Update README.md

README.md

@@ -1,3 +1,36 @@
----
-license: llama2
----
+---
+license: llama2
+language:
+- fa
+---
+Base Model:
+https://huggingface.co/mostafaamiri/persian_llama_7B_merged
+
+---
+Model fine-tuned on a real news dataset and optimized for neural news generation.
+
+Note: Turkish was not in pretraining.
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained('bigscience/bloomz')
+model = AutoModelForSequenceClassification.from_pretrained('tum-nlp/neural-news-generator-llama-7b-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