GitLab

* Correct cast to device

* Comment back the slow test

* make executable

* make executable

* same for the template

* cleanup

* add prepare_decoder_input_ids_from_labels in s2s models

* support lbl smoothing and enc/emb freezing

* fix freezing

* use pad_token_id from config

* remove embed freezing and add warning

* prepare decoder_input_ids inside DataCollatorForSeq2Seq

* Bump minimum Jax requirement to 2.8.0

* update table

* add big bird

* change teacher to mentor

* add proposal template

* adapt template

* delete old template

* correct some links

* finish template

* create big bird from template

* add big bird

* improve boxes

* finish boxes

* add pointers for BigBird

* finish big bird

* up

* up

* up

* up

* apply lysandres and sylvains suggestions

* delete bogus file

* correct markdown

* try different style

* try different style

* finalize

* Clarify QA pipeline output based on character

* Style

* Update doc for pre-release

* Use stable as default

* Use the right commit :facepalms:

* Authorize last version of tokenizer

* Update version table

* Fix conversion of spm tokenizers and fix some hub links

* Bump tokenizers version to 0.10.1rc1

* Add script to check tokenizers conversion with XNLI

* Add some more mask_token lstrip support

* Must modify mask_token in slow tokenizers too

* Keep using the old method for Pegasus

* add missing import
Co-authored-by: Anthony MOI <m.anthony.moi@gmail.com>

`encoder_no_repeat_ngram_size` from their config.

* trainer fixes

* don't switch the model  just for deepspeed and mp

* correct the fix

* Replace `attn_weights = attn_wegihts = tf.reshape(...)`
with `attn_weights = tf.reshape(...)` and thus remove
unintentionally used "double" assignment.

Adding new `encoder_no_repeat_ngram_size` to `generate`.

Blenderbot results seemed off compared to original ParlAI script:
`https://parl.ai/projects/recipes/`

. Notably the model seems
to repeat a lot what was said during the conversation.

The actual problem was that `no_repeat_ngram_size` actually applies
to the `encoder_input_ids` but HF's `no_repeat_ngram_size` applies
to the previously generated ids (within the decoder). The history
conversation of blenderbot is within the `encoder` part so that
explains why HF's implementation had the repetitions.

This fix was focused on blenderbot *not* small and added tests
for those because they are quite different in configuration.

This change includes:

- Adding a new EncoderNoRepeatLogitProcessor.
- Adding 1 new arg to `generate` (`encoder_no_repeat_ngram_size`)
- Adding 1 new config parameter `encoder_no_repeat_ngram_size`.
- Adding 2 tests, one for the pipeline (high level, inputs exhibited
repeat behavior, one low level for EncoderNoRepeatLogitProcessor)
- Factored NoRepeatLogitProcessor so that logic could be reused.

Further work:

- Blenderbot conversational pipeline still does not behave correctly
 as they way input is prepared within the pipeline is still incorrect
(follow up PR)
- Blenderbot allows the bot to have personas, which is done by
prepending "your personna: XXXX" to the input, this could be explored
too in a follow up PR.

@patrickvonplaten
@LysandreJik

* Update src/transformers/generation_logits_process.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/transformers/generation_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/transformers/generation_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/transformers/configuration_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Doc quality.

* Fixing test.

* Last fixes.

* Fixing to account for batch_size.

* Update src/transformers/configuration_utils.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/generation_utils.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* initiliaze bart4causalLM

* create BartDecoderWrapper, setters/getters

* delete spaces

* forward and additional methods

* update cache function, loss function, remove ngram* params in data class.

* add bartcausallm, bartdecoder testing

* correct bart for causal lm

* remove at

* add mbart as well

* up

* fix typo

* up

* correct

* add pegasusforcausallm

* add blenderbotforcausallm

* add blenderbotsmallforcausallm

* add marianforcausallm

* add test for MarianForCausalLM

* add Pegasus test

* add BlenderbotSmall test

* add blenderbot test

* fix a fail

* fix an import fail

* a fix

* fix

* Update modeling_pegasus.py

* fix models

* fix inputs_embeds setting getter

* adapt tests

* correct repo utils check

* finish test improvement

* fix tf models as well

* make style

* make fix-copies

* fix copies

* run all tests

* last changes

* fix all tests
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* TF DistilBERT integration test

* Update test_modeling_tf_distilbert.py

* TF Albert integration test

* TF Alber integration test added

* fix steps_in_epoch variable when using max_steps

* redundant sentence

* Revert "redundant sentence"

This reverts commit ad5c0e9b6e66d65732dee2239cdc9c76dfa0dc5a.

* remove redundant sentence
Co-authored-by: wujindou <wujindou@sogou-inc.com>

* Fix Longformer and LED

* Add a test for graph execution with inputs_embeds

* Apply style

Looks like a vulnerability and it's not really used anywhere in the code, so just as well remove it completely from deps.
https://github.com/huggingface/transformers/security/dependabot/examples/research_projects/lxmert/requirements.txt/bleach/open

* Add {decoder_,}head_mask to LED

* Fix create_custom_forward signatue in encoder

* Add head_mask to longformer

* Add head_mask to longformer to fix dependencies
of LED on Longformer.

* Not working yet

* Add mising one input in longofrmer_modeling.py

* make fix-copies