riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

Fix examples of loading pretrained models in docstring

Browse Source
This commit is contained in:
wangfei 2019-08-06 11:30:35 +08:00
parent beb03ec6c5
commit f889e77b9c
1 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
pytorch_transformers/modeling_gpt2.py
View File

@ -433,11 +433,11 @@ class GPT2Model(GPT2PreTrainedModel):
Examples::
>>> tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
>>> model = GPT2Model.from_pretrained('gpt2')
>>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
>>> outputs = model(input_ids)
>>> last_hidden_states = outputs[0] # The last hidden-state is the first element of the output tuple
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2Model.from_pretrained('gpt2')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
outputs = model(input_ids)
last_hidden_states = outputs[0] # The last hidden-state is the first element of the output tuple
"""
def __init__(self, config):
@ -566,11 +566,11 @@ class GPT2LMHeadModel(GPT2PreTrainedModel):
Examples::
>>> tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
>>> model = GPT2LMHeadModel.from_pretrained('gpt2')
>>> input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
>>> outputs = model(input_ids, labels=input_ids)
>>> loss, logits = outputs[:2]
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2LMHeadModel.from_pretrained('gpt2')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute")).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=input_ids)
loss, logits = outputs[:2]
"""
def __init__(self, config):
@ -681,13 +681,13 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
Examples::
>>> tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
>>> model = GPT2DoubleHeadsModel.from_pretrained('gpt2')
>>> choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"] # Assume you've added [CLS] to the vocabulary
>>> input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices
>>> mc_token_ids = torch.tensor([-1, -1]).unsqueeze(0) # Batch size 1
>>> outputs = model(input_ids, mc_token_ids)
>>> lm_prediction_scores, mc_prediction_scores = outputs[:2]
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2DoubleHeadsModel.from_pretrained('gpt2')
choices = ["Hello, my dog is cute [CLS]", "Hello, my cat is cute [CLS]"] # Assume you've added [CLS] to the vocabulary
input_ids = torch.tensor([tokenizer.encode(s) for s in choices]).unsqueeze(0) # Batch size 1, 2 choices
mc_token_ids = torch.tensor([-1, -1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, mc_token_ids)
lm_prediction_scores, mc_prediction_scores = outputs[:2]
"""
def __init__(self, config):