game24-rl
This repository contains two checkpoints from the game24-rl course project:
sft-final/: full fine-tunedQwen/Qwen2.5-1.5B-Instructcheckpoint for 24-game reasoning.grpo-lora-final/: LoRA adapter trained from the SFT checkpoint with GRPO.
Code and experiment documentation: https://github.com/ElysiaFollower/game24-rl
Training Route
Qwen2.5-1.5B-Instruct -> full SFT final -> GRPO LoRA adapter -> decoding/eval
Notes
The project focuses on standard 24-point game solving. The model is expected to produce reasoning and a final answer expression that can be checked by the repository verifier.
The GRPO artifact is a PEFT LoRA adapter, not a standalone full model. Load the SFT checkpoint first, then apply the adapter.
Reported Repo-Local Results
Under the repo-local train/validation/test split documented in the GitHub repository:
- Base model full-data direct eval:
16/1362 = 1.17% - SFT final, validation, 1024 token budget:
110/136 = 80.88% - GRPO LoRA, validation, 1024 token budget:
116/136 = 85.29% - SFT final, validation, 4096 token budget:
123/136 = 90.44% - SFT final, test, 4096 token budget:
128/137 = 93.43% - GRPO LoRA, validation, 4096 token budget:
126/136 = 92.65% - GRPO LoRA, test, 4096 token budget:
129/137 = 94.16%
See the GitHub handoff and experiment docs for split details, verifier details, decoding settings, and caveats.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prometheus17/game24-rl", dtype="auto")