Downloads · 30 days
13
5% of all-time downloads
RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-GRPO
tomhu/RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-GRPO
RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-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.
This model starts from Qwen/Qwen2.5-3B-Instruct, is supervised-fine-tuned on unit tests generated by Qwen2.5-Coder-7B-Instruct, and is then trained for two GRPO epochs on the Defects4J mutation subset used by RL4TG.
All-time downloads
252
Public
Parameters
3.1B
67.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen2
- Access
- Public
- Created
- Jul 18, 2026
- Updated
- Jul 19, 2026
- SHA
- 6b9accfe
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen2.5-3B-Instruct Coder-7B Offline-SFT + GRPO
This model starts from Qwen/Qwen2.5-3B-Instruct, is supervised-fine-tuned
on unit tests generated by Qwen2.5-Coder-7B-Instruct, and is then trained for
two GRPO epochs on the Defects4J mutation subset used by RL4TG.
Revisions
main contains the final step-98 model. Every saved training checkpoint is
also available as a Hugging Face revision.
| Revision | Training step | Notes |
|---|---|---|
main | 98 | Final model; identical weights to checkpoint-98 |
checkpoint-10 | 10 | GRPO checkpoint |
checkpoint-20 | 20 | GRPO checkpoint |
checkpoint-30 | 30 | GRPO checkpoint |
checkpoint-40 | 40 | GRPO checkpoint |
checkpoint-50 | 50 | GRPO checkpoint |
checkpoint-60 | 60 | Highest Correct rate in the held-out checkpoint evaluation |
checkpoint-70 | 70 | Highest Branch Coverage in the held-out checkpoint evaluation |
checkpoint-80 | 80 | GRPO checkpoint |
checkpoint-90 | 90 | GRPO checkpoint |
checkpoint-98 | 98 | Final checkpoint |
Loading a Checkpoint
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "tomhu/RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-GRPO"
revision = "checkpoint-60"
tokenizer = AutoTokenizer.from_pretrained(repo_id, revision=revision)
model = AutoModelForCausalLM.from_pretrained(
repo_id,
revision=revision,
torch_dtype="auto",
device_map="auto",
)
Omit revision to load the final step-98 model from main.
GRPO Configuration
- Training samples: 1,582 Defects4J focal methods with eligible FAIL mutants
- Epochs: 2
- Global prompt batch: 32
- Rollouts per prompt: 8
- Sampling temperature: 1.0
- Learning rate: 1e-6
- Data shuffle seed: 42
- Maximum prompt and response lengths: 4,096 tokens each
- Checkpoint interval: 10 steps
This model is part of the RL4TG experimental model collection.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- Created
- Jul 18, 2026
- Updated
- Jul 19, 2026