-
### 🚀 The feature, motivation and pitch
While we already have `Outlines` and `lm-format-enforcer` integration, they are implemented purely in Python and may suffer from Python interpreter overhead li…
-
### Feature request
It would be nice to constrain the model output with a CFG directly when calling `model.generate`.
This is already done by llama.cpp [grammars](https://github.com/ggerganov/ll…
-
Opening a new issue to further discuss the [comment in #164](https://github.com/waycrate/swhkd/issues/164#issuecomment-1280376134)
> I am planning to write a formal grammar for the config, but have…
-
Hi @lbeurerkellner,
Do you have any plans to "natively" integrate token constraint into the lmql language, perhaps through ATLR/Lark/ENBF grammar notation? This is a feature currently supported by …
-
-
**Note**: Only take this ticket if you experience in context-free grammars.
**Problem**: Umpires write different scoring formulae for open season each game. This has been done directly in a Python…
-
I found log-bmm very useful for linear-chain CRF to save memory and speed up, while in context-free grammars, A->BC requires amounts of GPU memories, which is more serious. So it is difficult to incre…
-
TODO: remove lexical rules (only syntactic ones remain)
-
There are type of programs that accept data matching context-free grammars: compilers, parsers etc.
These programs can be easily tested using property-based approach with generator of strings matchin…
-
In [Json Schema](https://json-schema.org/draft/2020-12/json-schema-validation) and [Pydantic Fields](https://docs.pydantic.dev/latest/concepts/fields/#numeric-constraints) a lot of non type-level cons…