riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 02:31:11 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

[Longformer] fix model name in examples (#4653)

Browse Source 
* fix longformer model names in examples

* a better name for the notebook
This commit is contained in:
Iz Beltagy 2020-05-29 04:12:35 -07:00 committed by GitHub
parent b5015a2a0f
commit 91487cbb8e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
notebooks/README.md
View File

@ -30,5 +30,5 @@ Pull Request so it can be included under the Community notebooks.
| [Fine-tune BART for Summarization](https://github.com/ohmeow/ohmeow_website/blob/master/_notebooks/2020-05-23-text-generation-with-blurr.ipynb) | How to fine-tune BART for summarization with fastai using blurr | [Wayde Gilliam](https://ohmeow.com/) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ohmeow/ohmeow_website/blob/master/_notebooks/2020-05-23-text-generation-with-blurr.ipynb) |
| [Fine-tune a pre-trained Transformer on anyone's tweets](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb) | How to generate tweets in the style of your favorite Twitter account by fine-tune a GPT-2 model | [Boris Dayma](https://github.com/borisdayma) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb) |
| [A Step by Step Guide to Tracking Hugging Face Model Performance](https://colab.research.google.com/drive/1NEiqNPhiouu2pPwDAVeFoN4-vTYMz9F8) | A quick tutorial for training NLP models with HuggingFace and & visualizing their performance with Weights & Biases | [Jack Morris](https://github.com/jxmorris12) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1NEiqNPhiouu2pPwDAVeFoN4-vTYMz9F8) |
| [Pretrain Longformer](https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb) | How to convert existing pretrained models into their Long version | [Iz Beltagy](https://beltagy.net) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb) |
| [Pretrain Longformer](https://github.com/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb) | How to build a "long" version of existing pretrained models | [Iz Beltagy](https://beltagy.net) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/allenai/longformer/blob/master/scripts/convert_model_to_long.ipynb) |
| [Fine-tune Longformer for QA](https://github.com/patil-suraj/Notebooks/blob/master/longformer_qa_training.ipynb) | How to fine-tune longformer model for QA task | [Suraj Patil](https://github.com/patil-suraj) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patil-suraj/Notebooks/blob/master/longformer_qa_training.ipynb) |

20
src/transformers/modeling_longformer.py
View File

@ -572,8 +572,8 @@ class LongformerModel(RobertaModel):
import torch
from transformers import LongformerModel, LongformerTokenizer
model = LongformerModel.from_pretrained('longformer-base-4096')
tokenizer = LongformerTokenizer.from_pretrained('longformer-base-4096')
model = LongformerModel.from_pretrained('allenai/longformer-base-4096')
tokenizer = LongformerTokenizer.from_pretrained('allenai/longformer-base-4096')
SAMPLE_TEXT = ' '.join(['Hello world! '] * 1000) # long input document
input_ids = torch.tensor(tokenizer.encode(SAMPLE_TEXT)).unsqueeze(0) # batch of size 1
@ -681,8 +681,8 @@ class LongformerForMaskedLM(BertPreTrainedModel):
import torch
from transformers import LongformerForMaskedLM, LongformerTokenizer
model = LongformerForMaskedLM.from_pretrained('longformer-base-4096')
tokenizer = LongformerTokenizer.from_pretrained('longformer-base-4096')
model = LongformerForMaskedLM.from_pretrained('allenai/longformer-base-4096')
tokenizer = LongformerTokenizer.from_pretrained('allenai/longformer-base-4096')
SAMPLE_TEXT = ' '.join(['Hello world! '] * 1000) # long input document
input_ids = torch.tensor(tokenizer.encode(SAMPLE_TEXT)).unsqueeze(0) # batch of size 1
@ -769,8 +769,8 @@ class LongformerForSequenceClassification(BertPreTrainedModel):
from transformers import LongformerTokenizer, LongformerForSequenceClassification
import torch
tokenizer = LongformerTokenizer.from_pretrained('longformer-base-4096')
model = LongformerForSequenceClassification.from_pretrained('longformer-base-4096')
tokenizer = LongformerTokenizer.from_pretrained('allenai/longformer-base-4096')
model = LongformerForSequenceClassification.from_pretrained('allenai/longformer-base-4096')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
labels = torch.tensor([1]).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)
@ -909,8 +909,8 @@ class LongformerForQuestionAnswering(BertPreTrainedModel):
from transformers import LongformerTokenizer, LongformerForQuestionAnswering
import torch
tokenizer = LongformerTokenizer.from_pretrained("longformer-large-4096-finetuned-triviaqa")
model = LongformerForQuestionAnswering.from_pretrained("longformer-large-4096-finetuned-triviaqa")
tokenizer = LongformerTokenizer.from_pretrained("allenai/longformer-large-4096-finetuned-triviaqa")
model = LongformerForQuestionAnswering.from_pretrained("allenai/longformer-large-4096-finetuned-triviaqa")
question, text = "Who was Jim Henson?", "Jim Henson was a nice puppet"
encoding = tokenizer.encode_plus(question, text, return_tensors="pt")
@ -1031,8 +1031,8 @@ class LongformerForTokenClassification(BertPreTrainedModel):
from transformers import LongformerTokenizer, LongformerForTokenClassification
import torch
tokenizer = LongformerTokenizer.from_pretrained('longformer-base-4096')
model = LongformerForTokenClassification.from_pretrained('longformer-base-4096')
tokenizer = LongformerTokenizer.from_pretrained('allenai/longformer-base-4096')
model = LongformerForTokenClassification.from_pretrained('allenai/longformer-base-4096')
input_ids = torch.tensor(tokenizer.encode("Hello, my dog is cute", add_special_tokens=True)).unsqueeze(0) # Batch size 1
labels = torch.tensor([1] * input_ids.size(1)).unsqueeze(0) # Batch size 1
outputs = model(input_ids, labels=labels)