Modelpublic

maxbittker/opus-4b-dsl-step180-2026-04-29

sourceHugging Faceupdated 5mo agoView on Hugging Face

0likes3downloads

Model Card

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)
—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: qwen35disable_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)