Downloads · 30 days
11
15% of all-time downloads
ginrummy-qwen3-8b-grpo-lora-v2
GoodStartLabs/ginrummy-qwen3-8b-grpo-lora-v2
ginrummy-qwen3-8b-grpo-lora-v2 is a reinforcement learning model from GoodStartLabs. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
LoRA trained via GRPO on Gin Rummy with shaped rewards and WeakKnocker opponent. Final run of a 9-run iteration.
All-time downloads
72
Public
Repo size
72.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors61.4 MB · 79%
At a glance
- Task
- Reinforcement Learning
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Mar 26, 2026
- SHA
- 44297463
Base models
Datasets
Model card
From the Hugging Face model README
Gin Rummy GRPO LoRA v2 — Run 9 (Qwen3-8B)
LoRA trained via GRPO on Gin Rummy with shaped rewards and WeakKnocker opponent. Final run of a 9-run iteration.
| Field | Value |
|---|---|
| Base model | Qwen/Qwen3-8B |
| Method | GRPO (TRL GRPOTrainer) |
| LoRA | r=16, alpha=32, q/k/v/o_proj |
| Steps | 500 (~2000 games) |
| Opponent | WeakKnocker (random draws, smart discards, always knocks) |
| Win rate | 0.5% |
| Infra | Together AI 8x H100 80GB, ~3.5 hours |
| Git commit | 2a987af docs: add Phase 3 (V2 migration) to experiment log |
| W&B | good-start-labs/ginrummy-grpo |
| Dataset | Self-play rollouts vs WeakKnocker bot |
Config
enable_thinking=True, simplified rules-only prompt, single vLLM call/turnnum_generations=8,lr=1e-5,beta=0.1,max_completion_length=2048- Shaped reward: 40% terminal + 40% deadwood progress + 20% game length
Key Finding
GRPO alone cannot teach gin rummy from scratch. The game is too complex for random exploration. SFT on expert data should precede RL. See full experiment log.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(base, "GoodStartLabs/ginrummy-qwen3-8b-grpo-lora-v2")
- Task
- Reinforcement Learning
- Library
- peft
- License
- apache-2.0
- Created
- Mar 26, 2026
- Updated
- Mar 26, 2026