MCPcopy Create free account

hub / github.com/Tele-AI/Telechat / functions

Functions680 in github.com/Tele-AI/Telechat

⨍ Functions 680◇ Types & classes 127↳ Endpoints 2
↓ 27 callersMethodappend
(self, message)
models/7B/generation_utils.py:25
↓ 21 callersMethodfrom_pretrained
load un-quantized pretrained model to cpu
quant/modeling_telechat_gptq.py:31
↓ 13 callersMethodpop
(self)
models/7B/generation_utils.py:35
↓ 11 callersFunctionprint_rank_0
(msg, rank=0)
deepspeed-telechat/utils/utils.py:14
↓ 10 callersFunctionresponse_data
(seqid, code, message, flag, data)
service/telechat_service.py:88
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/7B_8bit/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/12B_4bit/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/7B/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/12B/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/7B_4bit/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/12B-V2_8bit/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/12B_8bit/modeling_telechat.py:494
↓ 9 callersMethod__init__
(self, config: TelechatConfig)
models/12B-V2/modeling_telechat.py:494
↓ 7 callersMethodchat
Args: tokenizer: the tokenizer of telechat question: question which the model reply in this turn hi
models/7B/modeling_telechat.py:833
↓ 7 callersMethodeval
(self)
deepspeed-telechat/utils/module/lora.py:52
↓ 7 callersMethodupdate
(self, message)
models/12B_4bit/generation_utils.py:46
↓ 7 callersMethodupdate
(self, content: str)
models/7B/generation_utils.py:43
↓ 7 callersMethodupdate
(self, message)
models/12B/generation_utils.py:46
↓ 7 callersMethodupdate
(self, message)
models/12B-V2_8bit/generation_utils.py:46
↓ 7 callersMethodupdate
(self, message)
models/12B_8bit/generation_utils.py:46
↓ 7 callersMethodupdate
(self, message)
models/12B-V2/generation_utils.py:46
↓ 6 callersMethodappend
(self, message)
models/12B_4bit/generation_utils.py:26
↓ 6 callersMethodappend
(self, message)
models/12B/generation_utils.py:26
↓ 6 callersMethodappend
(self, message)
models/12B-V2_8bit/generation_utils.py:26
↓ 6 callersMethodappend
(self, message)
models/12B_8bit/generation_utils.py:26
↓ 6 callersMethodappend
(self, message)
models/12B-V2/generation_utils.py:26
↓ 6 callersMethodupdate
(self, content: str)
models/7B_8bit/generation_utils.py:43
↓ 6 callersMethodupdate
(self, content: str)
models/7B_4bit/generation_utils.py:43
↓ 5 callersMethodappend
(self, message)
models/7B_8bit/generation_utils.py:25
↓ 5 callersMethodappend
(self, message)
models/7B_4bit/generation_utils.py:25
↓ 4 callersMethod__init__
( self, hidden_size: int, intermediate_size: int, hidden_act: str, qua
service/vllm_inf/telechat_12B.py:62
↓ 4 callersMethodchat
shortcut for model.chat
quant/modeling_telechat_gptq.py:350
↓ 3 callersMethodpop
(self)
models/7B_8bit/generation_utils.py:35
↓ 3 callersMethodpop
(self)
models/12B_4bit/generation_utils.py:38
↓ 3 callersMethodpop
(self)
models/12B/generation_utils.py:38
↓ 3 callersMethodpop
(self)
models/7B_4bit/generation_utils.py:35
↓ 3 callersMethodpop
(self)
models/12B-V2_8bit/generation_utils.py:38
↓ 3 callersMethodpop
(self)
models/12B_8bit/generation_utils.py:38
↓ 3 callersMethodpop
(self)
models/12B-V2/generation_utils.py:38
↓ 2 callersFunction_z3_params_to_fetch
(param_list)
deepspeed-telechat/utils/module/lora.py:123
↓ 2 callersFunctioncheck_ex
(do_sample, max_length, top_k, top_p, temperature, repetition_penalty)
service/telechat_service.py:48
↓ 2 callersFunctionconvert_lora_to_linear_layer
(model)
deepspeed-telechat/utils/module/lora.py:132
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *require
models/7B_8bit/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *required*):
models/12B_4bit/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *require
models/7B/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *require
models/12B/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *require
models/7B_4bit/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *required*):
models/12B-V2_8bit/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *required*):
models/12B_8bit/modeling_telechat.py:248
↓ 2 callersFunctiondropout_add
Dropout add function Args: x (`torch.tensor`, *required*): input tensor residual (`torch.tensor`, *required*):
models/12B-V2/modeling_telechat.py:248
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/7B_8bit/generation_utils.py:137
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/12B_4bit/generation_utils.py:139
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/7B/generation_utils.py:137
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/12B/generation_utils.py:139
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/7B_4bit/generation_utils.py:137
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/12B-V2_8bit/generation_utils.py:139
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/12B_8bit/generation_utils.py:139
↓ 2 callersMethodon_finalized_text
Put the text tuple in the queue.
models/12B-V2/generation_utils.py:139
↓ 2 callersFunctionparse_data
(dialog)
service/telechat_service.py:101
↓ 2 callersMethodput
put printable text into queue
models/7B_8bit/generation_utils.py:89
↓ 2 callersMethodput
put printable text into queue
models/12B_4bit/generation_utils.py:92
↓ 2 callersMethodput
put printable text into queue
models/7B/generation_utils.py:89
↓ 2 callersMethodput
put printable text into queue
models/12B/generation_utils.py:92
↓ 2 callersMethodput
put printable text into queue
models/7B_4bit/generation_utils.py:89
↓ 2 callersMethodput
put printable text into queue
models/12B-V2_8bit/generation_utils.py:92
↓ 2 callersMethodput
put printable text into queue
models/12B_8bit/generation_utils.py:92
↓ 2 callersMethodput
put printable text into queue
models/12B-V2/generation_utils.py:92
↓ 2 callersFunctionrotate_half
(x)
models/7B_8bit/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/12B_4bit/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/7B/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/12B/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/7B_4bit/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/12B-V2_8bit/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/12B_8bit/modeling_telechat.py:131
↓ 2 callersFunctionrotate_half
(x)
models/12B-V2/modeling_telechat.py:131
↓ 2 callersFunctionsave_hf_format
(model, tokenizer, args, sub_folder="")
deepspeed-telechat/utils/utils.py:37
↓ 2 callersFunctionsave_zero_three_model
(model, tokenizer, args, sub_folder="")
deepspeed-telechat/utils/utils.py:107
↓ 2 callersFunctionset_random_seed
(seed)
deepspeed-telechat/utils/utils.py:58
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/7B_8bit/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/12B_4bit/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/7B/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/12B/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/7B_4bit/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/12B-V2_8bit/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/12B_8bit/modeling_telechat.py:267
↓ 2 callersFunctiontelechat_gelu_forward
Custom bias GELU function. Adapted from Megatron-DeepSpeed code. Here we use a simple implementation (inference) to make the model jitable.
models/12B-V2/modeling_telechat.py:267
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/7B_8bit/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/12B_4bit/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/7B/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/12B/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/7B_4bit/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/12B-V2_8bit/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/12B_8bit/modeling_telechat.py:237
↓ 1 callersFunction_expand_mask
Expands attention_mask from `[batch_size, src_length]` to `[batch_size, 1, tgt_length, src_length]`.
models/12B-V2/modeling_telechat.py:237
↓ 1 callersFunction_gc
()
service/telechat_service.py:24
↓ 1 callersMethod_is_printable
Checks whether tokens can be decoded or not
models/7B_8bit/generation_utils.py:145
↓ 1 callersMethod_is_printable
Checks whether tokens can be decoded or not
models/12B_4bit/generation_utils.py:148
↓ 1 callersMethod_is_printable
Checks whether tokens can be decoded or not
models/7B/generation_utils.py:145
↓ 1 callersMethod_is_printable
Checks whether tokens can be decoded or not
models/12B/generation_utils.py:148
↓ 1 callersMethod_is_printable
Checks whether tokens can be decoded or not
models/7B_4bit/generation_utils.py:145
next →1–100 of 680, ranked by callers