Functions — github.com/InternLM/InternLM-XComposer

hub / github.com/InternLM/InternLM-XComposer / functions

Functions1,890 in github.com/InternLM/InternLM-XComposer

⨍ Functions 1,890◇ Types & classes 331↳ Endpoints 15

↓ 4 callersFunctioncall_og_forward

()

projects/DualFocus/dualfocus/model/language_model/mpt/hf_prefixlm_converter.py:74

↓ 4 callersFunctionchn2num

(chinese_string, numbering_type=NUMBERING_TYPES[1])

InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/cn_tn.py:568

↓ 4 callersFunctiondisable_torch_init

Disable the redundant torch default initialization to accelerate model creation.

projects/DualFocus/dualfocus/utils.py:94

↓ 4 callersFunctionexpand2square

(pil_img, background_color)

projects/DualFocus/dualfocus/mm_utils.py:14

↓ 4 callersFunctionfind_boxes

(string)

projects/DualFocus/dualfocus/misc/boxes.py:53

↓ 4 callersMethodforward

(self, x)

projects/DualFocus/dualfocus/model/language_model/mpt/norm.py:43

↓ 4 callersMethodget_images_xlab

(self, caption, loc, exclude)

InternLM-XComposer-1.0/examples/web_demo.py:87

↓ 4 callersFunctionget_length_grouped_indices

(lengths, batch_size, world_size, generator=None, merge=True)

projects/ShareGPT4V/share4v/train/share4v_trainer.py:91

↓ 4 callersFunctionget_length_grouped_indices

(lengths, batch_size, world_size, generator=None, merge=True)

projects/DualFocus/dualfocus/train/llava_trainer.py:88

↓ 4 callersFunctionget_model_name_from_path

(model_path)

projects/DualFocus/dualfocus/mm_utils.py:65

↓ 4 callersFunctionget_model_response

Get the model response for the given input Model: Model name file: Video file path inp: Input prompt

InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/utils/data_execution.py:19

↓ 4 callersMethodget_prompt

(self)

InternLM-XComposer-2.0/demo_asset/conversation.py:32

↓ 4 callersFunctionget_stopping_criteria

(stop_words_ids)

InternLM-XComposer-2.0/examples/utils.py:48

↓ 4 callersMethodimg2emb

(self, image)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:1085

↓ 4 callersMethodinterleav_wrap

(self, text, image, max_length=16384)

gradio_demo/gradio_demo_composition.py:357

↓ 4 callersMethodinterleav_wrap

(self, text, image, max_length=4096)

InternLM-XComposer-2.0/examples/gradio_demo_composition.py:301

↓ 4 callersMethodinterleav_wrap

(self, text, image, max_length=4096)

InternLM-XComposer-2.0/examples/IXC2_demo.py:309

↓ 4 callersMethodload_model

(self)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/build_mlp.py:60

↓ 4 callersMethodload_model

(self)

projects/ShareGPT4V/share4v/model/multimodal_encoder/clip_encoder.py:26

↓ 4 callersFunctionload_pretrained_model

(model_path, model_base, model_name, load_8bit=False, load_4bit=False, device_map="auto", device="cuda")

projects/DualFocus/dualfocus/model/builder.py:26

↓ 4 callersFunctionmaybe_zero_3

(param, ignore_status=False, name=None)

projects/ShareGPT4V/share4v/train/train.py:156

↓ 4 callersMethodoutput

(result: Union[str, int])

InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/whisper_normalizer/english.py:176

↓ 4 callersFunctionrank0_print

(*args)

projects/DualFocus/dualfocus/train/train.py:41

↓ 4 callersMethodresize_pos

(self)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/build_mlp.py:66

↓ 4 callersFunctionset_random_seed

Set the random seed for reproducibility. Parameters: seed (int): The seed to use for generating random numbers.

gradio_demo/utils.py:67

↓ 4 callersFunctionset_random_seed

Set the random seed for reproducibility. Parameters: seed (int): The seed to use for generating random numbers.

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_xcomposer2.py:77

↓ 4 callersFunctionset_random_seed

Set the random seed for reproducibility. Parameters: seed (int): The seed to use for generating random numbers.

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm_xcomposer2.py:77

↓ 4 callersMethodshow_article

(self, show_cap=False)

gradio_demo/gradio_demo_composition.py:523

↓ 4 callersMethodshow_article

(self, show_cap=False)

InternLM-XComposer-2.0/examples/gradio_demo_composition.py:460

↓ 4 callersMethodshow_article

(self, show_cap=False)

InternLM-XComposer-2.0/examples/IXC2_demo.py:468

↓ 3 callersMethod__init__

(self, date=None, chntext=None)

InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/cn_tn.py:844

↓ 3 callersFunction_flash_attn_backward

(do, q, k, v, o, lse, dq, dk, dv, bias=None, causal=False, softmax_scale=None)

projects/DualFocus/dualfocus/model/language_model/mpt/flash_attn_triton.py:366

↓ 3 callersFunction_flash_attn_forward

(q, k, v, bias=None, causal=False, softmax_scale=None)

projects/DualFocus/dualfocus/model/language_model/mpt/flash_attn_triton.py:329

↓ 3 callersFunction_parse_text

(text)

InternLM-XComposer-2.5-OmniLive/online_demo_gradio/webdemo.py:112

↓ 3 callersMethod_shape

(self, tensor: torch.Tensor, seq_len: int, bsz: int)

projects/ShareGPT4V/share4v/model/multimodal_encoder/modeling_evaclip.py:263

↓ 3 callersMethod_shape

(self, tensor: torch.Tensor, seq_len: int, bsz: int)

projects/ShareGPT4V/share4v/model/multimodal_encoder/modeling_evaclip.py:378

↓ 3 callersFunctionauto_configure_device_map

(num_gpus)

InternLM-XComposer-2.0/examples/utils.py:6

↓ 3 callersMethodbackward

(ctx, do)

projects/DualFocus/dualfocus/model/language_model/mpt/flash_attn_triton.py:475

↓ 3 callersFunctionbuild_vision_projector

(config, delay_load=False, **kwargs)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/builder_projector.py:341

↓ 3 callersFunctionbuild_vision_tower

(vision_tower_cfg, **kwargs)

projects/ShareGPT4V/share4v/model/multimodal_encoder/builder.py:6

↓ 3 callersFunctioncloseAudio

()

InternLM-XComposer-2.5-OmniLive/online_demo/Frontend/src/hooks/usePlayer.tsx:18

↓ 3 callersFunctionexpand2square

(pil_img, background_color)

projects/ShareGPT4V/share4v/mm_utils.py:15

↓ 3 callersFunctiongenerate

(model, prompt, image_tensor, tokenizer, device)

projects/DualFocus/dualfocus/eval/model_vqa_mmbench.py:57

↓ 3 callersFunctiongenerate

(model, prompt, image_tensor, tokenizer, device)

projects/DualFocus/dualfocus/eval/model_vqa_gqa.py:33

↓ 3 callersFunctiongenerate

(model, prompt, image_tensor, tokenizer, device)

projects/DualFocus/dualfocus/eval/model_vqa_seed.py:33

↓ 3 callersFunctiongenerate

(model, prompt, image_tensor, tokenizer, device)

projects/DualFocus/dualfocus/eval/model_vqa_textvqa.py:32

↓ 3 callersMethodget_images_xlab

(self, caption, loc, exclude)

InternLM-XComposer-1.0/examples/web_demo_4bit.py:105

↓ 3 callersMethodget_input_embeddings

(self)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/modeling_qwen.py:802

↓ 3 callersMethodget_output_embeddings

(self)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/modeling_qwen.py:1034

↓ 3 callersFunctionget_pred_idx

Get the index (e.g. 2) from the prediction (e.g. 'C')

projects/ShareGPT4V/share4v/eval/eval_science_qa_gpt4_requery.py:30

↓ 3 callersFunctionget_vision_tower_state_maybe_zero_3

(named_params, keys_to_match=[''])

projects/ShareGPT4V/share4v/train/train.py:217

↓ 3 callersFunctionimg_process

(imgs)

InternLM-XComposer-2.5-OmniLive/online_demo_gradio/backend_llm.py:32

↓ 3 callersFunctioninit_empty_weights

Meta initialization context manager. A context manager under which models are initialized with all parameters on the meta device, therefore c

projects/DualFocus/dualfocus/model/language_model/mpt/meta_init_context.py:6

↓ 3 callersFunctionload_image

(image_file)

projects/ShareGPT4V/share4v/eval/run_share4v.py:17

↓ 3 callersMethodload_model

(self)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/clip_encoder.py:22

↓ 3 callersMethodload_model

(self)

projects/DualFocus/dualfocus/model/multimodal_encoder/clip_encoder.py:22

↓ 3 callersFunctionmaybe_zero_3

(param, ignore_status=False, name=None)

projects/DualFocus/dualfocus/train/train.py:112

↓ 3 callersFunctionnormalize_str

Normalize the str to lower case and make them float numbers if possible.

InternLM-XComposer-2.0/evaluation/MMMU/utils/eval_utils.py:76

↓ 3 callersFunctionprocess_images

(images, image_processor, model_cfg)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/mm_utils.py:30

↓ 3 callersFunctionprocess_images

(images, image_processor, model_cfg)

projects/ShareGPT4V/share4v/mm_utils.py:29

↓ 3 callersMethodreset

(self)

InternLM-XComposer-2.0/examples/IXC2_demo.py:177

↓ 3 callersMethodshow_md

(self, text_sections, title, caps, selected, show_cap=False)

InternLM-XComposer-1.0/examples/web_demo_4bit.py:329

↓ 3 callersMethodshow_md

(self, text_sections, title, caps, selected, show_cap=False)

InternLM-XComposer-1.0/examples/web_demo.py:311

↓ 3 callersFunctionsplit_video

Split video into prefix part based on timestamp. video_file: path to video file start_time: start time in seconds end_time: end time

InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/utils/video_execution.py:5

↓ 3 callersFunctiontokenizer_image_token

(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)

InternLM-XComposer-2.5-OmniLive/online_demo/Backend/backend_ixc/vs_deploy/video_streaming.py:77

↓ 3 callersFunctiontokenizer_image_token

(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)

InternLM-XComposer-2.5-OmniLive/online_demo/Backend/backend_ixc/vs_deploy/vs_only.py:74

↓ 3 callersFunctiontrain

()

projects/ShareGPT4V/share4v/train/train.py:830

↓ 3 callersFunctionunlock_vit

(training_args, model_args, vision_tower)

projects/ShareGPT4V/share4v/train/train.py:808

↓ 2 callersFunctionR560_HD18_Identity_transform

(img)

gradio_demo/gradio_demo_chat.py:67

↓ 2 callersFunctionVideo_transform

(img, hd_num=25)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/ixc_utils.py:54

↓ 2 callersMethod__init__

(self, in_features: int, out_features: int, bias: bool = Tr

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/build_mlp.py:174

↓ 2 callersMethod__init__

(self, in_features: int, out_features: int, bias: bool = Tr

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/build_mlp.py:174

↓ 2 callersMethod__init__

( self, text_config=None, vision_config=None, projection_dim=512, logit_scale_init_value=2.6592, **kwa

projects/ShareGPT4V/share4v/model/multimodal_encoder/configuration_evaclip.py:305

↓ 2 callersMethod__init__

(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None)

projects/DualFocus/dualfocus/model/language_model/mpt/norm.py:35

↓ 2 callersFunction_bwd_kernel_one_col_block

(start_n, Q, K, V, Bias, DO, DQ, DK, DV, LSE, D, softmax_scale, stride_qm, stride_kn, stride_vn, stride_bm, st

projects/DualFocus/dualfocus/model/language_model/mpt/flash_attn_triton.py:184

↓ 2 callersFunction_bwd_store_dk_dv

(dk_ptrs, dv_ptrs, dk, dv, offs_n, offs_d, seqlen_k, headdim, EVEN_M: tl.constexpr, EVEN_N: tl.constexpr, EVEN

projects/DualFocus/dualfocus/model/language_model/mpt/flash_attn_triton.py:168

↓ 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

projects/DualFocus/dualfocus/model/language_model/mpt/hf_prefixlm_converter.py:45

↓ 2 callersMethod_maybe_log_save_evaluate

(self, tr_loss, tr_logs, model, trial, epoch, ignore_keys_for_eval)

InternLM-XComposer-2.5-Reward/training/trainer.py:558

↓ 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

projects/DualFocus/dualfocus/model/language_model/mpt/param_init_fns.py:124

↓ 2 callersFunction_reset_is_causal

(num_query_tokens: int, num_key_tokens: int, original_is_causal: bool)

projects/DualFocus/dualfocus/model/language_model/mpt/attention.py:12

↓ 2 callersMethod_set_config_defaults

(self, config, config_defaults)

projects/DualFocus/dualfocus/model/language_model/mpt/configuration_mpt.py:90

↓ 2 callersMethod_set_cos_sin_cache

(self, seq_len, device, dtype)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/modeling_qwen.py:101

↓ 2 callersMethod_set_cos_sin_cache

(self, seq_len, device, dtype)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:156

↓ 2 callersMethod_set_cos_sin_cache

(self, seq_len, device, dtype)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm2.py:152

↓ 2 callersMethod_set_cos_sin_cache

(self, seq_len, device, dtype)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm2.py:152

↓ 2 callersFunction_to_float

(text: str)

InternLM-XComposer-2.0/evaluation/utils.py:94

↓ 2 callersFunction_tokenize_fn

Tokenize a list of strings.

projects/ShareGPT4V/share4v/train/train.py:337

↓ 2 callersFunction_tokenize_fn

Tokenize a list of strings.

projects/DualFocus/dualfocus/train/train.py:246

↓ 2 callersMethod_validate_config

(self)

projects/DualFocus/dualfocus/model/language_model/mpt/configuration_mpt.py:96

↓ 2 callersMethodaddedit

(self, edit_type, inst_edit, text_imgs)

gradio_demo/gradio_demo_composition.py:185

↓ 2 callersMethodaddedit

(self, edit_type, inst_edit, text_imgs)

InternLM-XComposer-2.0/examples/gradio_demo_composition.py:137

↓ 2 callersMethodaddedit

(self, edit_type, inst_edit, text_imgs)

InternLM-XComposer-2.0/examples/IXC2_demo.py:138

↓ 2 callersMethodappend_wav_info

(self, bytes_audio, p, rate)

InternLM-XComposer-2.5-OmniLive/online_demo_gradio/frontend.py:43

↓ 2 callersFunctionapply_rotary_pos_emb

Applies Rotary Position Embedding to the query and key tensors.

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:235

↓ 2 callersFunctionapply_rotary_pos_emb

Applies Rotary Position Embedding to the query and key tensors.

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm2.py:231

↓ 2 callersFunctionapply_rotary_pos_emb

Applies Rotary Position Embedding to the query and key tensors.

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm2.py:231

↓ 2 callersFunctionauto_configure_device_map

(num_gpus)

InternLM-XComposer-1.0/examples/utils.py:2

↓ 2 callersFunctionauto_upgrade

(config)

projects/DualFocus/dualfocus/model/utils.py:4

↓ 2 callersFunctionbuild_prompt_chatbot

(problems, shot_qids, prompt_format, use_caption=False, options=["A", "B", "C", "D", "E"], is_test=False)

projects/ShareGPT4V/scripts/convert_sqa_to_share4v_base_prompt.py:220

↓ 2 callersFunctionbuild_vision_projector

(input_dim=4096)

InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/build_mlp.py:13

← previous next →101–200 of 1,890, ranked by callers