Upload reproduce/README.md with huggingface_hub

reproduce/README.md

@@ -0,0 +1,71 @@
+# Reproduction guide
+
+This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.
+> [!WARNING]
+> **Local code**
+>
+> This system installed Heretic from a local directory or wheel. Uncommitted or experimental code may have been executed.
+>
+> Reproducibility *cannot* be guaranteed in this environment.
+
+
+## Models
+
+- **Base model:** [TheDrummer/Anubis-Mini-8B-v1](https://huggingface.co/TheDrummer/Anubis-Mini-8B-v1) (Commit: [`696f5b9`](https://huggingface.co/TheDrummer/Anubis-Mini-8B-v1/commit/696f5b956f0511168d98cd32106299cebc3cc12b))
+
+## Datasets
+
+- **Good prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
+- **Bad prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
+- **Good evaluation prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
+- **Bad evaluation prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
+
+## Selected trial
+
+- **Trial number:** 200
+- **KL divergence:** 0.008160
+- **Refusals:** 6/100
+
+## System
+
+- **Python:** 3.12.3 (CPython, GCC 13.3.0) [Virtualenv/Venv]
+- **Operating system:** Linux-6.17.0-1021-nvidia-aarch64-with-glibc2.39 (aarch64)
+- **CPU:** Cortex-X925
+
+### Accelerators
+
+- **CUDA:** Detected 1 device(s) (121.69 GB total VRAM)
+  - **CUDA Version:** 13.0
+  - **Driver Version:** 580.159.03
+- **Devices:**
+  - **CUDA 0:** NVIDIA GB10 (121.69 GB)
+
+## Environment
+
+- **Heretic:** v1.3.0 (Origin: Local)
+- **PyTorch:** 2.12.0+cu130
+- **Other dependencies:** See [`requirements.txt`](requirements.txt).
+
+## Contents of this directory
+
+- [`requirements.txt`](requirements.txt): The exact versions of all Python packages.
+- [`config.toml`](config.toml): The exact configuration used, including the RNG seed.
+- [`TheDrummer--Anubis-Mini-8B-v1.jsonl`](TheDrummer--Anubis-Mini-8B-v1.jsonl): The Optuna study journal containing the history of all trials.
+- [`SHA256SUMS`](SHA256SUMS): Cryptographic hashes for all weight files.
+- [`reproduce.json`](reproduce.json): A machine-readable file containing all reproducibility information.
+
+## How to reproduce
+
+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.
+1. Install the exact version of Heretic indicated in the **Environment** section above, from its original source.
+1. Install the packages listed in `requirements.txt`: `pip install -r requirements.txt`
+1. Install the correct version of PyTorch: `pip install torch==2.12.0+cu130 --index-url https://download.pytorch.org/whl/cu130`
+1. Place the provided `config.toml` in your working directory.
+1. Run Heretic without any additional arguments: `heretic`
+1. Wait for the run to finish, then select trial **200** and export the model.
+1. 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 `TheDrummer--Anubis-Mini-8B-v1.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.