---
license: apache-2.0
base_model: Qwen/Qwen2.5-3B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
- qwen2
- test-generation
- reinforcement-learning
- grpo
- opd
- java
- defects4j
---

# Qwen2.5-3B + GRPO (2 epochs)

This is an RL4TG checkpoint for Java unit-test generation.

| Field | Value |
|---|---|
| Base model | `Qwen/Qwen2.5-3B-Instruct` |
| Method | Group Relative Policy Optimization (GRPO) |
| Teacher | `None` |
| Released checkpoint | step 98 (2 epochs) |
| Training data | 1,582 mutation-eligible Defects4J training samples |
| Prompt format | Qwen2.5 chat template |
| Global training seed | 42 |

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tomhu/RL4TG-Qwen2.5-3B-GRPO-2-Epochs"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)
```

The model is intended for research on Java unit-test generation. Generated tests
must still be compiled and executed in the target project's own build environment.

<!-- RL4TG_CHECKPOINT_REVISIONS -->
## Checkpoint revisions

The 10-step trajectory checkpoints are available as Git revisions in this repo.
The `main` revision is the final step-98 model.

| Revision | Training step | Load argument |
|---|---:|---|
| `step-10` | 10 | `revision="step-10"` |
| `step-20` | 20 | `revision="step-20"` |
| `step-30` | 30 | `revision="step-30"` |
| `step-40` | 40 | `revision="step-40"` |
| `step-50` | 50 | `revision="step-50"` |
| `step-60` | 60 | `revision="step-60"` |
| `step-70` | 70 | `revision="step-70"` |
| `step-80` | 80 | `revision="step-80"` |
| `step-90` | 90 | `revision="step-90"` |