README.md

metadata

license: bigscience-bloom-rail-1.0
language:
  - fa

Base Model: https://huggingface.co./bigscience/bloomz-7b1

---

Model fine-tuned on a real news dataset and optimized for neural news generation.

Note: Persian was not in pretraining.

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-7b1")
model = AutoModelForSequenceClassification.from_pretrained('tum-nlp/neural-news-generator-bloomz-7b1-fa')

# Create the pipeline for neural news generation and set the repetition penalty >1.1 to punish repetition.
generator = pipeline('text-generation',
                      model=model,
                      tokenizer=tokenizer,
                      repetition_penalty=1.2)

# Define the prompt
prompt = " [EOP] به‌ دنبال «شورش مسلحانه» مزدوران نظامی واگنر و تصرف برخی "

# Generate
generator(prompt, max_length=1000, num_return_sequences=1)

Trained on 6k datapoints (including all splits) from: https://huggingface.co./datasets/RohanAiLab/persian_news_dataset