Daniel Korat
fb0c6b521d
Universal Assisted Generation: Assisted generation with any assistant model (by Intel Labs) (#33383)
* Update candidate_generator.py
* Update utils.py
* add lookbehind params to _get_candidate_generator
* make fixup
* add unit tests
* fix failing tests
* add docstrings
* fix docstrings; remove non-optimized AnyTokenizer
* added any tokenizer generation correctness test
* make fixup
* fix assertion syntax
* PR review fixes
* address additional PR comments
* fix tests
* remove stropping criteria arg
* make fixup
* add AssistantConfig
* fix prev_tokens branching
* pass tokenizers through `generate()`kwargs
* fix lookbehind values; tokenizer params WIP
* fixup
* AssistantConfig
* remove AssistantConfig; apply PR suggestions
* restructure tests
* fixup
* fix assistant_tokenizer arg validation
* fixup
* fix tests in TestAssistedCandidateGeneratorDifferentTokenizers
* fix class docstring
* PR suggestions
* doc
* doc update and improvements to `_validate_assistant()`
---------
Co-authored-by: mosheber <moshe.berchansky@intel.com>
2024-10-10 14:41:53 +02:00
..
2024-10-09 14:51:19 -07:00
2024-06-26 21:59:08 +01:00
2024-10-10 14:41:53 +02:00
2024-10-02 14:08:46 +01:00
2024-10-02 14:08:46 +01:00
2024-04-16 11:58:55 +02:00
2024-08-26 13:15:43 +02:00
2024-10-08 14:26:43 +02:00
2024-10-09 11:55:07 -07:00
2024-04-23 16:06:20 +01:00
2024-10-02 14:08:46 +01:00
2024-10-02 14:08:46 +01:00
2023-11-08 08:35:20 -05:00
2024-10-02 14:08:46 +01:00
2024-04-08 14:21:16 +01:00