ViSum - Vietnamese News Summarization (QLoRA 5 Epochs)

Mô hình tóm tắt tin tức tiếng Việt, fine-tuned từ vinai/bartpho-syllable bằng QLoRA trên 144K mẫu VietNews trong 5 epochs.

🚀 Cách sử dụng

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "OrdinaryAI/visum-qlora-5epochs"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)

article = "Bài báo của bạn..."
inputs = tokenizer(article, max_length=512, truncation=True, return_tensors="pt")
summary_ids = model.generate(inputs["input_ids"], max_length=150, num_beams=4)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(summary)
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train OrdinaryAI/visum-qlora-5epochs

Spaces using OrdinaryAI/visum-qlora-5epochs 2