| --- |
| license: "other" |
| license_name: "statim-weights" |
| license_link: "https://huggingface.co/Beko2210/statim-decide-multilingual-base-pii/blob/main/LICENSE-MODEL.md" |
| base_model: "Beko2210/statim-decide-multilingual-base" |
| base_model_relation: "adapter" |
| library_name: "gguf" |
| language: ["ar", "de", "en", "es", "fr", "it", "ja", "nl", "ru", "sv", "zh"] |
| tags: ["statim", "lora", "adapter", "gguf", "pii"] |
| pipeline_tag: "zero-shot-classification" |
| model-index: [{"name": "statim-decide-multilingual-base-pii", "results": [{"task": {"type": "text-classification"}, "dataset": {"name": "pii ar (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.9067}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii de (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.8667}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii en (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.9267}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii es (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.8933}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii fr (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.94}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii it (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.92}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii ja (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.9267}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii nl (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.8667}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii ru (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.9467}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii sv (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.8733}]}, {"task": {"type": "text-classification"}, "dataset": {"name": "pii zh (n=150, seed=20260927, z=2.0, alpha=0.05)", "type": "pii"}, "metrics": [{"type": "accuracy", "value": 0.9467}]}]}] |
| --- |
| |
| # Statim Decide Multilingual Base: PII adapter |
|
|
| A LoRA adapter that improves the PII decisions of |
| [`Beko2210/statim-decide-multilingual-base`](https://huggingface.co/Beko2210/statim-decide-multilingual-base) **0.7.0**. |
| Checked with Statim 0.8.3: the published f32 file loads it merged at load, the q8_0 file as runtime LoRA. LoRA adapters need Statim 0.8.0 or later. |
| |
| ## Quick start |
| |
| ```sh |
| hf download Beko2210/statim-decide-multilingual-base statim-decide-multilingual-base-q8_0.gguf --local-dir models |
| hf download Beko2210/statim-decide-multilingual-base-pii statim-decide-multilingual-base-pii.lora.gguf --local-dir models |
| statim serve -m multilingual=models/statim-decide-multilingual-base-q8_0.gguf --adapter multilingual:pii=models/statim-decide-multilingual-base-pii.lora.gguf --port 8080 |
| |
| curl -s localhost:8080/v1/systemone -d '{"state": {"text": "Hi, this is Anna Schmidt. Call me back at +49 170 1234567."}, "questions": {"pii": {"type": "noul", "instructions": "Does the text contain a phone number?"}}, "adapter": "pii"}' |
| curl -s localhost:8080/v1/systemone -d '{"state": {"text": "Hi, this is Anna Schmidt. Call me back at +49 170 1234567."}, "questions": {"pii": {"type": "noul", "instructions": "Does the text contain a phone number?"}}, "adapter": "auto"}' |
| ``` |
| |
| Python (Python SDK 0.8.3 or later): |
| |
| ```python |
| from statim import Client |
| client = Client("http://127.0.0.1:8080") |
| client.decide({"text": "Hi, this is Anna Schmidt. Call me back at +49 170 1234567."}, {"pii": {"type": "noul", "instructions": "Does the text contain a phone number?"}}, adapter="pii") |
| ``` |
| |
| ## Results (experiment's f32 run) |
| |
| Each cell uses 150 items (seed 20260927). |
| |
| | Language | Base | Adapter | Change (points) | Verdict | Qwen3-8B zero-shot | |
| |---|---:|---:|---:|---|---:| |
| | ar | 0.8467 | **0.9067** | +6.00 | within noise | 0.893 | |
| | de | 0.8400 | **0.8667** | +2.67 | within noise | 0.893 | |
| | en | 0.8933 | **0.9267** | +3.34 | within noise | 0.887 | |
| | es | 0.8533 | **0.8933** | +4.00 | within noise | 0.867 | |
| | fr | 0.8933 | **0.9400** | +4.67 | within noise | 0.880 | |
| | it | 0.8400 | **0.9200** | +8.00 | gain (2 SE) | 0.873 | |
| | ja | 0.8467 | **0.9267** | +8.00 | gain (2 SE) | 0.893 | |
| | nl | 0.7600 | **0.8667** | +10.67 | gain (2 SE) | 0.800 | |
| | ru | 0.9067 | **0.9467** | +4.00 | within noise | 0.947 | |
| | sv | 0.8333 | **0.8733** | +4.00 | within noise | 0.800 | |
| | zh | 0.9000 | **0.9467** | +4.67 | within noise | 0.920 | |
| | **Mean** | 0.8558 | **0.9103** | +5.46 | — | 0.878 | |
| |
| The pooled family change is **+5.46 points** with **2 SE = 2.22 points** (gain). |
| |
| A single cell of 150 items rarely clears 2 SE on its own; the decision uses the pooled family. |
| |
| Decision rule: promote when the category family gains more than 2 standard errors, pooled by rows or by suites, and nothing regresses. A regression is a pooled drop beyond 2 standard errors under either pooling, or a drop in one language cell that stays significant after Holm-Bonferroni (family-wise 5 %). |
| |
| Statim is trained on this category, while [Qwen3-8B runs zero-shot](https://github.com/BEKO2210/statim/blob/main/docs/BASELINES.md). |
| |
| ## Checked on the published files |
| |
| | Weights | Adapter mode | Base mean | Adapter mean | Change (points) | Cell for cell as in the experiment | |
| |---|---|---:|---:|---:|---| |
| | f32 | merged at load | 0.8558 | 0.9103 | +5.46 | yes | |
| | q8_0 | runtime LoRA | 0.8558 | 0.9109 | +5.52 | — (experiment: f32) | |
|
|
| ## Training |
|
|
| | Source | Rows | Licence | |
| |---|---:|---| |
| | [`E3-JSI/synthetic-multi-pii-ner-v1`](https://huggingface.co/datasets/E3-JSI/synthetic-multi-pii-ner-v1) (`default`) | 2,971 | MIT | |
| | [`Wismut/nym-pii-multilingual-data`](https://huggingface.co/datasets/Wismut/nym-pii-multilingual-data) (`default`) | 6,200 | MIT | |
| | [`gretelai/gretel-pii-masking-en-v1`](https://huggingface.co/datasets/gretelai/gretel-pii-masking-en-v1) (`default`) | 6,200 | Apache-2.0 | |
| | [`gretelai/synthetic_pii_finance_multilingual`](https://huggingface.co/datasets/gretelai/synthetic_pii_finance_multilingual) (`default`) | 6,200 | Apache-2.0 | |
| | [`nvidia/Nemotron-PII`](https://huggingface.co/datasets/nvidia/Nemotron-PII) (`default`) | 6,200 | CC-BY-4.0 | |
| | [`urchade/synthetic-pii-ner-mistral-v1`](https://huggingface.co/datasets/urchade/synthetic-pii-ner-mistral-v1) (`data.json`) | 6,200 | Apache-2.0 | |
|
|
| LoRA rank **16**, alpha **32.0**, dropout **0.05**; |
| target modules `Wqkv`, `Wo`, `Wi`; **88** wrapped modules and |
| **3,379,200** trainable parameters. |
|
|
| - Items: **33,571 train**, **400 dev**. |
| - Updates: **1,172**. |
| - Dev accuracy: **0.8375** before, **0.8725** after. |
| - Time: **1631.7 seconds**; peak memory: **2,332 MB**. |
|
|
| ## Provenance |
|
|
| - Adapter GGUF SHA-256: `2991a33b5d9db4f5b679081885faab1f84289d6eae7660830447e790bd168b29` |
| - PEFT safetensors SHA-256: `f8e7e674ab868b312ff32f403552daa436e7437411e83fa0ece60187431a2d6f` |
| - Training checkpoint `model.safetensors` SHA-256: `c44425f14ac9d55508f73a6f371e4e2802ed59e646287c3abbec10b653a19840` |
| - Base fingerprint: `e7a8fa743b4920850167b587226e339d651be0244fcc6a9e24fff8ed5073bae5` |
| - Training mixture SHA-256: `b8a87e85f3bf72b61509555aba9148358760d3329ecf37a36cebd94f9358cb03` |
| - Source registry SHA-256: `309ce8ec262886b3bfaa529934151ae0c1879595c26301e4269da276d95cbfcd` |
|
|
| Experiment commands (paths relative to the Statim repository): |
|
|
| - `train`: `'.venv-train/bin/python' 'tools/finetune/train_lora.py' 'models/laya-multilingual-v9' --mixture 'data/mixture-v8.jsonl.gz' --category pii --registry 'tools/finetune/sources/v6-keep.json' --out 'models/lora-exp1/pii' --device cuda --epochs 2` |
| - `convert`: `'.venv/bin/python' 'tools/convert_lora.py' 'models/lora-exp1/pii' -o 'models/lora-exp1/pii.lora.gguf' --base 'models/laya-multilingual-v9-f32.gguf' --category pii --name pii` |
| - `serve`: `'build-vk/statim' serve -m 'multilingual=models/laya-multilingual-v9-f32.gguf' --adapter 'multilingual:pii=models/lora-exp1/pii.lora.gguf' --device vulkan --threads 16 --port 8098 --no-access-log --inference-timeout 600` |
| - `eval_base`: `'.venv/bin/python' 'bench/eval_categories.py' --strict --url http://127.0.0.1:8098 --model multilingual --suites pii --n 150 --seed 20260927 --exclude-mixture 'data/mixture-v8.jsonl.gz' --out 'models/lora-exp1/pii.base.jsonl'` |
| - `eval_adapter`: `'.venv/bin/python' 'bench/eval_categories.py' --strict --url http://127.0.0.1:8098 --model multilingual --suites pii --n 150 --seed 20260927 --exclude-mixture 'data/mixture-v8.jsonl.gz' --adapter pii --out 'models/lora-exp1/pii.adapter.jsonl'` |
|
|
| Protocol and experiment: [docs/ADAPTERS.md](https://github.com/BEKO2210/statim/blob/main/docs/ADAPTERS.md). Full reproduction |
| instructions: [REPRODUCE.md](https://github.com/BEKO2210/statim/blob/main/REPRODUCE.md). |
|
|
| ## Intended use and limits |
|
|
| - This adapter only helps its category; route requests with `"pii"` or `"auto"`. |
| - Bound to `Beko2210/statim-decide-multilingual-base` 0.7.0 by the base fingerprint `e7a8fa743b492085…` (`statim.lora.base_fingerprint`, SHA-256 over the checkpoint's norm and bias tensors); Statim refuses the adapter on a base whose fingerprint differs. |
| - Languages outside the evaluated list are untested. |
| - Each language cell has 150 items. |
| - Do not automate decisions about people without human review. |
|
|
| ## Licence |
|
|
| The weights may be used under any one of: PolyForm Noncommercial 1.0.0, PolyForm Small Business |
| 1.0.0 (free commercial use below 100 people and 1 M USD revenue), PolyForm Free Trial 1.0.0 (any |
| company, fewer than 32 days), or a Statim commercial licence |
| ([COMMERCIAL.md](https://github.com/BEKO2210/statim/blob/main/COMMERCIAL.md)). Texts in [LICENSE-MODEL.md](LICENSE-MODEL.md). |
| The Statim engine is Apache-2.0. |
|
|
| Training data attribution is listed source by source above, with the row count and licence read |
| from the experiment registry. |
|
|
