Upload reproduce/README.md with huggingface_hub
Browse files- reproduce/README.md +69 -0
reproduce/README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Reproduction guide
|
| 2 |
+
|
| 3 |
+
This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.
|
| 4 |
+
|
| 5 |
+
## Models
|
| 6 |
+
|
| 7 |
+
- **Base model:** [squ11z1/Mythos-nano](https://huggingface.co/squ11z1/Mythos-nano) (Commit: [`64667ba`](https://huggingface.co/squ11z1/Mythos-nano/commit/64667ba4c7f320348f0398916304d0c22f37c56d))
|
| 8 |
+
|
| 9 |
+
## Datasets
|
| 10 |
+
|
| 11 |
+
- **Good prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
|
| 12 |
+
- **Bad prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
|
| 13 |
+
- **Good evaluation prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
|
| 14 |
+
- **Bad evaluation prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
|
| 15 |
+
|
| 16 |
+
## Selected trial
|
| 17 |
+
|
| 18 |
+
- **Trial number:** 188
|
| 19 |
+
- **KL divergence:** 0.060961
|
| 20 |
+
- **Refusals:** 13/100
|
| 21 |
+
|
| 22 |
+
## System
|
| 23 |
+
|
| 24 |
+
- **Python:** 3.12.3 (CPython, GCC 13.3.0) [Virtualenv/Venv]
|
| 25 |
+
- **Operating system:** Linux-6.8.0-124-generic-x86_64-with-glibc2.39 (x86_64)
|
| 26 |
+
- **CPU:** AMD Ryzen 9 7950X 16-Core Processor
|
| 27 |
+
|
| 28 |
+
### Accelerators
|
| 29 |
+
|
| 30 |
+
- **CUDA:** Detected 1 device(s) (23.51 GB total VRAM)
|
| 31 |
+
- **CUDA Version:** 13.0
|
| 32 |
+
- **Driver Version:** 580.159.03
|
| 33 |
+
- **Devices:**
|
| 34 |
+
- **CUDA 0:** NVIDIA GeForce RTX 4090 (23.51 GB)
|
| 35 |
+
|
| 36 |
+
## Environment
|
| 37 |
+
|
| 38 |
+
- **Heretic:** v1.4.0 (Origin: PyPI)
|
| 39 |
+
- **PyTorch:** 2.12.1+cu130
|
| 40 |
+
- **Other dependencies:** See [`requirements.txt`](requirements.txt).
|
| 41 |
+
|
| 42 |
+
## Contents of this directory
|
| 43 |
+
|
| 44 |
+
- [`requirements.txt`](requirements.txt): The exact versions of all Python packages.
|
| 45 |
+
- [`config.toml`](config.toml): The exact configuration used, including the RNG seed.
|
| 46 |
+
- [`squ11z1--Mythos-nano.jsonl`](squ11z1--Mythos-nano.jsonl): The Optuna study journal containing the history of all trials.
|
| 47 |
+
- [`SHA256SUMS`](SHA256SUMS): Cryptographic hashes for all weight files.
|
| 48 |
+
- [`reproduce.json`](reproduce.json): A machine-readable file containing all reproducibility information.
|
| 49 |
+
|
| 50 |
+
## How to reproduce
|
| 51 |
+
|
| 52 |
+
> [!TIP]
|
| 53 |
+
> You can automate this process, including all verification steps, by downloading the `reproduce.json` file and running
|
| 54 |
+
> `heretic --reproduce reproduce.json`.
|
| 55 |
+
|
| 56 |
+
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.
|
| 57 |
+
1. Install the exact version of Heretic indicated in the **Environment** section above, from its original source.
|
| 58 |
+
1. Install the packages listed in `requirements.txt`: `pip install -r requirements.txt`
|
| 59 |
+
1. Install the correct version of PyTorch: `pip install torch==2.12.1+cu130 --index-url https://download.pytorch.org/whl/cu130`
|
| 60 |
+
1. Place the provided `config.toml` in your working directory.
|
| 61 |
+
1. Run Heretic without any additional arguments: `heretic`
|
| 62 |
+
1. Wait for the run to finish, then select trial **188** and export the model.
|
| 63 |
+
1. Verify that the weight files have been exactly reproduced by comparing their SHA-256 hashes against those in `SHA256SUMS`:
|
| 64 |
+
`sha256sum -c SHA256SUMS` (or look at the hashes online if you uploaded to Hugging Face)
|
| 65 |
+
|
| 66 |
+
> [!TIP]
|
| 67 |
+
> To use the included Optuna study journal `squ11z1--Mythos-nano.jsonl`, place it in the checkpoints directory (usually `checkpoints/`) before running Heretic.
|
| 68 |
+
>
|
| 69 |
+
> This allows you to export other models from the Pareto front, or to run additional trials without having to re-run the stored trials.
|