|
--- |
|
language: vi |
|
datasets: |
|
- cc100 |
|
tags: |
|
- summarization |
|
|
|
license: mit |
|
|
|
widget: |
|
- text: "Input text." |
|
--- |
|
|
|
# ViT5-large Finetuned on `vietnews` Abstractive Summarization |
|
|
|
|
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("VietAI/vit5-large-vietnews-summarization") |
|
model = AutoModelForSeq2SeqLM.from_pretrained("VietAI/vit5-large-vietnews-summarization") |
|
model.cuda() |
|
|
|
sentence = "Input text" |
|
text = "vietnews: " + sentence + " </s>" |
|
encoding = tokenizer(text, return_tensors="pt") |
|
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda") |
|
outputs = model.generate( |
|
input_ids=input_ids, attention_mask=attention_masks, |
|
max_length=512, |
|
early_stopping=True |
|
) |
|
for output in outputs: |
|
line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True) |
|
print(line) |
|
``` |
|
|
