55 lines
3.3 KiB
Markdown
55 lines
3.3 KiB
Markdown
|
# Reproduction guide
|
||
|
|
|
||
|
|
This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.
|
||
|
|
|
||
|
|
## Models
|
||
|
|
|
||
|
|
- **Base model:** [c4tdr0ut/grok-oss-Apollyon-8B](https://huggingface.co/c4tdr0ut/grok-oss-Apollyon-8B) (Commit: [`199d817`](https://huggingface.co/c4tdr0ut/grok-oss-Apollyon-8B/commit/199d817b1db576a2485528c8745492f0df926fe4))
|
||
|
|
|
||
|
|
## 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:** 170
|
||
|
|
- **KL divergence:** 0.005239
|
||
|
|
- **Refusals:** 5/100
|
||
|
|
|
||
|
|
## Environment
|
||
|
|
|
||
|
|
- **Heretic:** v1.4.0 (Origin: PyPI)
|
||
|
|
- **PyTorch:** 2.12.0+rocm7.2
|
||
|
|
- **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.
|
||
|
|
- [`c4tdr0ut--grok-oss-Apollyon-8B.jsonl`](c4tdr0ut--grok-oss-Apollyon-8B.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
|
||
|
|
|
||
|
|
> [!TIP]
|
||
|
|
> You can automate this process, including all verification steps, by downloading the `reproduce.json` file and running
|
||
|
|
> `heretic --reproduce reproduce.json`.
|
||
|
|
|
||
|
|
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+rocm7.2 --index-url https://download.pytorch.org/whl/rocm7.2`
|
||
|
|
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 **170** 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 `c4tdr0ut--grok-oss-Apollyon-8B.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.
|