Update train.py

train.py

@@ -961,7 +961,7 @@ class MonitorRewardCallback(TrainerCallback):
 max_seq_length = 1200
 
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name="/home/anon/gemma-3-4b-it",
+    model_name="google/gemma-3-4b-it",
     # fast_inference = True,
     max_seq_length=max_seq_length,  # Choose any for long context!
     load_in_4bit=False,  # 4 bit quantization to reduce memory