You can deploy this model and start earning money today!

maxbittker/
opus-27b-dsl-step65-2026-05-01

Name: opus-27b-dsl-step65-2026-05-01
Availability: InStock

Views

No views yet

opus-27b-dsl-step65-2026-05-01

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 65 / 300.

Source training run

wandb: 67h0ngi6
tinker checkpoint: tinker://c4901d4e-3f47-5a93-a26e-af7460a95caf:train:0/sampler_weights/000065
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-step65-2026-05-01"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)