Downloads · 30 days
6
6% of all-time downloads
pokemon-showdown-agent-battle-grpo
GoldenGrapeGentleman1/pokemon-showdown-agent-battle-grpo
pokemon-showdown-agent-battle-grpo is a machine learning model from GoldenGrapeGentleman1. Use it for the machine 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 adapter for Champion tier play. Trained with battle-outcome GRPO on gen9randombattle data (reward from wins vs heuristics and baselines).
All-time downloads
103
Public
Repo size
809 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors529 MB · 65%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 28, 2026
- Updated
- Jul 28, 2026
- SHA
- 4d76da11
Base models
Model card
From the Hugging Face model README
Pokémon Showdown Agent — Battle GRPO
LoRA adapter for Champion tier play. Trained with battle-outcome GRPO on gen9randombattle data (reward from wins vs heuristics and baselines).
Stack on Qwen3-4B or load after the full SFT model for best ladder strength.
Quick start
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
"Qwen/Qwen3-4B",
max_seq_length=2048,
load_in_4bit=False,
)
model.load_adapter("GoldenGrapeGentleman1/pokemon-showdown-agent-battle-grpo", adapter_name="grpo")
model.set_adapter("grpo")
Use in this tutorial
Step 0:
os.environ["POKEMON_AGENT_TIER"] = "champion"
os.environ["POKEMON_HF_BATTLE_GRPO"] = "GoldenGrapeGentleman1/pokemon-showdown-agent-battle-grpo"
Then run Steps 13 → 14 → 15.
- Library
- peft
- License
- apache-2.0
- Created
- Jul 28, 2026
- Updated
- Jul 28, 2026