MCPcopy Create free account

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

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

⨍ Functions 1,890◇ Types & classes 331↳ Endpoints 15
↓ 2 callersFunctionsetup4lmdeploy
()
InternLM-XComposer-2.5-OmniLive/online_demo/Backend/backend_ixc/vs_deploy/configs_vs/__init__.py:6
↓ 2 callersMethodtelephone2chntext
(self, fixed=False)
InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/cn_tn.py:804
↓ 2 callersFunctiontokenizer_image_token
(prompt, tokenizer, image_token_index=IMAGE_TOKEN_INDEX, return_tensors=None)
InternLM-XComposer-2.5-OmniLive/online_demo_gradio/backend_vs.py:175
↓ 2 callersFunctiontrain
()
projects/DualFocus/dualfocus/train/train.py:805
↓ 2 callersFunctionzero2_align
(x)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/adapter/zero_to_fp32.py:305
↓ 2 callersFunctionzero3_partitioned_param_info
(unpartitioned_numel, world_size)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/adapter/zero_to_fp32.py:345
↓ 1 callersFunctionFlashVstream_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/FlashVstream.py:24
↓ 1 callersFunctionFlashVstream_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/FlashVstream.py:40
↓ 1 callersFunctionHD_transform
(img, hd_num=16)
InternLM-XComposer-2.0/finetune/ixc_utils.py:20
↓ 1 callersFunctionIdentity_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/ixc2d5_ol.py:31
↓ 1 callersFunctionIdentity_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/benchmarks/mlvu/mlvu.py:37
↓ 1 callersFunctionIdentity_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/benchmarks/video_mme/video_mme.py:38
↓ 1 callersFunctionIdentity_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/benchmarks/mvbench/mvbench.py:38
↓ 1 callersFunctionImage_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/ixc_utils.py:28
↓ 1 callersFunctionImage_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/ixc_utils.py:28
↓ 1 callersFunctionInternVL_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/InternVL.py:149
↓ 1 callersFunctionInternVL_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/InternVL.py:166
↓ 1 callersFunctionKangaroo_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/Kangaroo.py:17
↓ 1 callersFunctionKangaroo_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/Kangaroo.py:28
↓ 1 callersFunctionLLaVANextVideo32_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/LLaVANextVideo32.py:31
↓ 1 callersFunctionLLaVANextVideo32_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/LLaVANextVideo32.py:65
↓ 1 callersFunctionLLaVAOneVision_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/LLaVAOneVision.py:33
↓ 1 callersFunctionLLaVAOneVision_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/LLaVAOneVision.py:55
↓ 1 callersFunctionLongVA_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/LongVA.py:25
↓ 1 callersFunctionLongVA_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/LongVA.py:35
↓ 1 callersFunctionQwen2VL_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/Qwen2VL.py:18
↓ 1 callersFunctionQwen2VL_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/Qwen2VL.py:30
↓ 1 callersFunctionR560_HD18_Identity_transform
(img)
gradio_demo/gradio_demo_composition.py:105
↓ 1 callersFunctionR560_HD18_Identity_transform
(img)
InternLM-XComposer-2.0/examples/gradio_4khd_chat.py:56
↓ 1 callersFunctionR560_HD18_Identity_transform
(img, resolution=560, hd_num=18)
InternLM-XComposer-2.5-Reward/training/ixc_utils.py:21
↓ 1 callersFunctionR560_HD18_Identity_transform
(img, resolution=560, hd_num=18)
finetune/ixc_utils.py:21
↓ 1 callersFunctionR560_HD4_transform
(img)
gradio_demo/gradio_demo_chat.py:96
↓ 1 callersFunctionR560_HD4_transform
(img)
InternLM-XComposer-2.0/examples/gradio_4khd_chat.py:85
↓ 1 callersMethodRun
(self, file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VILA.py:20
↓ 1 callersFunctionStreamingBenchEval
(data, MODEL, output_path, video_folder)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/benchmark/StreamingBench.py:40
↓ 1 callersFunctionStreamingBenchInit
(data)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/benchmark/StreamingBench.py:37
↓ 1 callersFunctionStreamingBenchProactiveEval
(data, MODEL, output_path)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/benchmark/StreamingBenchProactive.py:28
↓ 1 callersFunctionStreamingBenchProactiveInit
(data)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/benchmark/StreamingBenchProactive.py:25
↓ 1 callersFunctionStreamingBenchSQAEval
(data, MODEL, output_path)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/benchmark/StreamingBenchSQA.py:35
↓ 1 callersFunctionStreamingBenchSQAInit
(data)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/benchmark/StreamingBenchSQA.py:32
↓ 1 callersFunctionVILA_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VILA.py:28
↓ 1 callersFunctionVILA_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VILA.py:34
↓ 1 callersFunctionVideoCCam_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VideoCCam.py:17
↓ 1 callersFunctionVideoCCam_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VideoCCam.py:27
↓ 1 callersFunctionVideoLLaMA2_Init
()
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VideoLLaMA2.py:21
↓ 1 callersFunctionVideoLLaMA2_Run
(file, inp)
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/VideoLLaMA2.py:32
↓ 1 callersFunctionVideo_transform
(img, hd_num=25)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/ixc_utils.py:54
↓ 1 callersMethod__get_item__
(self, i)
InternLM-XComposer-2.0/finetune/data_mix.py:178
↓ 1 callersMethod__get_item__
(self, i)
InternLM-XComposer-1.0/finetune/data_mix.py:112
↓ 1 callersMethod__get_item__
(self, i)
InternLM-XComposer-2.5-Reward/training/data_mix.py:156
↓ 1 callersMethod__get_item__
(self, i)
finetune/data_mix.py:152
↓ 1 callersMethod__init__
(self, config: Qwen2Config)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/grounding_qwen.py:38
↓ 1 callersMethod__init__
(self, stops=[], encounters=1)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_xcomposer2.py:60
↓ 1 callersMethod__init__
(self, stops=[], encounters=1)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm_xcomposer2.py:60
↓ 1 callersMethod__init__
Initialize the model
InternLM-XComposer-2.5-OmniLive/benchmarks/streamingbench/src/model/videoStream.py:190
↓ 1 callersMethod__init__
(self)
InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/whisper_normalizer/english.py:466
↓ 1 callersMethod__init__
(self, config: LlamaConfig)
projects/ShareGPT4V/share4v/model/language_model/share4v_llama.py:20
↓ 1 callersMethod__init__
(self)
projects/ShareGPT4V/share4v/model/multimodal_projector/builder.py:7
↓ 1 callersMethod__init__
(self, config: LlamaConfig)
projects/DualFocus/dualfocus/model/language_model/llava_llama.py:37
↓ 1 callersMethod__init__
(self, config: MPTConfig)
projects/DualFocus/dualfocus/model/language_model/llava_mpt.py:37
↓ 1 callersMethod__init__
(self, d_model: int, expansion_ratio: int, device: Optional[str]=None)
projects/DualFocus/dualfocus/model/language_model/mpt/blocks.py:10
↓ 1 callersMethod__init__
(self, config: MPTConfig)
projects/DualFocus/dualfocus/model/language_model/mpt/modeling_mpt.py:35
↓ 1 callersMethod__init__
(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False,
projects/DualFocus/dualfocus/model/language_model/mpt/attention.py:158
↓ 1 callersMethod__init__
(self)
projects/DualFocus/dualfocus/model/multimodal_projector/builder.py:7
↓ 1 callersMethod__init__
(self, save_path: str, collect_device: str = 'cpu', prefix:
InternLM-XComposer-1.0/evaluation/mmbench/utils.py:80
↓ 1 callersMethod__init__
(self, cc3m_path, )
InternLM-XComposer-1.0/evaluation/seed_bench/utils.py:100
↓ 1 callersFunction__padding__
(image)
InternLM-XComposer-2.0/evaluation/utils.py:54
↓ 1 callersFunction__resize_img__
( b)
InternLM-XComposer-2.0/evaluation/mme/utils.py:5
↓ 1 callersMethod__str__
(self)
InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/cn_tn.py:405
↓ 1 callersFunction_add_speaker_and_signal
Add speaker and start/end signal on each round.
projects/ShareGPT4V/share4v/train/train.py:375
↓ 1 callersFunction_add_speaker_and_signal
Add speaker and start/end signal on each round.
projects/DualFocus/dualfocus/train/train.py:284
↓ 1 callersMethod_apply_prefix_mask
(self, attn_bias: torch.Tensor, prefix_mask: torch.Tensor)
projects/DualFocus/dualfocus/model/language_model/mpt/modeling_mpt.py:119
↓ 1 callersMethod_apply_sequence_id
(self, attn_bias: torch.Tensor, sequence_id: torch.LongTensor)
projects/DualFocus/dualfocus/model/language_model/mpt/modeling_mpt.py:134
↓ 1 callersMethod_attn_bias
(self, device, dtype, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]
projects/DualFocus/dualfocus/model/language_model/mpt/modeling_mpt.py:88
↓ 1 callersMethod_build_causal_attention_mask
(self, bsz, seq_len, dtype)
projects/ShareGPT4V/share4v/model/multimodal_encoder/modeling_evaclip.py:906
↓ 1 callersMethod_compute_answer_scores
compute the accuracy (soft score) of human answers
projects/ShareGPT4V/share4v/eval/m4c_evaluator.py:225
↓ 1 callersMethod_compute_answer_scores
compute the accuracy (soft score) of human answers
projects/DualFocus/dualfocus/eval/m4c_evaluator.py:225
↓ 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
projects/DualFocus/dualfocus/model/language_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`
projects/DualFocus/dualfocus/model/language_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
projects/DualFocus/dualfocus/model/language_model/mpt/hf_prefixlm_converter.py:269
↓ 1 callersMethod_ensure_feature
(self, sess: Session)
InternLM-XComposer-2.5-OmniLive/online_demo/Backend/backend_ixc/vs_deploy/video_streaming.py:362
↓ 1 callersMethod_ensure_feature
(self, sess: Session)
InternLM-XComposer-2.5-OmniLive/online_demo/Backend/backend_ixc/vs_deploy/vs_only.py:320
↓ 1 callersMethod_ensure_feature
(self, sess: Session)
InternLM-XComposer-2.5-OmniLive/online_demo_gradio/backend_vs.py:379
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:108
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm2.py:104
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm2.py:104
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
projects/ShareGPT4V/share4v/model/multimodal_encoder/modeling_evaclip.py:46
↓ 1 callersFunction_flash_attention_forward
Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token first unpad the input, then compu
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/modeling_flash_attention_utils.py:183
↓ 1 callersMethod_flash_attention_forward
Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token first unpad the input, th
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:518
↓ 1 callersMethod_flash_attention_forward
Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token first unpad the input, th
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm2.py:514
↓ 1 callersMethod_flash_attention_forward
Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token first unpad the input, th
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm2.py:514
↓ 1 callersFunction_get_fp32_state_dict_from_zero2_checkpoint
(world_size, fp32_flat_groups, zero_model_states)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/adapter/zero_to_fp32.py:324
↓ 1 callersFunction_get_fp32_state_dict_from_zero3_checkpoint
(world_size, fp32_flat_groups, zero_model_states)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/adapter/zero_to_fp32.py:442
↓ 1 callersFunction_get_fp32_state_dict_from_zero_checkpoint
Returns fp32 state_dict reconstructed from ds checkpoint Args: - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (whe
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/adapter/zero_to_fp32.py:194
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
InternLM-XComposer-2.5-OmniLive/benchmarks/eval_audio/evaluate_asr.py:110
↓ 1 callersFunction_get_unpad_data
Retrieves indexing data required to repad unpadded (ragged) tensors. Arguments: attention_mask (`torch.Tensor`): Boolean
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/memory/modeling_flash_attention_utils.py:33
↓ 1 callersFunction_get_unpad_data
(attention_mask)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:77
↓ 1 callersFunction_get_unpad_data
(attention_mask)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm2.py:73
↓ 1 callersFunction_get_unpad_data
(attention_mask)
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/merge_lora/modeling_internlm2.py:73
↓ 1 callersFunction_import_flash_attn
()
InternLM-XComposer-2.5-OmniLive/internlm-xcomposer2d5-ol-7b/base/modeling_internlm_.py:65
← previousnext →301–400 of 1,890, ranked by callers