---
base_model: Qwen/Qwen3-4B
library_name: transformers
tags:
- battle game
- showdown
- sft
- unsloth
- rocm
license: apache-2.0
---

# turn-based battle game Agent — Full SFT

Fine-tuned **Qwen3-4B** on **2.3M** turn-based battle game replay logs. The model reads raw battle protocol lines and outputs the next action as `move …` or `switch …`.

**Use case:** Competitive tier agent for gen9randombattle — load directly for inference or as the base for battle-oriented GRPO.

## Quick start

```python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="GoldenGrapeGentleman1/battle game-showdown-agent-full-sft",
    max_seq_length=2048,
    load_in_4bit=False,
)
```

## Training

| Setting | Value |
|---------|-------|
| Base model | Qwen/Qwen3-4B |
| Data | Raw Showdown replay logs (~2.3M samples) |
| Method | Full SFT (merged weights) |
| Hardware | AMD Instinct MI300X, ROCm, bfloat16 |

## Tutorial

End-to-end ROCm notebook: [battle game LLM Agent with Unsloth](https://github.com/ROCm/gpuaidev) — set `POKEMON_AGENT_TIER=competitive` and `POKEMON_HF_FULL_SFT=GoldenGrapeGentleman1/battle game-showdown-agent-full-sft`.

## License

Apache-2.0 (base model Qwen3-4B).