Update README.md

README.md

@@ -52,12 +52,29 @@ tokenizer.push_to_hub(save_to)
 
 # Manual Testing
 prompt = "Hey, are you conscious? Can you talk to me?"
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+messages = [
+    {
+        "role": "system",
+        "content": "",
+    },
+    {"role": "user", "content": prompt},
+]
+templated_prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+print("Prompt:", prompt)
+print("Templated prompt:", templated_prompt)
+inputs = tokenizer(
+    templated_prompt,
+    return_tensors="pt",
+).to("cuda")
 generated_ids = quantized_model.generate(**inputs, max_new_tokens=128)
 output_text = tokenizer.batch_decode(
     generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
 )
-print(output_text)
+print("Response:", output_text[0][len(prompt):])
 
 # Local Benchmark
 import torch.utils.benchmark as benchmark