llava/eval/generate_webpage_data_from_table.py:10
↓ 4 callersFunctiontext2Markdown
(text)
llava/eval/webpage/script.js:35
↓ 3 callersFunctionbuild_logger
(logger_name, logger_filename)
llava/utils.py:17
↓ 3 callersFunctiondisplayQuestion
(index)
llava/eval/webpage/script.js:110
↓ 3 callersMethodflush
(self)
llava/utils.py:87
↓ 3 callersFunctionget_pred_idx
Get the index (e.g. 2) from the prediction (e.g. 'C')
llava/eval/eval_science_qa_gpt4_requery.py:30
↓ 3 callersMethodget_worker_status
(self, worker_name: str)
llava/serve/controller.py:88
↓ 3 callersMethodstyle
This method can be used to change the appearance of the Chatbot component.
llava/serve/gradio_patch.py:153
↓ 3 callersFunctionupdateQuestionSelect
(question_id)
llava/eval/webpage/script.js:48
↓ 3 callersFunctionvote_last_response
(state, vote_type, model_selector, request: gr.Request)
llava/serve/gradio_web_server.py:95
↓ 2 callersMethod__init__
(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None)
llava/model/mpt/norm.py:35
↓ 2 callersFunction_get_attn_modules
Helper that gets a list of the model's attention modules. Each module has a `bias` buffer used for causal masking. The Prefix LM conv
llava/model/mpt/hf_prefixlm_converter.py:45
↓ 2 callersFunction_normal_param_init_fn_
(module: nn.Module, std: float, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, f
llava/model/mpt/param_init_fns.py:124
↓ 2 callersFunction_reset_is_causal
(num_query_tokens: int, num_key_tokens: int, original_is_causal: bool)
llava/model/mpt/attention.py:11
↓ 2 callersMethod_set_config_defaults
(self, config, config_defaults)
llava/model/mpt/configuration_mpt.py:90
↓ 2 callersFunction_tokenize_fn
Tokenize a list of strings.
llava/train/train.py:128
↓ 2 callersMethod_validate_config
(self)
llava/model/mpt/configuration_mpt.py:96
↓ 2 callersFunctionauto_upgrade
(config)
llava/model/utils.py:6
↓ 2 callersFunctionbuild_prompt_chatbot
(problems, shot_qids, prompt_format, use_caption=False, options=["A", "B", "C", "D", "E"], is_test=False)
scripts/convert_sqa_to_llava_base_prompt.py:221
↓ 2 callersFunctioncheck_valid_inputs
(*tensors, valid_dtypes=[torch.float16, torch.bfloat16])
llava/model/mpt/attention.py:54
↓ 2 callersFunctioncreate_one_example
(format, question, context, choice, answer, lecture, solution, test_example=True)
scripts/convert_sqa_to_llava_base_prompt.py:106
↓ 2 callersFunctioncreate_one_example_gpt4
(format, question, context, choice, answer, lecture, solution, test_example=True)
scripts/convert_sqa_to_llava_base_prompt.py:162
↓ 2 callersMethoddict
(self)
llava/conversation.py:154
↓ 2 callersFunctiondisplayAnswers
(index)
llava/eval/webpage/script.js:116
↓ 2 callersFunctionget_conv_log_filename
()
llava/serve/gradio_web_server.py:35
↓ 2 callersMethodget_model
(self)
llava/model/llava_mpt.py:193
↓ 2 callersFunctionget_model_list
()
llava/serve/gradio_web_server.py:41
↓ 2 callersFunctionget_pred_idx
Get the index (e.g. 2) from the prediction (e.g. 'C')
llava/eval/eval_science_qa_gpt4.py:28
↓ 2 callersFunctionget_pred_idx
Get the index (e.g. 2) from the prediction (e.g. 'C')
llava/eval/eval_science_qa.py:28
↓ 2 callersMethodget_queue_length
(self)
llava/serve/model_worker.py:168
↓ 2 callersMethodget_status
(self)
llava/serve/model_worker.py:175
↓ 2 callersMethodget_worker_address
(self, model_name: str)
llava/serve/controller.py:120
↓ 2 callersFunctionpreprocess
Given a list of sources, each is a conversation list. This transform: 1. Add signal '### ' at the beginning each sentence, with end signal '\
llava/train/train.py:354
↓ 2 callersMethodregister_to_controller
(self)
llava/serve/model_worker.py:135
↓ 2 callersMethodregister_worker
(self, worker_name: str, check_heart_beat: bool, worker_status: dict)
llava/serve/controller.py:69
↓ 2 callersMethodremove_worker
(self, worker_name: str)
llava/serve/controller.py:101
↓ 2 callersFunctionrms_norm
(x, weight=None, eps=1e-05)
llava/model/mpt/norm.py:27
↓ 2 callersMethodsend_heart_beat
(self)
llava/serve/model_worker.py:147
↓ 2 callersFunctionsplit_sample
(sample, start_idx, end_idx)
llava/data/split_long_conversation.py:23
↓ 2 callersFunctionswitchQuestionAndCategory
()
llava/eval/webpage/script.js:203
↓ 2 callersFunctiontrain
()
llava/train/train.py:538
↓ 2 callersFunctionupdateExpandButtonVisibility
(card)
llava/eval/webpage/script.js:226
↓ 2 callersFunctionupdateModelSelect
()
llava/eval/webpage/script.js:64
↓ 1 callersMethod__init__
(self, config: LlamaConfig, mm_vision_tower=None, mm_hidden_size=None)
llava/model/llava.py:43
↓ 1 callersMethod__init__
(self, config: MPTConfig, mm_vision_tower=None, mm_hidden_size=None)
llava/model/llava_mpt.py:47
↓ 1 callersMethod__init__
(self, d_model: int, expansion_ratio: int, device: Optional[str]=None)
llava/model/mpt/blocks.py:10
↓ 1 callersMethod__init__
(self, config: MPTConfig)
llava/model/mpt/modeling_mpt.py:32
↓ 1 callersMethod__init__
(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False,
llava/model/mpt/attention.py:122
↓ 1 callersMethod__init__
(self, data_path: str, tokenizer: transformers.PreTrainedTokenizer)
llava/train/train.py:391
↓ 1 callersFunction_add_speaker_and_signal
Add speaker and start/end signal on each round.
llava/train/train.py:166
↓ 1 callersMethod_apply_prefix_mask
(self, attn_bias: torch.Tensor, prefix_mask: torch.Tensor)
llava/model/mpt/modeling_mpt.py:109
↓ 1 callersMethod_apply_sequence_id
(self, attn_bias: torch.Tensor, sequence_id: torch.LongTensor)
llava/model/mpt/modeling_mpt.py:124
↓ 1 callersMethod_attn_bias
(self, device, dtype, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]
llava/model/mpt/modeling_mpt.py:79
↓ 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
llava/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`
llava/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
llava/model/mpt/hf_prefixlm_converter.py:269
↓ 1 callersFunction_mask_targets
(target, tokenized_lens, speakers)
llava/train/train.py:155
↓ 1 callersFunction_normal_init_
(std, mean=0.0)
llava/model/mpt/param_init_fns.py:121
↓ 1 callersMethod_process_chat_messages
( self, chat_message: str | Tuple | List | Dict | None )
llava/serve/gradio_patch.py:97
↓ 1 callersMethod_save
(self, output_dir: Optional[str] = None, state_dict=None)
llava/train/llava_trainer.py:25
↓ 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
llava/model/mpt/adapt_tokenizer.py:6
↓ 1 callersFunctionapply_delta
(base_model_path, target_model_path, delta_path)
llava/model/apply_delta.py:13
↓ 1 callersFunctionattn_bias_shape
(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal, use_sequence_id)
llava/model/mpt/attention.py:234
↓ 1 callersFunctionbuild_alibi_bias
(n_heads, seq_len, full=False, alibi_bias_max=8, device=None, dtype=None)
llava/model/mpt/attention.py:268
↓ 1 callersFunctionbuild_attn_bias
(attn_impl, attn_bias, n_heads, seq_len, causal=False, alibi=False, alibi_bias_max=8)
llava/model/mpt/attention.py:248
↓ 1 callersFunctionbuild_demo
(embed_mode)
llava/serve/gradio_web_server.py:322
↓ 1 callersFunctioncapitalizeFirstChar
(str)
llava/eval/webpage/script.js:41
↓ 1 callersFunctionclean_html_all
Clean the source html files.
llava/data/clean_sharegpt.py:108
↓ 1 callersFunctionconsolidate_ckpt
(src_path, dst_path)
llava/model/consolidate.py:13
↓ 1 callersFunctioncontain_blocked_words
(val: str)
llava/data/clean_sharegpt.py:66
↓ 1 callersFunctioncreate_custom_forward
(module)
llava/model/mpt/hf_prefixlm_converter.py:207
↓ 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 callersFunctioneval_model
(args)
llava/eval/model_vqa_science.py:110
↓ 1 callersFunctioneval_model
(model_name, questions_file, answers_file)
llava/eval/model_qa.py:33
↓ 1 callersFunctioneval_model
(args)
llava/eval/run_llava.py:34
↓ 1 callersFunctioneval_model
(args)
llava/eval/model_vqa.py:51
↓ 1 callersMethodfrom_str
(cls, name)
llava/serve/controller.py:33
↓ 1 callersFunctionfused_init_helper_
(module: nn.Module, init_fn_)
llava/model/mpt/param_init_fns.py:17
↓ 1 callersFunctiongen_slopes
(n_heads, alibi_bias_max=8, device=None)
llava/model/mpt/attention.py:259
next →1–100 of 275, ranked by callers