# qwen-rag-lora

This is a LoRA adapter trained on the Qwen model for RAG tasks.

## Model Details
- Base Model: Qwen/Qwen2.5-0.5B-Instruct
- Training Type: LoRA
- Task: RAG (Retrieval-Augmented Generation)

## Usage

```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load base model and tokenizer
model_name = "Qwen/Qwen2.5-0.5B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)

# Load LoRA weights
peft_model = PeftModel.from_pretrained(model, "TatvaJoshi-AHS/qwen-rag-lora")
```