You can deploy this model and start earning money today!

GoodStartLabs/
opus-k26-py-step150-2026-05-02

Name: opus-k26-py-step150-2026-05-02
Availability: InStock

Views

No views yet

opus-k26-py-step150-2026-05-02

LoRA adapter trained with reinforcement learning (GRPO via Thinking Machines' Tinker SDK) on the Opus-Magnum puzzle-solving REPL benchmark, snapshotted at training step 150.

Training setup

Base model: moonshotai/Kimi-K2.6
Renderer: kimi_k25
Representation: python (action language the agent emits)
Adapter: LoRA, rank 32
RL recipe: GRPO via Tinker
Hyperparameters:
- learning_rate = 1e-5
- group_size = 8, groups_per_batch = 16
- max_tokens = 1024, max_trajectory_tokens = 12000
- distances = 1,2,3,4
- max_steps_off_policy = None
- save_every = 5

Files

adapter_model.safetensors — Tinker raw LoRA adapter weights
adapter_config.json — adapter metadata (rank, alpha, target modules)
README.md — this file

Provenance

Tinker checkpoint:

tinker://0aedf8c7-c9ad-57de-b8d5-d451fd058fde:train:0/sampler_weights/000150

Converting to PEFT format

The files above are in Tinker's raw adapter format. To convert to PEFT format suitable for direct vLLM --lora-modules loading, run on a machine that can host the base model: