An abstract Formatter that enforces a format on the string generated by a language model. More...
Public Member Functions | |
| accept_token (self, int token_id) | |
| Accept a token from the language model. | |
| None | accept_bytes (self, bytes _bytes) |
| Accept a bytes object from the language model. | |
| None | compute_allowed_tokens (self) |
| Compute the allowed tokens based on the current state. | |
| typing.Any | mask_logits (self, logits) |
| Mask the logits based on the current state. | |
| typing.Sequence[int] | get_allowed_tokens_since_last_computation (self) |
Get the allowed tokens since the last computation(in other words, the last call to compute_allowed_tokens). | |
| bool | is_completed (self) |
| Check if the generated string satisfies the format and hence the generation is completed. | |
| dict[str, typing.Any|None] | captures (self) |
| None | reset (self) |
| Reset the formatter to the initial state. | |
Protected Member Functions | |
| None | _on_completion (self, str generated_output) |
| Perform actions when the generation is completed. | |
Detailed Description
An abstract Formatter that enforces a format on the string generated by a language model.
Definition at line 24 of file formatter.py.
Member Function Documentation
◆ _on_completion()
|
protected |
Perform actions when the generation is completed.
Reimplemented in formatron.formatter.Formatter.
Definition at line 80 of file formatter.py.
◆ accept_bytes()
| None formatron.formatter.FormatterBase.accept_bytes | ( | self, | |
| bytes | _bytes ) |
Accept a bytes object from the language model.
- Parameters
-
_bytes The bytes object.
Reimplemented in formatron.formatter.Formatter.
Definition at line 42 of file formatter.py.
◆ accept_token()
| formatron.formatter.FormatterBase.accept_token | ( | self, | |
| int | token_id ) |
Accept a token from the language model.
- Parameters
-
token_id The token ID.
- Returns
- The result of accepting the token.
Reimplemented in formatron.formatter.Formatter.
Definition at line 34 of file formatter.py.
◆ captures()
| dict[str, typing.Any|None] formatron.formatter.FormatterBase.captures | ( | self | ) |
Reimplemented in formatron.formatter.Formatter.
Definition at line 98 of file formatter.py.
◆ compute_allowed_tokens()
| None formatron.formatter.FormatterBase.compute_allowed_tokens | ( | self | ) |
Compute the allowed tokens based on the current state.
Reimplemented in formatron.formatter.Formatter.
Definition at line 48 of file formatter.py.
◆ get_allowed_tokens_since_last_computation()
| typing.Sequence[int] formatron.formatter.FormatterBase.get_allowed_tokens_since_last_computation | ( | self | ) |
Get the allowed tokens since the last computation(in other words, the last call to compute_allowed_tokens).
- Returns
- The allowed tokens.
Reimplemented in formatron.formatter.Formatter.
Definition at line 66 of file formatter.py.
◆ is_completed()
| bool formatron.formatter.FormatterBase.is_completed | ( | self | ) |
Check if the generated string satisfies the format and hence the generation is completed.
Reimplemented in formatron.formatter.Formatter.
Definition at line 72 of file formatter.py.
◆ mask_logits()
| typing.Any formatron.formatter.FormatterBase.mask_logits | ( | self, | |
| logits ) |
Mask the logits based on the current state.
- Parameters
-
logits The logits to mask.
- Returns
- The masked logits.
Reimplemented in formatron.formatter.Formatter.
Definition at line 58 of file formatter.py.
◆ reset()
| None formatron.formatter.FormatterBase.reset | ( | self | ) |
Reset the formatter to the initial state.
Reimplemented in formatron.formatter.Formatter.
Definition at line 104 of file formatter.py.
The documentation for this class was generated from the following file:
- src/formatron/formatter.py
