MCPcopy Create free account

hub / github.com/Tele-AI/Telechat / types & classes

Types & classes127 in github.com/Tele-AI/Telechat

⨍ Functions 680◇ Types & classes 127↳ Endpoints 2
↓ 4 callersClassMixedFusedRMSNorm
models/7B_8bit/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/12B_4bit/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/7B/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/12B/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/7B_4bit/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/12B-V2_8bit/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/12B_8bit/modeling_telechat.py:141
↓ 4 callersClassMixedFusedRMSNorm
models/12B-V2/modeling_telechat.py:141
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax
models/7B_8bit/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax att
models/12B_4bit/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax
models/7B/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax
models/12B/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax
models/7B_4bit/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax att
models/12B-V2_8bit/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax att
models/12B_8bit/modeling_telechat.py:156
↓ 1 callersClassFlashSelfAttention
Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax att
models/12B-V2/modeling_telechat.py:156
↓ 1 callersClassHistory
models/7B_8bit/generation_utils.py:7
↓ 1 callersClassHistory
models/12B_4bit/generation_utils.py:7
↓ 1 callersClassHistory
models/7B/generation_utils.py:7
↓ 1 callersClassHistory
models/12B/generation_utils.py:7
↓ 1 callersClassHistory
models/7B_4bit/generation_utils.py:7
↓ 1 callersClassHistory
models/12B-V2_8bit/generation_utils.py:7
↓ 1 callersClassHistory
models/12B_8bit/generation_utils.py:7
↓ 1 callersClassHistory
models/12B-V2/generation_utils.py:7
↓ 1 callersClassLinearLayer_LoRA
deepspeed-telechat/utils/module/lora.py:12
↓ 1 callersClassPromptDataset
deepspeed-telechat/utils/data/data_utils.py:38
↓ 1 callersClassRotaryEmbedding
models/7B_8bit/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/12B_4bit/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/7B/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/12B/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/7B_4bit/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/12B-V2_8bit/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/12B_8bit/modeling_telechat.py:82
↓ 1 callersClassRotaryEmbedding
models/12B-V2/modeling_telechat.py:82
↓ 1 callersClassTeleChatAttention
service/vllm_inf/telechat_12B.py:100
↓ 1 callersClassTeleChatDecoderLayer
service/vllm_inf/telechat_12B.py:210
↓ 1 callersClassTeleChatMLP
service/vllm_inf/telechat_12B.py:60
↓ 1 callersClassTeleChatModel
service/vllm_inf/telechat_12B.py:280
↓ 1 callersClassTelechatAttention
models/7B_8bit/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/12B_4bit/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/7B/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/12B/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/7B_4bit/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/12B-V2_8bit/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/12B_8bit/modeling_telechat.py:329
↓ 1 callersClassTelechatAttention
models/12B-V2/modeling_telechat.py:329
↓ 1 callersClassTelechatBlock
models/7B_8bit/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/12B_4bit/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/7B/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/12B/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/7B_4bit/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/12B-V2_8bit/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/12B_8bit/modeling_telechat.py:508
↓ 1 callersClassTelechatBlock
models/12B-V2/modeling_telechat.py:508
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/7B_8bit/generation_utils.py:64
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/12B_4bit/generation_utils.py:67
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/7B/generation_utils.py:64
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/12B/generation_utils.py:67
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/7B_4bit/generation_utils.py:64
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/12B-V2_8bit/generation_utils.py:67
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/12B_8bit/generation_utils.py:67
↓ 1 callersClassTelechatIterTextStreamer
With reference to the TextIterStreamers in transformers, we have rewritten this class
models/12B-V2/generation_utils.py:67
↓ 1 callersClassTelechatMLP
models/7B_8bit/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/12B_4bit/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/7B/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/12B/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/7B_4bit/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/12B-V2_8bit/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/12B_8bit/modeling_telechat.py:493
↓ 1 callersClassTelechatMLP
models/12B-V2/modeling_telechat.py:493
↓ 1 callersClassTelechatModel
models/7B_8bit/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/12B_4bit/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/7B/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/12B/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/7B_4bit/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/12B-V2_8bit/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/12B_8bit/modeling_telechat.py:596
↓ 1 callersClassTelechatModel
models/12B-V2/modeling_telechat.py:596
ClassGeLUFunction
models/7B_8bit/modeling_telechat.py:297
ClassGeLUFunction
models/12B_4bit/modeling_telechat.py:297
ClassGeLUFunction
models/7B/modeling_telechat.py:297
ClassGeLUFunction
models/12B/modeling_telechat.py:297
ClassGeLUFunction
models/7B_4bit/modeling_telechat.py:297
ClassGeLUFunction
models/12B-V2_8bit/modeling_telechat.py:297
ClassGeLUFunction
models/12B_8bit/modeling_telechat.py:297
ClassGeLUFunction
models/12B-V2/modeling_telechat.py:297
ClassPromptRawDataset
deepspeed-telechat/utils/data/raw_datasets.py:7
ClassTeleChat12BForCausalLM
service/vllm_inf/telechat_12B.py:336
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional
models/7B_8bit/configuration_telechat.py:23
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional*,
models/12B_4bit/configuration_telechat.py:26
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional
models/7B/configuration_telechat.py:23
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional*,
models/12B/configuration_telechat.py:26
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional
models/7B_4bit/configuration_telechat.py:23
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional*,
models/12B-V2_8bit/configuration_telechat.py:26
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional*,
models/12B_8bit/configuration_telechat.py:26
ClassTelechatConfig
Args: vocab_size (`int`, *optional*, defaults to 160256): Vocabulary size of the Telechat model. hidden_size (`int`, *optional*,
models/12B-V2/configuration_telechat.py:26
ClassTelechatDataset
deepspeed-telechat/utils/data/raw_datasets.py:29
ClassTelechatForCausalLM
models/7B_8bit/modeling_telechat.py:741
ClassTelechatForCausalLM
models/12B_4bit/modeling_telechat.py:741
ClassTelechatForCausalLM
models/7B/modeling_telechat.py:741
next →1–100 of 127, ranked by callers