* Let's try autodetecting serving sigs
* Don't clobber existing sigs
* Change shapes for multiplechoice models
* Make default dummy inputs smarter too
* Fix missing f-string
* Let's YOLO a serving output too
* Read __class__.__name__ properly
* Don't just pass naked lists in there and expect it to be okay
* Code cleanup
* Update default serving sig
* Clearer error messages
* Further updates to the default serving output
* make fixup
* Update the serving output a bit more
* Cleanups and renames, raise errors appropriately when we can't infer inputs
* More renames
* we're building in a functional context again, yolo
* import DUMMY_INPUTS from the right place
* import DUMMY_INPUTS from the right place
* Support cross-attention in the dummies
* Support cross-attention in the dummies
* Complete removal of dummy/serving overrides in BERT
* Complete removal of dummy/serving overrides in RoBERTa
* Obliterate lots and lots of serving sig and dummy overrides
* merge type hint changes
* Fix for token_type_ids with vocab_size 1
* Add missing property decorator
* Fix T5 and hopefully some models that take conv inputs
* More signature pruning
* Fix T5's signature
* Fix Wav2Vec2 signature
* Fix LongformerForMultipleChoice input signature
* Fix BLIP and LED
* Better default serving output error handling
* Fix BART dummies
* Fix dummies for cross-attention, esp encoder-decoder models
* Fix visionencoderdecoder signature
* Fix BLIP serving output
* Small tweak to BART dummies
* Cleanup the ugly parameter inspection line that I used in a few places
* committed a breakpoint again
* Move the text_dims check
* Remove blip_text serving_output
* Add decoder_input_ids to the default input sig
* Remove all the manual overrides for encoder-decoder model signatures
* Tweak longformer/led input sigs
* Tweak default serving output
* output.keys() -> output
* make fixup
* Extremely small change to TF SAM dummies to reduce memory usage on build
* remove debug breakpoint
* Debug print statement to track array sizes
* More debug shape printing
* More debug shape printing
* Now remove the debug shape printing
* make fixup
* make fixup
* Rework TF type hints to use | None instead of Optional[] for tf.Tensor
* Rework TF type hints to use | None instead of Optional[] for tf.Tensor
* Don't forget the imports
* Add the imports to tests too
* make fixup
* Refactor tests that depended on get_type_hints
* Better test refactor
* Fix an old hidden bug in the test_keras_fit input creation code
* Fix for the Deit tests
* Use bool instead of uint8/byte in DebertaV2 to make it compatible with TensorRT
TensorRT cannot accept onnx graph with uint8/byte intermediate tensors. This PR uses bool tensors instead of unit8/byte tensors to make the exported onnx file can work with TensorRT.
* fix: use bool instead of uint8/byte in Deberta and SEW-D
---------
Co-authored-by: Yuxian Qiu <yuxianq@nvidia.com>
* doc refocused on using optimum, tflite
* minor updates to fix checks
* Apply suggestions from code review
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
* TFLite to separate page, added links
* Removed the onnx list builder
* make style
* Update docs/source/en/serialization.mdx
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
---------
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
* Added lion and paged optimizers and made original tests pass.
* Added tests for paged and lion optimizers.
* Added and fixed optimizer tests.
* Style and quality checks.
---------
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
* Added lion and paged optimizers and made original tests pass.
* Added tests for paged and lion optimizers.
* Added and fixed optimizer tests.
* Style and quality checks.
* Initial draft. Some tests fail.
* Fixed dtype bug.
* Fixed bug caused by torch_dtype='auto'.
* All test green for 8-bit and 4-bit layers.
* Added fix for fp32 layer norms and bf16 compute in LLaMA.
* Initial draft. Some tests fail.
* Fixed dtype bug.
* Fixed bug caused by torch_dtype='auto'.
* All test green for 8-bit and 4-bit layers.
* Added lion and paged optimizers and made original tests pass.
* Added tests for paged and lion optimizers.
* Added and fixed optimizer tests.
* Style and quality checks.
* Fixing issues for PR #23479.
* Added fix for fp32 layer norms and bf16 compute in LLaMA.
* Reverted variable name change.
* Initial draft. Some tests fail.
* Fixed dtype bug.
* Fixed bug caused by torch_dtype='auto'.
* All test green for 8-bit and 4-bit layers.
* Added lion and paged optimizers and made original tests pass.
* Added tests for paged and lion optimizers.
* Added and fixed optimizer tests.
* Style and quality checks.
* Added missing tests.
* Fixup changes.
* Added fixup changes.
* Missed some variables to rename.
* revert trainer tests
* revert test trainer
* another revert
* fix tests and safety checkers
* protect import
* simplify a bit
* Update src/transformers/trainer.py
* few fixes
* add warning
* replace with `load_in_kbit = load_in_4bit or load_in_8bit`
* fix test
* fix tests
* this time fix tests
* safety checker
* add docs
* revert torch_dtype
* Apply suggestions from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* multiple fixes
* update docs
* version checks and multiple fixes
* replace `is_loaded_in_kbit`
* replace `load_in_kbit`
* change methods names
* better checks
* oops
* oops
* address final comments
---------
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* New TF version compatibility fixes
* Remove dummy print statement, move expand_1d
* Make a proper framework inference function
* Make a proper framework inference function
* ValueError -> TypeError
* Making `safetensors` a core dependency.
To be merged later, I'm creating the PR so we can try it out.
* Update setup.py
* Remove duplicates.
* Even more redundant.
* Update modeling_open_llama.py
Fix typo in `use_memorry_efficient_attention` parameter name
* Update configuration_open_llama.py
Fix typo in `use_memorry_efficient_attention` parameter name
* Update configuration_open_llama.py
Take care of backwards compatibility ensuring that the previous parameter name is taken into account if used
* Update configuration_open_llama.py
format to adjust the line length
* Update configuration_open_llama.py
proper code formatting using `make fixup`
* Update configuration_open_llama.py
pop the argument not to let it be set later down the line