Update README.md

README.md

@@ -19,7 +19,7 @@ Continuing my efforts to finetune tiny LLMs on hyperspecific tasks, I've decided
 With a different base model comes a new name for the finetunes: FrenchGemma.
 Similarly to Meta Llama 3.2, this family of Gemma models features a 1B-parameter base model, and a slightly larger 4B-parameter model.
 This model repository is dedicated to the 4B-Instruct version.
-```
+```python
 training_args = TrainingArguments(
     output_dir="./gemma_fine_tuned",
     per_device_train_batch_size=2,