Update README.md

README.md

@@ -33,7 +33,7 @@ while True:
         break
 
     inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False, padding=True, truncation=True, max_length=512)
-    response = olmo.generate(**inputs, max_length=512, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, do_sample=True, top_k=50, top_p=0.95)
+    response = model.generate(**inputs, max_length=512, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, do_sample=True, top_k=50, top_p=0.95)
     reply = tokenizer.decode(response[0], skip_special_tokens=True)
     print("AI: ", reply)
 ```