Update README.md

README.md

@@ -19,12 +19,25 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 
 ```python
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "PhilSad/SmolLM2-1.7B-FT-SCP-Wiki"
+model = AutoModelForCausalLM.from_pretrained(
+    pretrained_model_name_or_path=model_name
+).to(device)
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name)
+
+prompt = "SCP-10214 is a god who loves making pasta."
+
+messages = [{"role": "user", "content": prompt}]
+formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False)
+
+inputs = tokenizer(formatted_prompt, return_tensors="pt").to(device)
+
+outputs = model.generate(**inputs, max_new_tokens=2048)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="PhilSad/SmolLM2-135M-FT-SCP-Wiki", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
 ```
 
 ## Training procedure