Create README.md

README.md

@@ -0,0 +1,40 @@
+---
+language: vi
+datasets:
+- cc100
+tags:
+- summarization
+
+license: mit
+---
+
+# ViT5-large Finetuned on `vietnews` Abstractive Summarization
+
+State-of-the-art pre-trained Transformer-based encoder-decoder model for Vietnamese.
+
+## How to use
+For more details, do check out [our Github repo](https://github.com/justinphan3110/ViT5). 
+```python
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+​
+tokenizer = AutoTokenizer.from_pretrained("VietAI/vit5-large-vietnews-summarization")  
+model = AutoModelForSeq2SeqLM.from_pretrained("VietAI/vit5-large-vietnews-summarization")
+​
+sentence = "Xin chào"
+text =  "summarize: " + sentence + " </s>"
+encoding = tokenizer.encode_plus(text, pad_to_max_length=True, 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=256,
+    early_stopping=True
+)
+for output in outputs:
+    line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
+    print(line)
+```
+
+## Citation
+```
+Coming Soon...
+```