ztom-gemma3-1b-recovery

Recovering a Model That Forgot Its Original Task

Sequential fine-tuning caused task interference that degraded accuracy. Authentrics ZTOM restores the lost capability — gradient-free, with no retraining from scratch.

Authentrics is a high-performance neural-network analysis library (Python wheel over a C++ core). It audits and maintains model checkpoints: parameter/behavioral drift, compliant data removal without full retraining, and loss-driven optimization without backprop. Analysis runs locally on your machine — only project metadata (names, descriptions) is exchanged with Authentrics servers, never your model weights.

What this demo shows

• ztom_analysis — optimize a model against a Callable[[output], float] loss without backprop/retraining.

Reproduce this analysis

The public code and outputs behind this demo live in https://github.com/Authentrics-ai/authentrics-analysis-examples/blob/main/hf_legal_understanding.ipynb.

Weights: This card documents a reproducible recovery result on google/gemma-3-1b-it; the recovered checkpoint is not redistributed here. Reproduce it locally with the SDK below.

Reproduce it yourself

pip install authentrics            # Linux x86_64, Python 3.11–3.13
authrx init                        # paste API key (stored at ~/.local/state/authentrics/api_key)
# or, for CI / non-interactive:
export AUTHRX_API_KEY=<your_api_key>

Generate an API key and read the full docs at https://app.authentrics.ai/.

---

Produced with the Authentrics SDK v0.35.1 — checkpoint analysis that runs locally on your own hardware; only project metadata ever leaves your machine, never your weights.

Links

• App & API keys: https://app.authentrics.ai/
• Docs & API reference: https://app.authentrics.ai/docs
• Examples & user guide: https://github.com/Authentrics-ai/authentrics-analysis-examples
• Contact: [email protected]