prompt_strategies.alpaca_w_system

prompt_strategies.alpaca_w_system

Prompt strategies loader for alpaca instruction datasets with system prompts

Classes

Name	Description
InstructionWSystemPromptTokenizingStrategy	Tokenizing strategy for instruction-based prompts.
OpenOrcaPromptTokenizingStrategy	Tokenizing strategy for OpenOrca datasets
OpenOrcaSystemDataPrompter	Alpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts
SystemDataPrompter	Alpaca Style Prompter that uses system prompts from the dataset

InstructionWSystemPromptTokenizingStrategy

prompt_strategies.alpaca_w_system.InstructionWSystemPromptTokenizingStrategy(
    self,
    prompter,
    tokenizer,
    train_on_inputs=False,
    sequence_len=2048,
)

Tokenizing strategy for instruction-based prompts.

OpenOrcaPromptTokenizingStrategy

prompt_strategies.alpaca_w_system.OpenOrcaPromptTokenizingStrategy(
    self,
    prompter,
    tokenizer,
    train_on_inputs=False,
    sequence_len=2048,
)

Tokenizing strategy for OpenOrca datasets

OpenOrcaSystemDataPrompter

prompt_strategies.alpaca_w_system.OpenOrcaSystemDataPrompter(
    self,
    prompt_style=PromptStyle.INSTRUCT.value,
)

Alpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts

SystemDataPrompter

prompt_strategies.alpaca_w_system.SystemDataPrompter(
    self,
    prompt_style=PromptStyle.INSTRUCT.value,
)

Alpaca Style Prompter that uses system prompts from the dataset