transformers/tests
Marc Sun 55db70c63d
GPTQ integration (#25062)
* GTPQ integration

* Add tests for gptq

* support for more quantization model

* fix style

* typo

* fix method

* Update src/transformers/modeling_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* add dataclass and fix quantization_method

* fix doc

* Update tests/quantization/gptq/test_gptq.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* modify dataclass

* add gtpqconfig import

* fix typo

* fix tests

* remove dataset as req arg

* remove tokenizer import

* add offload cpu quantization test

* fix check dataset

* modify dockerfile

* protect trainer

* style

* test for config

* add more log

* overwrite torch_dtype

* draft doc

* modify quantization_config docstring

* fix class name in docstring

* Apply suggestions from code review

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* more warning

* fix 8bit kwargs tests

* peft compatibility

* remove var

* fix is_gptq_quantized

* remove is_gptq_quantized

* fix wrap

* Update src/transformers/modeling_utils.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* add exllama

* skip test

* overwrite float16

* style

* fix skip test

* Apply suggestions from code review

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* fix docsting formatting

* add doc

* better test

---------

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
2023-08-10 16:06:29 -04:00
..
benchmark [Test refactor 1/5] Per-folder tests reorganization (#15725) 2022-02-23 15:46:28 -05:00
bettertransformer Add methods to PreTrainedModel to use PyTorch's BetterTransformer (#21259) 2023-04-27 11:03:42 +02:00
deepspeed accelerate deepspeed and gradient accumulation integrate (#23236) 2023-05-31 15:16:22 +05:30
extended [tests] switch to torchrun (#22712) 2023-04-12 08:25:45 -07:00
fixtures [WIP] add SpeechT5 model (#18922) 2023-02-03 12:43:46 -05:00
generation Generation: strict generation config validation at save time (#25411) 2023-08-10 10:42:34 +01:00
models Update Bark generation configs and tests (#25409) 2023-08-09 18:28:02 +02:00
optimization Make schedulers picklable by making lr_lambda fns global (#21768) 2023-03-02 12:08:43 -05:00
pipelines [ASR Pipeline] Clarify return timestamps (#25344) 2023-08-08 10:16:00 +01:00
quantization GPTQ integration (#25062) 2023-08-10 16:06:29 -04:00
repo_utils Document check copies (#25291) 2023-08-04 14:56:29 +02:00
sagemaker Avoid invalid escape sequences, use raw strings (#22936) 2023-04-25 09:17:56 -04:00
tokenization [ PreTrainedTokenizerFast] Keep properties from fast tokenizer (#25053) 2023-07-25 18:45:01 +02:00
tools Add support for for loops in python interpreter (#24429) 2023-06-26 09:58:14 -04:00
trainer Migrate Trainer from Repository to upload_folder (#25095) 2023-08-07 17:47:22 +02:00
utils Enable passing number of channels when inferring data format (#25412) 2023-08-09 17:41:21 +01:00
__init__.py GPU text generation: mMoved the encoded_prompt to correct device 2020-01-06 15:11:12 +01:00
test_backbone_common.py Add TimmBackbone model (#22619) 2023-06-06 17:11:30 +01:00
test_configuration_common.py Deal with nested configs better in base class (#25237) 2023-08-04 14:56:09 +02:00
test_configuration_utils.py Deal with nested configs better in base class (#25237) 2023-08-04 14:56:09 +02:00
test_feature_extraction_common.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00
test_feature_extraction_utils.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00
test_image_processing_common.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00
test_image_processing_utils.py Run hub tests (#24807) 2023-07-13 15:25:45 -04:00
test_image_transforms.py Bug fix - flip_channel_order for channels first images (#23701) 2023-05-31 17:12:27 +01:00
test_modeling_common.py Fix test_model_parallelism (#25359) 2023-08-08 10:48:45 +02:00
test_modeling_flax_common.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00
test_modeling_flax_utils.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00
test_modeling_tf_common.py Speed up TF tests by reducing hidden layer counts (#24595) 2023-06-30 16:30:33 +01:00
test_modeling_tf_utils.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00
test_modeling_utils.py Generate: Load generation config when device_map is passed (#25413) 2023-08-10 10:54:26 +01:00
test_pipeline_mixin.py Update tiny models for pipeline testing. (#24364) 2023-06-20 14:43:10 +02:00
test_sequence_feature_extraction_common.py Apply ruff flake8-comprehensions (#21694) 2023-02-22 09:14:54 +01:00
test_tokenization_common.py Fix TypeError: Object of type int64 is not JSON serializable (#24340) 2023-06-27 12:15:49 +01:00
test_tokenization_utils.py Split common test from core tests (#24284) 2023-06-15 07:30:24 -04:00