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

Update README.md (#8544)

Browse Source 
Modified Model in Action section. The class `AutoModelWithLMHead` is deprecated so changed it to `AutoModelForSeq2SeqLM` for encoder-decoder models. Removed duplicate eos token.
This commit is contained in:
Vishal Singh
2020-11-18 23:49:32 +05:30
committed by GitHub
parent 6c8fad4f0d
commit 26dc6593f3
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
model_cards/mrm8488/t5-base-finetuned-squadv2/README.md
View File

@@ -51,13 +51,13 @@ The training script is a slightly modified version of [this one](https://colab.r
## Model in Action 🚀 ## Model in Action 🚀
```python ```python
from transformers import AutoModelWithLMHead, AutoTokenizer from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-squadv2") tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-squadv2")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-squadv2") model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/t5-base-finetuned-squadv2")
def get_answer(question, context): def get_answer(question, context):
input_text = "question: %s context: %s </s>" % (question, context) input_text = "question: %s context: %s" % (question, context)
features = tokenizer([input_text], return_tensors='pt') features = tokenizer([input_text], return_tensors='pt')
output = model.generate(input_ids=features['input_ids'], output = model.generate(input_ids=features['input_ids'],