Formatron v0.4.9
Formatron empowers everyone to control the output format of language models with minimal overhead.
|
This module integrates the ExLlamaV2 library by providing convenience utilities. More...
Classes | |
class | FormatterFilter |
ExLlamaV2Filter that uses a formatter to mask logits. More... | |
Functions | |
kbnf.Vocabulary | create_engine_vocabulary (ExLlamaV2Tokenizer tokenizer, typing.Optional[list[typing.Callable]] vocab_processors=None) |
Create a vocabulary for the KBNF engine. | |
ExLlamaV2Filter | create_formatter_filter (ExLlamaV2 model, ExLlamaV2Tokenizer tokenizer, FormatterBuilder formatter_builder, EngineGenerationConfig engine_config=None, typing.Optional[list[typing.Callable]] vocab_processors=None) |
Create a formatter filter for the ExLlamaV2 engine. | |
This module integrates the ExLlamaV2 library by providing convenience utilities.
kbnf.Vocabulary formatron.integrations.exllamav2.create_engine_vocabulary | ( | ExLlamaV2Tokenizer | tokenizer, |
typing.Optional[list[typing.Callable]] | vocab_processors = None ) |
Create a vocabulary for the KBNF engine.
tokenizer | The tokenizer. |
vocab_processors | List of callables with signature (token_to_char: typing.Dict[bytes, bytes])->None. Callables can be used to "unmangle" encoded characters to original characters. If None, processors will be auto-detected. |
Definition at line 24 of file exllamav2.py.
ExLlamaV2Filter formatron.integrations.exllamav2.create_formatter_filter | ( | ExLlamaV2 | model, |
ExLlamaV2Tokenizer | tokenizer, | ||
FormatterBuilder | formatter_builder, | ||
EngineGenerationConfig | engine_config = None, | ||
typing.Optional[list[typing.Callable]] | vocab_processors = None ) |
Create a formatter filter for the ExLlamaV2 engine.
model | The ExLlamaV2 model. |
tokenizer | The ExLlamaV2 tokenizer. |
formatter_builder | The formatter builder. |
engine_config | The engine generation configuration. |
vocab_processors | List of callables with signature (token_to_char: typing.Dict[bytes, bytes])->None. Callables can be used to "unmangle" encoded characters to original characters. If None, processors will be auto-detected. |
Definition at line 46 of file exllamav2.py.