Update README.md

README.md

@@ -59,6 +59,25 @@ tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 model = PeftModel.from_pretrained(model, peft_model_id, device_map={"":0})
 model.eval()
 ```
+2. Generating summaries
+
+```python
+text = "Your text goes here..."
+
+# If you want to use CPU
+input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids
+# Ir you want to use GPU
+input_ids = tokenizer(text, return_tensors="pt", truncation=True).input_ids.cuda()
+# Adjust max_new_tokens based on size. This is set up for articles of text
+outputs = model.generate(input_ids=input_ids, max_new_tokens=120, do_sample=False)
+
+print(f"input sentence: {sample['article']}\n{'---'* 20}")
+print(f"summary:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]}")
+
+
+
+```
+
 
 ## Training procedure