Funtowicz Morgan 7231f7b503 Enable ONNX/ONNXRuntime optimizations through converter script (#6131) ...

* Add onnxruntime transformers optimization support

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Added Optimization section in ONNX/ONNXRuntime documentation.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Improve note reference

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Fixing imports order.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Add warning about different level of optimization between torch and tf export.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Address @LysandreJik wording suggestion

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Address @LysandreJik wording suggestion

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Always optimize model before quantization for maximum performances.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Address comments on the documentation.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Improve TensorFlow optimization message as suggested by @yufenglee

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Removed --optimize parameter

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Warn the user about current quantization limitation when model is larger than 2GB.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

* Trigger CI for last check

* Small change in print for the optimization section.

Signed-off-by: Morgan Funtowicz <morgan@huggingface.co>

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

2020-07-31 09:45:13 +02:00

..

_static

Add forum link in the docs (#5637)

2020-07-09 15:13:22 -04:00

imgs

Guide to fixed-length model perplexity evaluation (#5449)

2020-07-07 16:04:15 -06:00

internal

Doc tokenizer (#6110)

2020-07-30 14:51:19 -04:00

main_classes

Doc tokenizer (#6110)

2020-07-30 14:51:19 -04:00

model_doc

Actually the extra_id are from 0-99 and not from 1-100 (#5967)

2020-07-30 06:13:29 -04:00

benchmarks.rst

[Docs] Benchmark docs (#5360)

2020-06-29 16:08:57 +02:00

bertology.rst

[doc] Fix broken links + remove crazy big notebook

2020-05-07 18:44:18 -04:00

conf.py

Release: v3.0.2

2020-07-06 18:49:44 -04:00

contributing.md

Update installation page and add contributing to the doc (#5084)

2020-06-17 14:01:10 -04:00

converting_tensorflow_models.rst

Add ALBERT to the Tensorflow to Pytorch model conversion cli (#3933)

2020-05-11 13:10:00 -04:00

examples.md

per_device instead of per_gpu/error thrown when argument unknown (#4618)

2020-05-27 11:36:55 -04:00

favicon.ico

Adding usage examples for common tasks (#2850)

2020-02-25 13:48:24 -05:00

glossary.rst

Fix typo in glossary (#5466)

2020-07-02 09:19:33 -04:00

index.rst

Doc tokenizer (#6110)

2020-07-30 14:51:19 -04:00

installation.md

Update installation page and add contributing to the doc (#5084)

2020-06-17 14:01:10 -04:00

migration.md

Add hugs (#5225)

2020-06-24 07:56:14 -04:00

model_sharing.rst

How to share model cards with the CLI (#5374)

2020-06-30 08:59:32 -04:00

model_summary.rst

Update model_summary.rst (#5737)

2020-07-27 05:34:02 -04:00

multilingual.rst

Refactor Code samples; Test code samples (#5036)

2020-06-25 16:46:00 -04:00

notebooks.md

Update notebooks (#3620)

2020-04-06 14:32:39 -04:00

perplexity.rst

tiny ppl doc typo fix (#5751)

2020-07-14 10:39:44 -06:00

philosophy.rst

Add hugs (#5225)

2020-06-24 07:56:14 -04:00

preprocessing.rst

Tokenization tutorial (#5257)

2020-06-24 18:43:20 -04:00

pretrained_models.rst

Fix all sphynx warnings (#5068)

2020-06-16 16:50:02 -04:00

quicktour.rst

Switch from return_tuple to return_dict (#6138)

2020-07-30 09:17:00 -04:00

serialization.rst

Enable ONNX/ONNXRuntime optimizations through converter script (#6131)

2020-07-31 09:45:13 +02:00

task_summary.rst

Update doc to new model outputs (#5946)

2020-07-21 18:13:55 -04:00

tokenizer_summary.rst

doc fixes (#5613)

2020-07-08 19:52:44 -04:00

training.rst

Switch from return_tuple to return_dict (#6138)

2020-07-30 09:17:00 -04:00