---
base_model: Qwen/Qwen3.5-27B
library_name: peft
tags:
- tinker
- peft
- lora
- opus-magnum
---

# opus-27b-dsl-step45-2026-05-01

LoRA adapter (rank 32) trained with RL on a custom Opus-Magnum-style motion-planning task using the **dsl** answer representation. Snapshot at training step 45 / 300.

## Source training run

- wandb: [`67h0ngi6`](https://wandb.ai/websim/opus-task/runs/67h0ngi6)
- tinker checkpoint: `tinker://c4901d4e-3f47-5a93-a26e-af7460a95caf:train:0/sampler_weights/000045`
- distances: 1, 2, 3, 4
- task types: move, transmute (no bond)
- learning rate: 1e-5
- group size: 8, groups per batch: 16
- renderer: qwen3_5_disable_thinking

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "Qwen/Qwen3.5-27B"
adapter = "maxbittker/opus-27b-dsl-step45-2026-05-01"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
```