Update README.md

README.md

@@ -74,7 +74,7 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-```markdown
+```python
 from transformers import AutoModelForCausalLM
 from peft import PeftModel
 
@@ -85,7 +85,7 @@ model = PeftModel.from_pretrained(base_model, peft_model_id)
 
 Run the model with a quantization configuration
 
-```markdown
+```python
 import torch, accelerate, peft
 from transformers import AutoModelForCausalLM, BitsAndBytesConfig, pipeline
 from peft import PeftModel
@@ -161,7 +161,7 @@ The following subsets of the above dataset were leveraged:
 
 #### Training Hyperparameters
 
-```markdown
+```python
 per_device_train_batch_size=16  
 per_device_eval_batch_size=32  
 gradient_accumulation_steps=2