MCPcopy Create free account

hub / github.com/LlamaChinese/Llama-Chinese / functions

Functions68 in github.com/LlamaChinese/Llama-Chinese

⨍ Functions 68◇ Types & classes 13↳ Endpoints 2
↓ 4 callersFunctionpermute
(w, n_heads=n_heads, dim1=dim, dim2=dim)
scripts/convert2hf/convert_llama_weights_to_hf.py:114
↓ 2 callersFunctionget_world_size
()
scripts/api/accelerate_server.py:147
↓ 2 callersFunctionmain
()
train/sft/finetune_clm_lora.py:269
↓ 2 callersFunctionmain
()
train/sft/finetune_clm.py:238
↓ 2 callersFunctionmain
()
train/pretrain/pretrain_clm.py:224
↓ 2 callersFunctiontokenize
(prompt)
train/sft/finetune_clm_lora.py:508
↓ 2 callersFunctiontokenize
(prompt)
train/sft/finetune_clm.py:451
↓ 1 callersMethodask
(self,input_text,temperature=0.4,top_p=0.95,max_new_tokens=1024,repetition_penalty=1.2,system_prefix = '',merg
inference-speed/GPU/TensorRT-LLM_example/atom_inference.py:49
↓ 1 callersFunctioncompute_intermediate_size
(n, ffn_dim_multiplier=1, multiple_of=256)
scripts/convert2hf/convert_llama_weights_to_hf.py:75
↓ 1 callersFunctionget_engine_version
(engine_dir: str)
inference-speed/GPU/TensorRT-LLM_example/utils.py:54
↓ 1 callersFunctionget_prompt
(chat_history, system_prompt="")
scripts/api/accelerate_server.py:48
↓ 1 callersFunctionget_prompt_llama2_meta
(chat_history, system_prompt="")
inference-speed/GPU/vllm_example/client_test.py:30
↓ 1 callersFunctionget_prompt_llama2chinese
( chat_history, system_prompt="" )
scripts/api/accelerate_server.py:32
↓ 1 callersFunctionget_prompt_llama3
(chat_history, system_prompt="")
scripts/api/accelerate_server.py:81
↓ 1 callersFunctionget_prompt_llama3_meta
(chat_history, system_prompt="")
inference-speed/GPU/vllm_example/client_test.py:63
↓ 1 callersFunctionget_prompt_llama_chinese
( chat_history, system_prompt="" )
inference-speed/GPU/vllm_example/client_test.py:14
↓ 1 callersFunctioninput_prompt
Input a prompt in the consolo interface.
inference-speed/GPU/lmdeploy_example/test_api_server.py:5
↓ 1 callersFunctionload_tokenizer
(tokenizer_dir: Optional[str] = None, vocab_file: Optional[str] = None,
inference-speed/GPU/TensorRT-LLM_example/utils.py:86
↓ 1 callersFunctionmain
()
scripts/convert2hf/convert_llama_weights_to_hf.py:276
↓ 1 callersFunctionprint_rank0
(*msg)
scripts/api/accelerate_server.py:153
↓ 1 callersFunctionread_json
(path)
scripts/convert2hf/convert_llama_weights_to_hf.py:79
↓ 1 callersFunctionread_model_name
(engine_dir: str)
inference-speed/GPU/TensorRT-LLM_example/utils.py:65
↓ 1 callersFunctionstream_results
()
inference-speed/GPU/vllm_example/api_server.py:36
↓ 1 callersFunctiontest_api_server
(input_text)
scripts/api/accelerate_client.py:7
↓ 1 callersFunctiontest_api_server
(chat_history=[], system_prompt="")
inference-speed/GPU/vllm_example/client_test.py:80
↓ 1 callersFunctionthrottle_generator
(generator, stream_interval)
inference-speed/GPU/TensorRT-LLM_example/utils.py:77
↓ 1 callersFunctionwrite_json
(text, path)
scripts/convert2hf/convert_llama_weights_to_hf.py:84
↓ 1 callersFunctionwrite_model
(model_path, input_base_path, model_size, safe_serialization=True)
scripts/convert2hf/convert_llama_weights_to_hf.py:89
↓ 1 callersFunctionwrite_tokenizer
(tokenizer_path, input_tokenizer_path)
scripts/convert2hf/convert_llama_weights_to_hf.py:268
Method__init__
(self,engine_dir,tokenizer_dir,max_input_length=4096)
inference-speed/GPU/TensorRT-LLM_example/atom_inference.py:18
Method__init__
(self, model_name_or_path, bit4=False)
examples/llama2_for_langchain.py:14
Method__post_init__
(self)
train/sft/finetune_clm_lora.py:161
Method__post_init__
(self)
train/sft/finetune_clm_lora.py:235
Method__post_init__
(self)
train/sft/finetune_clm.py:151
Method__post_init__
(self)
train/sft/finetune_clm.py:224
Method__post_init__
(self)
train/pretrain/pretrain_clm.py:140
Method__post_init__
(self)
train/pretrain/pretrain_clm.py:210
Method_call
(self, prompt: str, stop: Optional[List[str]] = None)
examples/llama2_for_langchain.py:34
Method_compute
(self, predictions, references, normalize=True, sample_weight=None)
train/sft/accuracy.py:101
Method_compute
(self, predictions, references, normalize=True, sample_weight=None)
train/pretrain/accuracy.py:101
Method_info
(self)
train/sft/accuracy.py:82
Method_info
(self)
train/pretrain/accuracy.py:82
Method_llm_type
(self)
examples/llama2_for_langchain.py:31
Function_mp_fn
(index)
train/sft/finetune_clm_lora.py:688
Function_mp_fn
(index)
train/sft/finetune_clm.py:608
Function_mp_fn
(index)
train/pretrain/pretrain_clm.py:608
Functionabort_request
()
inference-speed/GPU/vllm_example/api_server.py:45
Methodask_streaming
(self,input_text,temperature=0.8,top_p=0.95,max_new_tokens=1024,repetition_penalty=1.2,system_prefix = '',max_
inference-speed/GPU/TensorRT-LLM_example/atom_inference.py:117
Functionbot
(history,temperature,top_p,slider_context_times)
examples/chat_gradio_no_merge.py:26
Functionbot
(history,temperature,top_p,slider_context_times)
examples/chat_gradio.py:25
Functioncompute_metrics
(eval_preds)
train/sft/finetune_clm_lora.py:583
Functioncompute_metrics
(eval_preds)
train/sft/finetune_clm.py:526
Functioncompute_metrics
(eval_preds)
train/pretrain/pretrain_clm.py:545
Functioncreate_item
(request: Request)
scripts/api/accelerate_server.py:99
Functiongenerate
Generate completion for the request. The request should be a JSON object with the following fields: - prompt: the prompt to use for the gener
inference-speed/GPU/vllm_example/api_server.py:20
Functiongenerate_and_tokenize_prompt
(data_point)
train/sft/finetune_clm_lora.py:513
Functiongenerate_and_tokenize_prompt
(data_point)
train/sft/finetune_clm.py:456
Functiongroup_texts
(examples)
train/pretrain/pretrain_clm.py:474
Functionmain
An example to communicate with inference server through the command line interface. Args: tritonserver_addr (str): the address in for
inference-speed/GPU/lmdeploy_example/test_api_server.py:20
Methodon_save
( self, args: TrainingArguments, state: TrainerState, control: TrainerControl,
train/sft/finetune_clm_lora.py:250
Functionpreprocess_logits_for_metrics
(logits, labels)
train/sft/finetune_clm_lora.py:574
Functionpreprocess_logits_for_metrics
(logits, labels)
train/sft/finetune_clm.py:517
Functionpreprocess_logits_for_metrics
(logits, labels)
train/pretrain/pretrain_clm.py:535
Functiontokenize_function
(examples)
train/sft/finetune_clm_lora.py:502
Functiontokenize_function
(examples)
train/sft/finetune_clm.py:445
Functiontokenize_function
(examples)
train/pretrain/pretrain_clm.py:433
Functionuser
(user_message, history)
examples/chat_gradio_no_merge.py:24
Functionuser
(user_message, history)
examples/chat_gradio.py:23