Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Tele-AI/Telechat
/ functions
Functions
680 in github.com/Tele-AI/Telechat
⨍
Functions
680
◇
Types & classes
127
↳
Endpoints
2
Method
get_output_embeddings
(self)
models/7B_8bit/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/12B_4bit/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/7B/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/12B/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/7B_4bit/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/12B-V2_8bit/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/12B_8bit/modeling_telechat.py:751
Method
get_output_embeddings
(self)
models/12B-V2/modeling_telechat.py:751
Method
get_prompt
(self, sample)
deepspeed-telechat/utils/data/raw_datasets.py:21
Method
get_prompt
(self, sample)
deepspeed-telechat/utils/data/raw_datasets.py:44
Method
get_prompt_and_answer
(self, sample)
deepspeed-telechat/utils/data/raw_datasets.py:24
Method
get_prompt_and_answer
(self, sample)
deepspeed-telechat/utils/data/raw_datasets.py:47
Method
get_special_tokens_mask
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
models/12B_4bit/tokenization_telechat.py:152
Method
get_special_tokens_mask
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
models/12B/tokenization_telechat.py:152
Method
get_special_tokens_mask
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
models/12B-V2_8bit/tokenization_telechat.py:152
Method
get_special_tokens_mask
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
models/12B_8bit/tokenization_telechat.py:152
Method
get_special_tokens_mask
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the
models/12B-V2/tokenization_telechat.py:152
Method
get_train_data
(self)
deepspeed-telechat/utils/data/raw_datasets.py:15
Method
get_vocab
Returns vocab as a dict
models/12B_4bit/tokenization_telechat.py:76
Method
get_vocab
Returns vocab as a dict
models/12B/tokenization_telechat.py:76
Method
get_vocab
Returns vocab as a dict
models/12B-V2_8bit/tokenization_telechat.py:76
Method
get_vocab
Returns vocab as a dict
models/12B_8bit/tokenization_telechat.py:76
Method
get_vocab
Returns vocab as a dict
models/12B-V2/tokenization_telechat.py:76
Function
lifespan
(app: FastAPI)
service/telechat_service.py:32
Method
load_kv_cache_scales
(self, quantization_param_path: str)
service/vllm_inf/telechat_12B.py:468
Method
load_weights
(self, weights: Iterable[Tuple[str, torch.Tensor]])
service/vllm_inf/telechat_12B.py:438
Method
make_empty_intermediate_tensors
( self, batch_size: int, dtype: torch.dtype, device: torch.device)
service/vllm_inf/telechat_12B.py:424
Function
make_inputs_require_grad
(module, input, output)
deepspeed-telechat/utils/module/lora.py:183
Method
pop_left
(self)
models/7B_8bit/generation_utils.py:39
Method
pop_left
(self)
models/12B_4bit/generation_utils.py:42
Method
pop_left
(self)
models/7B/generation_utils.py:39
Method
pop_left
(self)
models/12B/generation_utils.py:42
Method
pop_left
(self)
models/7B_4bit/generation_utils.py:39
Method
pop_left
(self)
models/12B-V2_8bit/generation_utils.py:42
Method
pop_left
(self)
models/12B_8bit/generation_utils.py:42
Method
pop_left
(self)
models/12B-V2/generation_utils.py:42
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Te
models/7B_8bit/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Tenso
models/12B_4bit/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Te
models/7B/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Te
models/12B/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Te
models/7B_4bit/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Tenso
models/12B-V2_8bit/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Tenso
models/12B_8bit/modeling_telechat.py:757
Method
prepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Tenso
models/12B-V2/modeling_telechat.py:757
Method
repeat_kv
(self, hidden_states, n_rep)
models/7B_8bit/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/12B_4bit/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/7B/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/12B/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/7B_4bit/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/12B-V2_8bit/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/12B_8bit/modeling_telechat.py:367
Method
repeat_kv
(self, hidden_states, n_rep)
models/12B-V2/modeling_telechat.py:367
Method
sample
( self, logits: torch.Tensor, sampling_metadata: SamplingMetadata, )
service/vllm_inf/telechat_12B.py:416
Method
save_vocabulary
Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory
models/12B_4bit/tokenization_telechat.py:114
Method
save_vocabulary
Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory
models/12B/tokenization_telechat.py:114
Method
save_vocabulary
Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory
models/12B-V2_8bit/tokenization_telechat.py:114
Method
save_vocabulary
Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory
models/12B_8bit/tokenization_telechat.py:114
Method
save_vocabulary
Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory
models/12B-V2/tokenization_telechat.py:114
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/7B_8bit/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/12B_4bit/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/7B/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/12B/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/7B_4bit/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/12B-V2_8bit/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/12B_8bit/modeling_telechat.py:633
Method
set_input_embeddings
(self, new_embeddings: torch.Tensor)
models/12B-V2/modeling_telechat.py:633
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/7B_8bit/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/12B_4bit/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/7B/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/12B/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/7B_4bit/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/12B-V2_8bit/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/12B_8bit/modeling_telechat.py:754
Method
set_output_embeddings
(self, new_embeddings: torch.Tensor)
models/12B-V2/modeling_telechat.py:754
Method
skip
(*args, **kwargs)
quant/modeling_telechat_gptq.py:45
Method
vocab_size
Returns vocab size
models/12B_4bit/tokenization_telechat.py:72
Method
vocab_size
Returns vocab size
models/12B/tokenization_telechat.py:72
Method
vocab_size
Returns vocab size
models/12B-V2_8bit/tokenization_telechat.py:72
Method
vocab_size
Returns vocab size
models/12B_8bit/tokenization_telechat.py:72
Method
vocab_size
Returns vocab size
models/12B-V2/tokenization_telechat.py:72
← previous
601–680 of 680, ranked by callers