opus-4b-dsl-step170-2026-04-29
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 170 / 300.
Source training run
- wandb: opus-4b-dsl-2026-04-29 (onya5lq7)
- tinker checkpoint:
tinker://883a6f46-abad-5e6e-b740-9c0051523362:train:0/sampler_weights/000170 - distances: 1, 2, 3
- task types: move, transmute
- learning rate: 1e-5
- group size: 8, groups per batch: 16
- renderer: qwen3_5_disable_thinking
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "Qwen/Qwen3.5-4B"
adapter = "maxbittker/opus-4b-dsl-step170-2026-04-29"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
model = PeftModel.from_pretrained(model, adapter)
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "maxbittker/opus-4b-dsl-step170-2026-04-29")