Downloads · 30 days
9
19% of all-time downloads
RL4TG-Qwen3-8B-Direct-GRPO
tomhu/RL4TG-Qwen3-8B-Direct-GRPO
RL4TG-Qwen3-8B-Direct-GRPO is a text generation model from tomhu. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model starts directly from Qwen3-8B and is trained with mutation-aware GRPO for Java unit-test generation. The repository name intentionally does not encode an internal checkpoint number.
All-time downloads
48
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- fa4f27d5
Try a prompt
Base models
Model card
From the Hugging Face model README
RL4TG Qwen3-8B Direct GRPO
This model starts directly from Qwen3-8B and is trained with mutation-aware GRPO for Java unit-test generation. The repository name intentionally does not encode an internal checkpoint number.
Training configuration
| Setting | Value |
|---|---|
| Starting policy | Qwen/Qwen3-8B |
| Training examples | 1,582 mutation-applicable Defects4J training samples |
| Algorithm | GRPO, no KL term in reward |
| Epochs | 2 |
| Actor optimization precision | FP32 |
| Learning rate | 1e-6 |
| Global prompt batch | 32 |
| Rollouts per prompt | 8 |
| PPO prompt groups / expanded mini batch | 4 / 32 |
| GPUs / per-GPU micro batch | 2 / 2 |
| Gradient accumulation | 8 |
| Parameter and optimizer offload | enabled |
| Temperature | 1.0 |
| Entropy coefficient | 0.01 |
| Maximum prompt/response length | 4096 / 4096 tokens |
| Data shuffle / seed | enabled / 42 |
| Chat template | enabled; Qwen thinking disabled |
The reward is -1 for an invalid generated test. A valid test receives
0.4 * line_coverage + 0.6 * branch_coverage + mutation_score. Mutation
analysis samples up to three eligible failing mutants per rollout, with a
mutation weight of 1.0. Coverage credit is gated by focal-call, assertion, and
local focal-data provenance checks.
Intended use
The model is intended for research on Java unit-test generation and reinforcement learning for software engineering. Generated tests must be compiled and executed in an isolated environment before use.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026