MCPcopy Create free account

hub / github.com/FreedomIntelligence/LLMZoo / functions

Functions114 in github.com/FreedomIntelligence/LLMZoo

⨍ Functions 114◇ Types & classes 19↳ Endpoints 9
↓ 13 callersMethodupdate
( value: Any | Literal[_Keywords.NO_VALUE] | None = _Keywords.NO_VALUE, label: str | N
llmzoo/deploy/webapp/gradio_patch.py:82
↓ 11 callersMethodto_gradio_chatbot
(self)
llmzoo/utils.py:51
↓ 8 callersMethodwrite
(self, buf)
llmzoo/deploy/webapp/utils.py:76
↓ 6 callersMethodappend_message
(self, role, message)
llmzoo/utils.py:48
↓ 3 callersFunctionbuild_logger
(logger_name, logger_filename)
llmzoo/deploy/webapp/utils.py:18
↓ 3 callersMethodcopy
(self)
llmzoo/utils.py:60
↓ 3 callersFunctionget_default_conv_template
(model_name=None)
llmzoo/utils.py:79
↓ 3 callersMethodget_prompt
(self)
llmzoo/utils.py:36
↓ 3 callersMethodget_worker_status
(self, worker_name: str)
llmzoo/deploy/webapp/controller.py:93
↓ 3 callersMethodstyle
This method can be used to change the appearance of the Chatbot component.
llmzoo/deploy/webapp/gradio_patch.py:154
↓ 3 callersFunctionvote_last_response
(state, vote_type, model_selector, request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:104
↓ 2 callersFunction_tokenize_fn
(strings: Sequence[str], tokenizer: transformers.PreTrainedTokenizer)
llmzoo/datasets/datasets.py:122
↓ 2 callersFunctionapply_rotary_pos_emb
(q, k, cos, sin, position_ids)
llmzoo/deploy/webapp/monkey_patch_non_inplace.py:20
↓ 2 callersMethoddict
(self)
llmzoo/utils.py:69
↓ 2 callersFunctionget_conv_log_filename
()
llmzoo/deploy/webapp/gradio_web_server.py:54
↓ 2 callersMethodget_queue_length
(self)
llmzoo/deploy/webapp/model_worker.py:132
↓ 2 callersMethodget_status
(self)
llmzoo/deploy/webapp/model_worker.py:146
↓ 2 callersMethodget_worker_address
(self, model_name: str)
llmzoo/deploy/webapp/controller.py:125
↓ 2 callersFunctionload_model
( model_path, device, num_gpus, max_gpu_memory=None, load_8bit=False, load_4bit=False, debug=False )
llmzoo/deploy/webapp/inference.py:51
↓ 2 callersFunctionread_jsonl
(path: str, key: str = None)
llmzoo/eval/compute_metric_all.py:10
↓ 2 callersFunctionread_jsonl
(path: str, key: str = None)
llmzoo/eval/eval_gpt_review_all.py:87
↓ 2 callersMethodregister_to_controller
(self)
llmzoo/deploy/webapp/model_worker.py:92
↓ 2 callersMethodregister_worker
( self, worker_name: str, check_heart_beat: bool, worker_status: dict )
llmzoo/deploy/webapp/controller.py:69
↓ 2 callersMethodremove_worker
(self, worker_name: str)
llmzoo/deploy/webapp/controller.py:106
↓ 2 callersFunctionrotate_half
Rotates half the hidden dims of the input.
llmzoo/deploy/webapp/monkey_patch_non_inplace.py:13
↓ 2 callersFunctiontrain
()
train.py:40
↓ 1 callersFunction_add_speaker_and_signal
(header, source, get_conversation=True)
llmzoo/datasets/datasets.py:93
↓ 1 callersFunction_prepro_data_dict
(list_data_dict)
llmzoo/datasets/datasets.py:117
↓ 1 callersMethod_process_chat_messages
( self, chat_message: str | Tuple | List | Dict | None )
llmzoo/deploy/webapp/gradio_patch.py:97
↓ 1 callersFunctionapply_delta
(base_model_path, target_model_path, delta_path)
tools/apply_delta.py:13
↓ 1 callersFunctionbuild_demo
()
llmzoo/deploy/webapp/gradio_web_server.py:432
↓ 1 callersFunctionbuild_model
(model_args, training_args)
llmzoo/models/__init__.py:12
↓ 1 callersFunctionbuild_single_model_ui
()
llmzoo/deploy/webapp/gradio_web_server.py:318
↓ 1 callersFunctionchat_loop
( model_path: str, device: str, num_gpus: str, max_gpu_memory: str, lo
llmzoo/deploy/webapp/inference.py:221
↓ 1 callersFunctioncompress
Simulate group-wise quantization.
llmzoo/deploy/webapp/compression.py:52
↓ 1 callersFunctioncompress_module
(module, target_device)
llmzoo/deploy/webapp/compression.py:39
↓ 1 callersFunctiondecompress
Simulate group-wise dequantization.
llmzoo/deploy/webapp/compression.py:105
↓ 1 callersMethodfrom_str
(cls, name)
llmzoo/deploy/webapp/controller.py:32
↓ 1 callersMethodgenerate_stream_gate
(self, params)
llmzoo/deploy/webapp/model_worker.py:153
↓ 1 callersFunctionget_gpu_memory
(max_gpus=None)
llmzoo/deploy/webapp/inference.py:32
↓ 1 callersFunctionget_model_list
(controller_url)
llmzoo/deploy/webapp/gradio_web_server.py:60
↓ 1 callersMethodlist_models
(self)
llmzoo/deploy/webapp/controller.py:117
↓ 1 callersFunctionload_demo_single
(url_params)
llmzoo/deploy/webapp/gradio_web_server.py:80
↓ 1 callersFunctionmain
(args)
llmzoo/deploy/cli.py:93
↓ 1 callersFunctionmake_supervised_data_module
(tokenizer: transformers.PreTrainedTokenizer, data_args)
llmzoo/datasets/datasets.py:15
↓ 1 callersFunctionparse_order_cot
(review)
llmzoo/eval/eval_gpt_review_all.py:53
↓ 1 callersFunctionparse_score_cot
(review)
llmzoo/eval/eval_gpt_review_all.py:30
↓ 1 callersFunctionpost_process_code
(code)
llmzoo/deploy/webapp/gradio_web_server.py:172
↓ 1 callersFunctionpreprocess
( sources: Sequence[str], tokenizer: transformers.PreTrainedTokenizer )
llmzoo/datasets/datasets.py:62
↓ 1 callersFunctionpretty_print_semaphore
(semaphore)
llmzoo/deploy/webapp/utils.py:151
↓ 1 callersMethodprompt_for_input
Prompt for input from a role.
llmzoo/deploy/webapp/inference.py:209
↓ 1 callersMethodprompt_for_output
Prompt for output from a role.
llmzoo/deploy/webapp/inference.py:213
↓ 1 callersMethodreceive_heart_beat
(self, worker_name: str, queue_length: int)
llmzoo/deploy/webapp/controller.py:177
↓ 1 callersMethodrefresh_all_workers
(self)
llmzoo/deploy/webapp/controller.py:109
↓ 1 callersMethodremove_stable_workers_by_expiration
(self)
llmzoo/deploy/webapp/controller.py:187
↓ 1 callersFunctionreplace_llama_attn_with_flash_attn
()
llmzoo/models/llama/llama_flash_attn_monkey_patch.py:86
↓ 1 callersFunctionreplace_llama_attn_with_non_inplace_operations
Avoid bugs in mps backend by not using in-place operations.
llmzoo/deploy/webapp/monkey_patch_non_inplace.py:116
↓ 1 callersFunctionsafe_save_model_for_hf_trainer
(trainer: transformers.Trainer, output_dir: str)
llmzoo/utils.py:8
↓ 1 callersMethodsend_heart_beat
(self)
llmzoo/deploy/webapp/model_worker.py:104
↓ 1 callersFunctionset_global_vars
(controller_url_, enable_moderation_, models_)
llmzoo/deploy/webapp/gradio_web_server.py:47
↓ 1 callersFunctionsmart_tokenizer_and_embedding_resize
Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.
llmzoo/models/utils.py:6
↓ 1 callersMethodstream_output
Stream output.
llmzoo/deploy/webapp/inference.py:217
↓ 1 callersFunctionviolates_moderation
Check whether the text violates OpenAI moderation API.
llmzoo/deploy/webapp/utils.py:108
↓ 1 callersMethodworker_api_generate_stream
(self, params)
llmzoo/deploy/webapp/controller.py:197
↓ 1 callersMethodworker_api_get_status
(self)
llmzoo/deploy/webapp/controller.py:227
Method__call__
(self, instances: Sequence[Dict])
llmzoo/datasets/datasets.py:48
Method__getattr__
(self, attr)
llmzoo/deploy/webapp/utils.py:73
Method__getitem__
(self, i)
llmzoo/datasets/datasets.py:34
Method__init__
(self)
llmzoo/deploy/cli.py:36
Method__init__
( self, controller_addr, worker_addr, worker_id, n
llmzoo/deploy/webapp/model_worker.py:52
Method__init__
(self, logger, log_level=logging.INFO)
llmzoo/deploy/webapp/utils.py:67
Method__init__
Parameters: value: Default value to show in chatbot. If callable, the function will be called whenever the app loads to set the i
llmzoo/deploy/webapp/gradio_patch.py:26
Method__init__
(self, weight, bias, device)
llmzoo/deploy/webapp/compression.py:28
Method__init__
(self, dispatch_method: str)
llmzoo/deploy/webapp/controller.py:57
Method__init__
(self, data_path: str, tokenizer: transformers.PreTrainedTokenizer, )
llmzoo/datasets/datasets.py:23
Method__len__
(self)
llmzoo/datasets/datasets.py:31
Function_prepare_decoder_attention_mask
(self, attention_mask, input_shape, inputs_embeds, past_key_values_length)
llmzoo/models/llama/llama_flash_attn_monkey_patch.py:80
Functionadd_text
(state, text, request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:147
Functionapi_generate_stream
(request: Request)
llmzoo/deploy/webapp/model_worker.py:184
Functionapi_get_status
(request: Request)
llmzoo/deploy/webapp/model_worker.py:199
Functionclean_flant5_ckpt
(ckpt_path)
llmzoo/deploy/webapp/utils.py:133
Functionclear_history
(request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:141
Functioncompletions_with_backoff
(**kwargs)
llmzoo/eval/prompt_turbo.py:14
Functiondisable_torch_init
Disable the redundant torch default initialization to accelerate model creation.
llmzoo/deploy/webapp/utils.py:98
Functiondownvote_last_response
(state, model_selector, request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:122
Functionflag_last_response
(state, model_selector, request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:128
Methodflush
(self)
llmzoo/deploy/webapp/utils.py:91
Functionforward
( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None,
llmzoo/deploy/webapp/monkey_patch_non_inplace.py:30
Functionforward
Input shape: Batch x Time x Channel attention_mask: [bsz, q_len]
llmzoo/models/llama/llama_flash_attn_monkey_patch.py:11
Methodforward
(self, input: Tensor)
llmzoo/deploy/webapp/compression.py:34
Functiongenerate_stream
(model, tokenizer, params, device, context_len=2048, stream_interval=2)
llmzoo/deploy/webapp/inference.py:113
Methodget_config
(self)
llmzoo/deploy/webapp/gradio_patch.py:74
Functionget_eval
(content: str, max_tokens: int)
llmzoo/eval/eval_gpt_review_all.py:14
Functionget_worker_address
(request: Request)
llmzoo/deploy/webapp/controller.py:269
Functionheart_beat_controller
(controller)
llmzoo/deploy/webapp/controller.py:50
Functionheart_beat_worker
(controller)
llmzoo/deploy/webapp/model_worker.py:45
Functionhttp_bot
(state, model_selector, temperature, max_new_tokens, request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:183
Functionlist_models
()
llmzoo/deploy/webapp/controller.py:263
Functionload_demo
(url_params, request: gr.Request)
llmzoo/deploy/webapp/gradio_web_server.py:99
Methodpostprocess
Parameters: y: List of tuples representing the message and response pairs. Each message and response should be a string, which ma
llmzoo/deploy/webapp/gradio_patch.py:121
next →1–100 of 114, ranked by callers