Sachin-Hansaka/Sinhala-qa-QLoRA-LLaMA-3.2-3B-Instruct

This repository contains only LoRA/QLoRA adapter weights. You must load them on top of the base model (e.g., google/gemma-2-2B-Instruct) using peft.

🚀 How to Use This Model

This model is fine-tuned for Sinhala Abstractive QA using QLoRA. You must load it with the base model:

# Example Inference
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B-Instruct")

model = PeftModel.from_pretrained(base_model, "Sachin-Hansaka/Sinhala-qa-QLoRA-LLaMA-3.2-3B-Instruct")