---
base_model: Qwen/Qwen3-4B-Instruct-2507
library_name: peft
license: apache-2.0
tags:
- orpo
- qwen
- structeval
- json-generation
---

# Qwen3-4B StructEval ORPO Adapter

This is a LoRA adapter trained using ORPO (Odds Ratio Preference Optimization) to enforce strict JSON output formatting.

## Training Details
- **Base Model**: Qwen/Qwen3-4B-Instruct-2507 (Merged with initial SFT adapter)
- **Training Algorithm**: ORPO
- **Objective**: Improve adherence to structured output constraints (StructEval-T oriented) and suppress unrequested text/thinking processes.
- **Hardware**: Trained on Google Colab (T4 GPU).

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "daichira/qwen3-4b-structeval-orpo-v1"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
model = AutoModelForCausalLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(model, adapter_id)
```