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

update run_openai_gpt to fix #1264

Browse Source
This commit is contained in:
thomwolf
2019-09-18 10:07:47 +02:00
parent 8334993915
commit e768f2322a
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/contrib/run_openai_gpt.py
View File

@@ -153,9 +153,11 @@ def main():
# This loading functions also add new tokens and embeddings called `special tokens`
# These new embeddings will be fine-tuned on the RocStories dataset
special_tokens = ['_start_', '_delimiter_', '_classify_']
tokenizer = OpenAIGPTTokenizer.from_pretrained(args.model_name, special_tokens=special_tokens)
special_tokens_ids = list(tokenizer.convert_tokens_to_ids(token) for token in special_tokens)
model = OpenAIGPTDoubleHeadsModel.from_pretrained(args.model_name, num_special_tokens=len(special_tokens))
tokenizer = OpenAIGPTTokenizer.from_pretrained(args.model_name)
tokenizer.add_tokens(special_tokens)
special_tokens_ids = tokenizer.convert_tokens_to_ids(special_tokens)
model = OpenAIGPTDoubleHeadsModel.from_pretrained(args.model_name)
model.resize_token_embeddings(len(tokenizer))
model.to(device)
# Load and encode the datasets