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

GPT-2 XL

Browse Source
This commit is contained in:
Lysandre
2019-11-05 17:49:01 +00:00
committed by Lysandre Debut
parent 7daacf00df
commit d7d36181fd
4 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
transformers/configuration_gpt2.py
View File

@@ -29,6 +29,7 @@ logger = logging.getLogger(__name__)
GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP = {"gpt2": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-config.json",
"gpt2-medium": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-medium-config.json",
"gpt2-large": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-large-config.json",
"gpt2-xl": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-xl-config.json",
"distilgpt2": "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-config.json",}
class GPT2Config(PretrainedConfig):

1
transformers/modeling_gpt2.py
View File

@@ -39,6 +39,7 @@ logger = logging.getLogger(__name__)
GPT2_PRETRAINED_MODEL_ARCHIVE_MAP = {"gpt2": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-pytorch_model.bin",
"gpt2-medium": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-medium-pytorch_model.bin",
"gpt2-large": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-large-pytorch_model.bin",
"gpt2-xl": "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-xl-pytorch_model.bin",
"distilgpt2": "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-pytorch_model.bin",}
def load_tf_weights_in_gpt2(model, config, gpt2_checkpoint_path):

3
transformers/tokenization_gpt2.py
View File

@@ -46,6 +46,7 @@ PRETRAINED_VOCAB_FILES_MAP = {
'gpt2': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-vocab.json",
'gpt2-medium': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-medium-vocab.json",
'gpt2-large': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-large-vocab.json",
'gpt2-xl': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-xl-vocab.json",
'distilgpt2': "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-vocab.json",
},
'merges_file':
@@ -53,6 +54,7 @@ PRETRAINED_VOCAB_FILES_MAP = {
'gpt2': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-merges.txt",
'gpt2-medium': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-medium-merges.txt",
'gpt2-large': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-large-merges.txt",
'gpt2-xl': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-xl-merges.txt",
'distilgpt2': "https://s3.amazonaws.com/models.huggingface.co/bert/distilgpt2-merges.txt",
},
}
@@ -61,6 +63,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
'gpt2': 1024,
'gpt2-medium': 1024,
'gpt2-large': 1024,
'gpt2-xl': 1024,
'distilgpt2': 1024,
}