transformers/tests/generation
Yu Chin Fabian Lim 9613933b02
Add the Bamba Model (#34982)
* initial commit for PR

Co-authored-by: Gabe Goodhart <gabe.l.hart@gmail.com>

* rename dynamic cache

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* add more unit tests

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* add integration test

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* add integration test

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* Add modular bamba file

* Remove trainer changes from unrelated PR

* Modify modular and cofig to get model running

* Fix some CI errors and beam search

* Fix a plethora of bugs from CI/docs/etc

* Add bamba to models with special caches

* Updat to newer mamba PR for mamba sublayer

* fix test_left_padding_compatibility

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* fix style

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* fix remaining tests

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* missed this test

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* ran make style

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* move slow tag to integration obj

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* make style

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* address comments

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* fix modular

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* left out one part of modular

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* change model

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* Make Rotary modular as well

* Update bamba.md

Added overview, update Model inference card and added config

* Update bamba.md

* Update bamba.md

* Update bamba.md

Minor fixes

* Add docs for config and model back

Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>

* Add warning when using fast kernels

* replaced generate example

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>

* Address comments from PR

Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>

* Propagate attention fixes

Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>

* Fix attention interfaces to the new API

Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>

* Fix API for decoder layer

Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>

* Remove extra weights

Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>

---------

Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Co-authored-by: Gabe Goodhart <gabe.l.hart@gmail.com>
Co-authored-by: Antoni Viros i Martin <aviros@ibm.com>
Co-authored-by: divya-kumari32 <72085811+divya-kumari32@users.noreply.github.com>
Co-authored-by: Antoni Viros <ani300@gmail.com>
2024-12-18 20:18:17 +01:00
..
__init__.py [Test refactor 1/5] Per-folder tests reorganization (#15725) 2022-02-23 15:46:28 -05:00
test_beam_constraints.py Generate: move generation_*.py src files into generation/*.py (#20096) 2022-11-09 15:34:08 +00:00
test_beam_search.py Time to Say Goodbye, torch 1.7 and 1.8 (#22291) 2023-03-21 19:22:01 +01:00
test_candidate_generator.py Refactoring AssistedCandidateGenerator for Improved Modularity and Reusability (#35009) 2024-12-12 15:47:05 +01:00
test_configuration_utils.py Fix flaky Hub CI (test_trainer.py) (#35062) 2024-12-05 17:02:27 +01:00
test_flax_logits_process.py Adding FlaxNoRepeatNGramLogitsProcessor (#29677) 2024-04-02 11:39:33 +02:00
test_flax_utils.py Fix CI (#34458) 2024-10-29 08:26:04 +01:00
test_framework_agnostic.py Generation: fix handling of special tokens (#31254) 2024-06-06 15:21:32 +05:00
test_fsdp.py Default synced_gpus to True when using FullyShardedDataParallel (#33483) 2024-10-10 14:09:04 -04:00
test_logits_process.py Add SynthID (watermerking by Google DeepMind) (#34350) 2024-10-23 21:18:52 +01:00
test_stopping_criteria.py Dynamic number of speculative tokens in order to accelerate speculative decoding (#33258) 2024-09-11 14:22:28 +02:00
test_streamers.py Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
test_tf_logits_process.py fix: multilingual midel convert to tflite get wrong token (#32079) 2024-08-27 11:44:09 +02:00
test_tf_utils.py Revert workaround for TF safetensors loading (#30128) 2024-04-09 11:04:18 +01:00
test_utils.py Add the Bamba Model (#34982) 2024-12-18 20:18:17 +01:00