granite-4.1-3b-heretic/reproduce

Reproduction guide

This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.

Models

• Base model: ibm-granite/granite-4.1-3b (Commit: c065040)

Datasets

• Good prompts: mlabonne/harmless_alpaca (Commit: 02c6a92)
• Bad prompts: mlabonne/harmful_behaviors (Commit: 01cead0)
• Good evaluation prompts: mlabonne/harmless_alpaca (Commit: 02c6a92)
• Bad evaluation prompts: mlabonne/harmful_behaviors (Commit: 01cead0)

Selected trial

• Trial number: 79
• KL divergence: 0.260342
• Refusals: 3/100

System

• Python: 3.12.3 (CPython, GCC 13.3.0) [System]
• Operating system: Linux-6.8.0-124-generic-x86_64-with-glibc2.39 (x86_64)
• CPU: AMD EPYC 7352 24-Core Processor

Accelerators

• CUDA: Detected 1 device(s) (15.57 GB total VRAM)
  • CUDA Version: 12.8
  • Driver Version: 580.159.04
• Devices:
  • CUDA 0: NVIDIA RTX 2000 Ada Generation (15.57 GB)

Environment

• Heretic: v1.4.0 (Origin: PyPI)
• PyTorch: 2.8.0+cu128
• Other dependencies: See requirements.txt.

Contents of this directory

• requirements.txt: The exact versions of all Python packages.
• config.toml: The exact configuration used, including the RNG seed.
• ibm-granite--granite-4--1-3b.jsonl: The Optuna study journal containing the history of all trials.
• SHA256SUMS: Cryptographic hashes for all weight files.
• reproduce.json: A machine-readable file containing all reproducibility information.

How to reproduce

Tip

You can automate this process, including all verification steps, by downloading the reproduce.json file and running heretic --reproduce reproduce.json.

1. Ensure your system matches the specifications in the System section above. Exact reproducibility is only guaranteed if all aspects of your system are identical to the one the model was originally generated on.
2. Install the exact version of Heretic indicated in the Environment section above, from its original source.
3. Install the packages listed in requirements.txt: pip install -r requirements.txt
4. Install the correct version of PyTorch: pip install torch==2.8.0+cu128 --index-url https://download.pytorch.org/whl/cu128
5. Place the provided config.toml in your working directory.
6. Run Heretic without any additional arguments: heretic
7. Wait for the run to finish, then select trial 79 and export the model.
8. Verify that the weight files have been exactly reproduced by comparing their SHA-256 hashes against those in SHA256SUMS: sha256sum -c SHA256SUMS (or look at the hashes online if you uploaded to Hugging Face)

Tip

To use the included Optuna study journal ibm-granite--granite-4--1-3b.jsonl, place it in the checkpoints directory (usually checkpoints/) before running Heretic.

This allows you to export other models from the Pareto front, or to run additional trials without having to re-run the stored trials.