SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Deberta_v2 tf (#13120)

Browse Source 
* Deberta_v2 tf

* added new line at the end of file, make style

* +V2, typo

* remove never executed branch of code

* rm cmnt and fixed typo in url filter

* cleanup according to review comments

* added #Copied from
This commit is contained in:
Kamal Raj
2021-08-31 16:02:47 +05:30
committed by GitHub
parent 286ccefb48
commit 3efcfeab67
8 changed files with 2109 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/index.rst
View File

@@ -351,7 +351,7 @@ Flax), PyTorch, and/or TensorFlow.
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| DeBERTa | ✅ | ✅ | ✅ | ✅ | ❌ |
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| DeBERTa-v2 | ✅ | ❌ | ✅ | ❌ | ❌ |
| DeBERTa-v2 | ✅ | ❌ | ✅ | ✅ | ❌ |
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+
| DeiT | ❌ | ❌ | ✅ | ❌ | ❌ |
+-----------------------------+----------------+----------------+-----------------+--------------------+--------------+

45
docs/source/model_doc/deberta_v2.rst
View File

@@ -58,7 +58,8 @@ New in v2:
- **900M model & 1.5B model** Two additional model sizes are available: 900M and 1.5B, which significantly improves the
performance of downstream tasks.
This model was contributed by `DeBERTa <https://huggingface.co/DeBERTa>`__. The original code can be found `here
This model was contributed by `DeBERTa <https://huggingface.co/DeBERTa>`__. This model TF 2.0 implementation was
contributed by `kamalkraj <https://huggingface.co/kamalkraj>`__. The original code can be found `here
<https://github.com/microsoft/DeBERTa>`__.
@@ -117,3 +118,45 @@ DebertaV2ForQuestionAnswering
.. autoclass:: transformers.DebertaV2ForQuestionAnswering
:members: forward
TFDebertaV2Model
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFDebertaV2Model
:members: call
TFDebertaV2PreTrainedModel
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFDebertaV2PreTrainedModel
:members: call
TFDebertaV2ForMaskedLM
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFDebertaV2ForMaskedLM
:members: call
TFDebertaV2ForSequenceClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFDebertaV2ForSequenceClassification
:members: call
TFDebertaV2ForTokenClassification
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFDebertaV2ForTokenClassification
:members: call
TFDebertaV2ForQuestionAnswering
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: transformers.TFDebertaV2ForQuestionAnswering
:members: call