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>
This commit is contained in:
Julien Chaumond
2019-11-06 16:26:31 -05:00
parent 2f3a421018
commit 1c542df7e5
4 changed files with 18 additions and 0 deletions

View File

@@ -47,6 +47,8 @@ PRETRAINED_VOCAB_FILES_MAP = {
'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':
{
@@ -54,6 +56,8 @@ PRETRAINED_VOCAB_FILES_MAP = {
'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 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
'roberta-large': 512,
'roberta-large-mnli': 512,
'distilroberta-base': 512,
'roberta-base-openai-detector': 512,
'roberta-large-openai-detector': 512,
}