opsd1: CoT-control LoRA checkpoints on Qwen/Qwen3.8-27B

Model organisms from a MATS sprint on CoT controllability (training a model to follow instructions about its own reasoning trace, and the related obfuscation / OPSD / many-types runs). Research artifacts only; do not deploy. Each step<N>/ folder is a rank-32 PEFT adapter exported from a Tinker sampler checkpoint, with tinker_provenance.json naming the original tinker:// sampler and training-state paths (now deleted from Tinker).

Checkpoints: step10/, step20/, step30/, step40/.

Training code, config and evaluations: https://github.com/johntrob14/tricky_little_guys, cot-control/rl/ and cot-control/results/rl/opsd1/ (config.json, checkpoints.json), run diary in runs/.

Downloads last month: 60

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for latentMO/cotcontrol-qwen38-opsd1

Base model

Qwen/Qwen3.8-27B

Adapter

(303)

this model