Functions — github.com/anarchy-ai/LLM-VM

hub / github.com/anarchy-ai/LLM-VM / functions

Functions280 in github.com/anarchy-ai/LLM-VM

⨍ Functions 280◇ Types & classes 98 ↳ Endpoints 2

↓ 1 callersMethodget_training_in_progress_set_true

(self, c_id)

src/llm_vm/completion/optimize.py:82

↓ 1 callersFunctionget_training_tool_subset

( list_of_tools: ToolList, tool_id_always_returned: Union[int, None], max_num_elements: int = 6 )

src/llm_vm/agents/FLAT/agent_helper/tool_utils.py:61

↓ 1 callersMethodgpu_model_loader

(self, vram=0, **kwargs)

src/llm_vm/onsite_llm.py:943

↓ 1 callersFunctionisValidIP

(ip)

src/llm_vm/config.py:56

↓ 1 callersMethodlora_finetune

(self, data, optimizer, c_id, model_filename=None)

src/llm_vm/onsite_llm.py:220

↓ 1 callersMethodmakeToolDesc

Creates the tool description to contain the relevant tags according to the dynamic params Parameters ---------- tool

src/llm_vm/agents/REBEL/agent.py:193

↓ 1 callersFunctionmake_interaction_request

(human_question, ai_response, data, Q = L_QUESTION, A = L_ANSWER, D = L_ANSWER_DATA, INTERACTION = L_INTERACTI

src/llm_vm/agents/FLAT/agent_helper/utils.py:82

↓ 1 callersMethodmake_sub

Formats the tool description to contain the relevant tags according to the dynamic params Parameters ---------- tool

src/llm_vm/agents/REBEL/agent.py:337

↓ 1 callersFunctionmemory_check

(memory,question)

src/llm_vm/agents/REBEL/bothandler.py:99

↓ 1 callersFunctionmetric

()

eval_finetuned.py:53

↓ 1 callersMethodmodel_loader

(self)

src/llm_vm/onsite_llm.py:130

↓ 1 callersMethodmodel_loader

(self, **kwargs)

src/llm_vm/onsite_llm.py:934

↓ 1 callersMethodparse_grammar

(self)

src/llm_vm/guided_completion.py:273

↓ 1 callersFunctionpick_tool

(tools_list, question, conversation_history, use_fine_tuned_model = True, debug_prompt = False)

src/llm_vm/agents/FLAT/agent_helper/bothandler.py:51

↓ 1 callersFunctionprompt_for_instructions

(instructions: str)

src/llm_vm/agents/FLAT/agent_helper/tool_utils.py:52

↓ 1 callersFunctionpromptf

( question: str, factual_memory: TupleList, tools: ToolList, bot_instructions: str, verbos

src/llm_vm/agents/FLAT/agent_helper/business_logic.py:68

↓ 1 callersMethodpromptf

Formats the gpt prompt to include conversation history, facts and logs responses to the console Parameters ----------

src/llm_vm/agents/REBEL/agent.py:427

↓ 1 callersMethodqlora_finetune

(self, data, optimizer, c_id, model_filename=None)

src/llm_vm/onsite_llm.py:301

↓ 1 callersFunctionquestion_split

(question,tools_list,memory)

src/llm_vm/agents/REBEL/bothandler.py:36

↓ 1 callersFunctionquestion_split

(question_to_split, use_fine_tuned_model = True)

src/llm_vm/agents/FLAT/agent_helper/bothandler.py:17

↓ 1 callersFunctionrebel_main

()

src/llm_vm/agents/REBEL/agent.py:583

↓ 1 callersMethodregex_completion

(regex)

src/llm_vm/guided_completion.py:54

↓ 1 callersFunctionremove_similars

(similars_list, tolerance = 3)

src/llm_vm/agents/FLAT/agent_helper/utils.py:67

↓ 1 callersFunctionremove_tags_from_html_string

(html_string)

src/llm_vm/agents/FLAT/agent_helper/utils.py:28

↓ 1 callersFunctionreplace_variables_for_values

( my_dict: dict, dynamic_keys, ignore_key: str = "_______" )

src/llm_vm/agents/REBEL/utils.py:145

↓ 1 callersFunctionreplace_variables_for_values

(my_dict: dict, dynamic_keys: dict, ignore_key: str = "_______")

src/llm_vm/agents/FLAT/agent_helper/replacer.py:17

↓ 1 callersFunctionrun_test_stub

()

tests/test_optimize.py:102

↓ 1 callersFunctionserver_entry_point

This function launches the server with specified parameters Parameters: host (str): Network IP address port (int): Port N

src/llm_vm/server/main.py:24

↓ 1 callersFunctiontidy_up_subquestions

(subquestions_str, main_question)

src/llm_vm/agents/FLAT/agent_helper/utils.py:109

↓ 1 callersMethodtokenizer_loader

(self)

src/llm_vm/onsite_llm.py:134

↓ 1 callersFunctiontool_api_call

(self, tool, gpt_suggested_input, question, memory, facts, query="")

src/llm_vm/agents/REBEL/utils.py:168

↓ 1 callersFunctiontool_picker

(tools_list, question, starting_tool_num)

src/llm_vm/agents/REBEL/bothandler.py:6

↓ 1 callersMethodtype_completion

(type_name)

src/llm_vm/guided_completion.py:62

↓ 1 callersFunctionuse_tool

( tool: SingleTool, gpt_suggested_input: dict, question: str, memory: TupleList, verbose:

src/llm_vm/agents/FLAT/agent_helper/use_tool.py:28

↓ 1 callersMethoduse_tool

Calls the appropriate API based on the tool that's in use. Parameters ---------- tool an integer refenci

src/llm_vm/agents/REBEL/agent.py:249

MethodCALL_BIG

(self, prompt, max_len=256, **kwargs)

src/llm_vm/client.py:100

MethodCALL_SMALL

(prompt, max_len=256, **kwargs)

src/llm_vm/client.py:87

MethodRAG_complete

This function is Anarchy's completion entry point Parameters: prompt (str): Prompt to send to LLM for generation

src/llm_vm/client.py:249

FunctionRegisterModelClass

(name)

src/llm_vm/onsite_llm.py:55

Method__call__

(self, input_ids, scores)

src/llm_vm/guided_completion.py:388

src/llm_vm/agents/REBEL/test_agent.py:25

src/llm_vm/agents/REBEL/test_agent.py:35

Method__getitem__

(self, idx)

src/llm_vm/onsite_llm.py:89

Method__init__

(self, suppress_stdout=False, suppress_stderr=False)

eval_finetuned.py:11

Method__init__

(self, model = default_big_model, model_config = {}, openai_key = None)

src/llm_vm/client.py:33

Method__init__

This __init__ function allows the user to specify which LLM they want to use upon instantiation. Parameters: big_model (

src/llm_vm/client.py:54

Method__init__

(self, api_key, pinecone_env)

src/llm_vm/vector_db.py:37

Method__init__

(self, api_key, cluster_url)

src/llm_vm/vector_db.py:76

Method__init__

Parameters: ----------- generator (Callable[[Transformers, ...generator_args], None]): Generator function to be use

src/llm_vm/guided_completion.py:38

Method__init__

(self, model_uri, tokenizer, grammar_type='python')

src/llm_vm/guided_completion.py:73

Method__init__

(self, model_uri, tokenizer)

src/llm_vm/guided_completion.py:127

Method__init__

(self, constraint_class, terminals_map)

src/llm_vm/guided_completion.py:383

Method__init__

(self,iterable_dataset,length)

src/llm_vm/onsite_llm.py:84

Method__init__

(self,model_uri=None, tokenizer_kw_args={}, model_kw_args={}, dtype=None)

src/llm_vm/onsite_llm.py:93

Method__init__

(self, with_GPU=False, **model_kwargs)

src/llm_vm/onsite_llm.py:901

Method__init__

(self, variance, examples_to_generate, seed_examples=10)

src/llm_vm/completion/data_synthesis.py:14

Method__init__

(self)

src/llm_vm/completion/optimize.py:59

Method__init__

(self, anarchy_key, openai_key, MIN_TRAIN_EXS=20, MAX_TRAIN_EXS = 2000)

src/llm_vm/completion/optimize.py:138

Method__init__

(self, storage=LocalEphemeral(), MIN_TRAIN_EXS = 1, MAX_TRAIN_EXS = 2000, call_small = None , call_big = None

src/llm_vm/completion/optimize.py:179

Method__init__

(self)

src/llm_vm/utils/ram.py:8

Method__init__

(self, openai_key, tools, bot_str="", verbose=4)

src/llm_vm/agents/REBEL/agent.py:180

Method__init__

(self, suppress_stdout=False, suppress_stderr=False)

src/llm_vm/agents/REBEL/test_agent.py:19

Method__init__

(self, openai_key, tools = None, bot_instructions = "", verbose = 4)

src/llm_vm/agents/FLAT/agent.py:15

Method__len__

(self)

src/llm_vm/onsite_llm.py:87

Function__use_tool

(tool_id: int, shuffle_value: int = 0, shuffle_modulo: int = 1e9)

src/llm_vm/agents/FLAT/models/utils/tool_picker_model/tool_picker_model_data.py:9

Methodactual_train

(use_completion = None)

src/llm_vm/completion/optimize.py:261

Methodadd_prop

(self, class_name, prop)

src/llm_vm/vector_db.py:123

Functionanarchy_client

(prompt, context, openai_key=None, temperature=0.0

examples/quickstart_interface.py:7

Functionanswer_from_memory_jsonl

()

src/llm_vm/agents/FLAT/models/utils/answer_from_memory_model/get_asm_as_jsonl.py:22

Methodasync_lora

()

src/llm_vm/onsite_llm.py:221

Methodasync_qlora

()

src/llm_vm/onsite_llm.py:302

Methodasynctune

()

src/llm_vm/onsite_llm.py:171

Functioncall_gpt

( state, cur_prompt: str, stop: str, max_tokens=20, quality="best", temperature=0.0 )

src/llm_vm/agents/REBEL/utils.py:77

Functionclient_build

(type = "inference", openai_key = None, big_model = default_big_model, small_model =default_small_model,big_mo

src/llm_vm/client.py:25

Methodcomplete

(self, prompt, max_len=256, **kwargs)

src/llm_vm/client.py:37

Methodcomplete

(self, prompt)

src/llm_vm/guided_completion.py:19

Methodcomplete

(self, prompt)

src/llm_vm/guided_completion.py:50

Methodcomplete

(self, prompt, **model_kwargs)

src/llm_vm/guided_completion.py:91

Methodcomplete

TODO: Runs the optimizing completion process on anarchy's hosted server with persistence. Parameters: ---------- - s

src/llm_vm/completion/optimize.py:144

Methodconstruct_filter_set

(self, expression)

src/llm_vm/guided_completion.py:135

Methodconstruct_filter_set

(self, expression)

src/llm_vm/guided_completion.py:159

Methodconstruct_final_filter_set

(self, prefix_ids, terminals_map)

src/llm_vm/guided_completion.py:221

Functioncos_similarity

return cosine similarity between two lists

eval_finetuned.py:41

Methodcreate

(grammar_type, model_uri, tokenizer)

src/llm_vm/guided_completion.py:143

Methodcreate_index

(self, **kwargs)

src/llm_vm/vector_db.py:43

Methodcreate_index

(self, class_name, class_properties=[], distance="cosine", emb_model="text2vec-openai", mod_config=None)

src/llm_vm/vector_db.py:81

Functioncreate_jsonl_file

(data_list)

src/llm_vm/completion/optimize.py:311

Methodcreate_pinecone_index

(self, **kwargs)

src/llm_vm/client.py:239

Functiondeep_fmap

(lambdaFunc, json_data)

src/llm_vm/agents/REBEL/utils.py:129

Methoddelete_index

(self, index_name)

src/llm_vm/vector_db.py:60

Methoddelete_index

(self, class_name)

src/llm_vm/vector_db.py:101

Functiondelete_model

(model_name: str)

src/llm_vm/agents/FLAT/models/helpers/delete_model.py:4

Methoddescribe_index

(self, index_name)

src/llm_vm/vector_db.py:57

Methoddescribe_index

(self, class_name)

src/llm_vm/vector_db.py:98

Methodeos_token_id

(self)

src/llm_vm/guided_completion.py:88

Functionexit_handler

(signum, frame)

src/llm_vm/completion/optimize.py:22

Methodfinetune

(self, dataset, optimizer, c_id, small_model_filename=None)

src/llm_vm/onsite_llm.py:821

Methodfinetune

(self, dataset, optimizer, c_id, small_model_filename=None)

src/llm_vm/onsite_llm.py:857

← previous next →101–200 of 280, ranked by callers