Update README.md

README.md

@@ -20,18 +20,25 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 
 ```python
+# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+pipe = pipeline("text-generation", model="Reubencf/gemma3-konkani")
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe(messages)
 ```
+Using PEFT
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM
 
-## Training procedure
-
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/reubencf/huggingface/runs/x8nvaeig) 
+base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it")
+model = PeftModel.from_pretrained(base_model, "Reubencf/gemma3-konkani")
+```
 
+## Training procedure
 
 This model was trained with SFT.