tum-nlp/neural-news-generator-llama-2-7b-chat-en

Base Model: https://huggingface.co/meta-llama/Llama-2-7b-chat-hf

---

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

from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForSequenceClassification.from_pretrained('tum-nlp/neural-news-generator-llama-2-7b-chat-en')

# 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 = "Headline: UK headline inflation rate drops sharply to 6.8% in July, in line with expectations Article: LONDON U.K. headline inflation cooled sharply in July to [EOP]"

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

Trained on 6k datapoints (including all splits) from: https://paperswithcode.com/dataset/cc-news