Update README.md

README.md

@@ -30,7 +30,37 @@ ElEmperador is an ORPO-based finetune derived from the Mistral-7B-v0.1 base mode
 ## Evals:
 BLEU:0.209
 
+## Inference Script:
 
+```python
+def generate_response(model_name, input_text, max_new_tokens=50):
+    # Load the tokenizer and model from Hugging Face Hub
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    
+    # Tokenize the input text
+    input_ids = tokenizer(input_text, return_tensors='pt').input_ids
+    
+    # Generate a response using the model
+    with torch.no_grad():
+        generated_ids = model.generate(input_ids, max_new_tokens=max_new_tokens)
+    
+    # Decode the generated tokens into text
+    generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+    
+    return generated_text
+
+if __name__ == "__main__":
+    # Set the model name from Hugging Face Hub
+    model_name = "AINovice2005/ElEmperador" 
+    input_text = "Hello, how are you?"
+
+    # Generate and print the model's response
+    output = generate_response(model_name, input_text)
+    
+    print(f"Input: {input_text}")
+    print(f"Output: {output}")
+```
 
 ## Results