| base_model: Qwen/Qwen3.5-4B | |
| library_name: peft | |
| tags: | |
| - tinker | |
| - peft | |
| - lora | |
| - opus-magnum | |
| # opus-4b-dsl-step180-2026-04-29 | |
| 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 180 / 300. | |
| ## Source training run | |
| - wandb: [opus-4b-dsl-2026-04-29 (onya5lq7)](https://wandb.ai/websim/opus-task/runs/onya5lq7) | |
| - tinker checkpoint: `tinker://883a6f46-abad-5e6e-b740-9c0051523362:train:0/sampler_weights/000180` | |
| - distances: 1, 2, 3 | |
| - 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/Qwen3.5-4B" | |
| adapter = "maxbittker/opus-4b-dsl-step180-2026-04-29" | |
| tok = AutoTokenizer.from_pretrained(base) | |
| model = AutoModelForCausalLM.from_pretrained(base, device_map="auto") | |
| model = PeftModel.from_pretrained(model, adapter) | |
| ``` | |