* Add draft model param to llama class, implement basic prompt lookup decoding draft model
* Use samplingcontext for sampling
* Use 1d array
* Use draft model for sampling
* Fix dumb mistake
* Allow for later extensions to the LlamaDraftModel api
* Cleanup
* Adaptive candidate prediction
* Update implementation to match hf transformers
* Tuning
* Fix bug where last token was not used for ngram prediction
* Remove heuristic for num_pred_tokens (no benefit)
* fix: n_candidates bug.
* Add draft_model_num_pred_tokens server setting
* Cleanup
* Update README
* feat: Add support for jinja templating
Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
* fix: Refactor chat formatter and update interface for jinja templates
- Simplify the `llama2_template` in `llama_jinja_format.py` by removing unnecessary line breaks for readability without affecting functionality.
- Update `ChatFormatterInterface` constructor to accept a more generic `Optional[object]` type for the template parameter, enhancing flexibility.
- Introduce a `template` property to `ChatFormatterInterface` for standardized access to the template string.
- Replace `MetaSingleton` metaclass with `Singleton` for the `ChatFormatterFactory` to streamline the singleton implementation.
These changes enhance code readability, maintain usability, and ensure consistency in the chat formatter's design pattern usage.
* Add outline for Jinja2 templating integration documentation
Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
* Add jinja2 as a dependency with version range for Hugging Face transformers compatibility
Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
* Update jinja2 version constraint for mkdocs-material compatibility
Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
* Fix attribute name in AutoChatFormatter
- Changed attribute name from `self._renderer` to `self._environment`
---------
Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
* Do not set `grammar` to `None` for new `LlamaGrammar` objects
The `grammar` attribute is written by `init()`, but that method always
returns `None`, so `__init__()` would then discard the previously
written object.
* Add minimal test for grammar parsing
* Add low-level batching notebook
* fix: tokenization of special characters: (#850)
It should behave like llama.cpp, where most out of the box usages
treat special characters accordingly
* Update CHANGELOG
* Cleanup
* Fix runner label
* Update notebook
* Use llama_decode and batch api
* Support logits_all parameter
---------
Co-authored-by: Antoine Lizee <antoine.lizee@gmail.com>
Define an init_llama function that starts llama with supplied settings instead of just doing it in the global context of app.py
This allows the test to be less brittle by not needing to mess with os.environ, then importing the app
