Update README.md

README.md

@@ -116,7 +116,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 
-model_id="nanochat-students/chat-d20"
+model_id="nanochat-students/d20-chat-transformers"
 max_new_tokens=64
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
@@ -137,11 +137,13 @@ inputs = tokenizer.apply_chat_template(
 
 with torch.no_grad():
     outputs = model.generate(
-        inputs,
+        **inputs,
         max_new_tokens=max_new_tokens,
     )
 
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# Decode only the generated tokens (excluding the input prompt)
+generated_tokens = outputs[0, inputs.input_ids.shape[1]:]
+print(tokenizer.decode(generated_tokens, skip_special_tokens=True))
 ```