tomhu/RL4TG-Qwen2.5-3B-OPD-GRPO-1-Epoch
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
RL4TG-Qwen2.5-3B-OPD-GRPO-1…/README.md
ModelHub XC f715f19a79 初始化项目，由ModelHub XC社区提供模型 
Model: tomhu/RL4TG-Qwen2.5-3B-OPD-GRPO-1-Epoch
Source: Original Platform
2026-07-20 15:42:11 +08:00

1.1 KiB
Raw Permalink Blame History

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

Qwen2.5-3B + OPD + GRPO (1 epoch)

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

Field Value
Base model Qwen/Qwen2.5-3B-Instruct
Method OPD initialization followed by GRPO
Teacher Qwen/Qwen2.5-Coder-7B-Instruct during OPD
Released checkpoint GRPO step 50 (1 epoch)
Training data OPD split followed by 1,582 mutation-eligible Defects4J samples
Prompt format Qwen2.5 chat template
Global training seed 42

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "tomhu/RL4TG-Qwen2.5-3B-OPD-GRPO-1-Epoch"
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.