DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to refit all 582 controller parameters from trajectories with State of Thought

Retrain the controller from released offline trajectories without a backbone pass.

  • Research
  • Advanced
  • 1 hour
  • From the README
  • Any agent

Who it is forA researcher testing whether the controller fit is stable, or modifying the training setup, who needs to refit it without running the backbone.

The problemRe-running the backbone for every training experiment is slow, so a fit from saved trajectories is needed for controlled comparisons.

The outcomeA refitted controller produced from the released trajectories, with the training run recorded in the same resumable format as evaluation.

What you need first

  • Python with pip and git installed
  • A virtual environment for the install
  • Hugging Face access for backbone weights, with license acceptance and hf auth login for gated models
  • Enough disk space and GPU memory for the chosen backbone when running evaluation

Steps

  1. Run git clone https://github.com/GongZhiren/State-of-Thought.git
  2. Run cd State-of-Thought
  3. Run python -m pip install -e . inside an activated virtual environment
  4. Run sot train --config experiments/paper/llama-3.1-8b.yaml
  5. Run sot checkpoint verify <path to refitted controller.pt> to check the new file (inferred, check the README)

Prompt for your agent

In the repo GongZhiren/State-of-Thought, install the package and run sot train with experiments/paper/llama-3.1-8b.yaml. Report the output controller path, run sot checkpoint verify on it, and state whether its parameter count is 582.

Caveat. A refitted controller will not match the frozen released checkpoint hashes, so label any refit clearly and do not present it as the paper controller.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page