File size: 978 Bytes
b91e974 18183fc e42be83 b91e974 b0513f1 e8bf1ac b0513f1 4794bbf b0513f1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 |
---
license: mit
language: th
datasets:
- thaisum
widget:
- text: "some news with head line"
---
# How to use
```python3
from transformers import MT5Tokenizer, MT5ForConditionalGeneration
tokenizer = MT5Tokenizer.from_pretrained('juierror/thai-news-summarization')
model = MT5ForConditionalGeneration.from_pretrained('juierror/thai-news-summarization')
text = "some news with head line"
tokenized_text = tokenizer(text, truncation=True, padding=True, return_tensors='pt')
source_ids = tokenized_text['input_ids'].to("cpu", dtype = torch.long)
source_mask = tokenized_text['attention_mask'].to("cpu", dtype = torch.long)
generated_ids = model.generate(
input_ids = source_ids,
attention_mask = source_mask,
max_length=512,
num_beams=5,
repetition_penalty=1,
length_penalty=1,
early_stopping=True,
no_repeat_ngram_size=2
)
pred = tokenizer.decode(generated_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)
``` |