Skip to content
Permalink
Browse files
Add RoBERTa-based GPT-2 Output Detector from OpenAI 
converted from https://github.com/openai/gpt-2-output-dataset/tree/master/detector

Co-Authored-By: Lysandre Debut <lysandre.debut@reseau.eseo.fr>
Co-Authored-By: Jong Wook Kim <jongwook@nyu.edu>
Co-Authored-By: Jeff Wu <wuthefwasthat@gmail.com>
  • Loading branch information
@julien-c @LysandreJik
@jongwook @WuTheFWasThat
4 people committed Nov 6, 2019
1 parent 2f3a421 commit 1c542df
Show file tree
Hide file tree
Showing 4 changed files with 18 additions and 0 deletions.
8 docs/source/pretrained_models.rst
View file
@@ -127,6 +127,14 @@ Here is the full list of the currently provided pretrained models together with
| | ``roberta-large-mnli`` | | 24-layer, 1024-hidden, 16-heads, 355M parameters |
| | | | ``roberta-large`` fine-tuned on `MNLI <http://www.nyu.edu/projects/bowman/multinli/>`__. |
| | | (see `details <https://github.com/pytorch/fairseq/tree/master/examples/roberta>`__) |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``roberta-base-openai-detector`` | | 12-layer, 768-hidden, 12-heads, 125M parameters |
| | | | ``roberta-base`` fine-tuned by OpenAI on the outputs of the 1.5B-parameter GPT-2 model. |
| | | (see `details <https://github.com/openai/gpt-2-output-dataset/tree/master/detector>`__) |
| +------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| | ``roberta-large-openai-detector`` | | 24-layer, 1024-hidden, 16-heads, 355M parameters |
| | | | ``roberta-large`` fine-tuned by OpenAI on the outputs of the 1.5B-parameter GPT-2 model. |
| | | (see `details <https://github.com/openai/gpt-2-output-dataset/tree/master/detector>`__) |
+-------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
| DistilBERT | ``distilbert-base-uncased`` | | 6-layer, 768-hidden, 12-heads, 66M parameters |
| | | | The DistilBERT model distilled from the BERT model `bert-base-uncased` checkpoint |
2 transformers/configuration_roberta.py
View file
@@ -29,6 +29,8 @@
'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-config.json",
'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-config.json",
'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-config.json",
'roberta-base-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-openai-detector-config.json",
'roberta-large-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-openai-detector-config.json",
}


2 transformers/modeling_roberta.py
View file
@@ -35,6 +35,8 @@
'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-pytorch_model.bin",
'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-pytorch_model.bin",
'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-pytorch_model.bin",
'roberta-base-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-openai-detector-pytorch_model.bin",
'roberta-large-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-openai-detector-pytorch_model.bin",
}

class RobertaEmbeddings(BertEmbeddings):
6 transformers/tokenization_roberta.py
View file
@@ -47,13 +47,17 @@ def lru_cache():
'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-vocab.json",
'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-vocab.json",
'roberta-base-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json",
'roberta-large-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
},
'merges_file':
{
'roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-merges.txt",
'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-merges.txt",
'roberta-base-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
'roberta-large-openai-detector': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
},
}

@@ -62,6 +66,8 @@ def lru_cache():
'roberta-large': 512,
'roberta-large-mnli': 512,
'distilroberta-base': 512,
'roberta-base-openai-detector': 512,
'roberta-large-openai-detector': 512,
}


2 comments on commit 1c542df

@kleio1975
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

STRANGER THINGS
CHAPTER 1

The disappearance of will

November 6, 1983 Hawkins, Indiana.

The Wheelers' basement is a meeting place for fantastic adventures that Mike and his friends experience through Dugeons and Dragons1, like every good MASTER2 worth his salt, young Mike is in charge of narrating and directing the games with which he and his friends spend their dead hours immersed in his fantasy world ...
<< Something is approaching, something thirsty for blood, a shadow grows on the wall behind you and leaves you in the dark, it's almost here ¬ >>
--What is it? —Interrupt him Will, a thin boy with pale skin, who was staring at his friend, waiting to know the outcome.

@julien-c
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is the purpose of this comment, @kleio1975?

Please sign in to comment.