Initial public release 1.0

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 AtomicoLabs
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+language:
+  - en
+  - es
+library_name: transformers
+pipeline_tag: token-classification
+tags:
+  - pii
+  - ner
+  - deberta
+  - on-device
+base_model: microsoft/deberta-v3-xsmall
+---
+
+# ALF-pii-nano 1.0
+
+Bilingual EN+ES PII token classifier. ALF is the AtomicoLabs model family. **Nano** = under 100M parameters.
+
+Weights: GitHub Release [`v1.0`](https://github.com/AtomicoLabs/ALF-pii-nano/releases/tag/v1.0) and this Hugging Face revision `v1.0`.
+
+| | F1 |
+|---|---|
+| English | 0.897 |
+| Spanish | 0.939 |
+
+Grok reference: EN 0.893 / ES 0.895. Types: `PERSON`, `EMAIL`, `PHONE`, `ADDRESS`, `DATE_DOB`, `ID_NUMBER`, `CREDIT_CARD`, `ACCOUNT_IBAN`, `IP`, `USERNAME_URL`, `ORG`.
+
+## Use
+
+```python
+from transformers import pipeline
+
+ner = pipeline(
+    "token-classification",
+    model="AtomicoLabs/ALF-pii-nano",
+    aggregation_strategy="simple",
+)
+print(ner("Email me at ada@example.com"))
+```
+
+Pin a version with `revision="v1.0"`. Weights are also on the GitHub Release if you want a local path to `from_pretrained`.
+
+## Limits
+
+- Token classifier, not a generative redactor. Pair with your own substitution policy.
+- `PERSON` is the weakest Spanish type (F1 0.78 on the tracked eval).
+- Max 512 tokens. Not a legal or privacy-compliance guarantee.
+
+## Training
+
+Fine-tune of [`microsoft/deberta-v3-xsmall`](https://huggingface.co/microsoft/deberta-v3-xsmall) (MIT) as `DebertaV2ForTokenClassification`, EN+ES SFT, 3 epochs.
+
+## License
+
+MIT. Include this notice and the DeBERTa-v3 MIT notice when you redistribute.

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACCOUNT_IBAN",
+    "2": "B-ADDRESS",
+    "3": "B-CREDIT_CARD",
+    "4": "B-DATE_DOB",
+    "5": "B-EMAIL",
+    "6": "B-ID_NUMBER",
+    "7": "B-IP",
+    "8": "B-ORG",
+    "9": "B-PERSON",
+    "10": "B-PHONE",
+    "11": "B-USERNAME_URL",
+    "12": "I-ACCOUNT_IBAN",
+    "13": "I-ADDRESS",
+    "14": "I-CREDIT_CARD",
+    "15": "I-DATE_DOB",
+    "16": "I-EMAIL",
+    "17": "I-ID_NUMBER",
+    "18": "I-IP",
+    "19": "I-ORG",
+    "20": "I-PERSON",
+    "21": "I-PHONE",
+    "22": "I-USERNAME_URL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "B-ACCOUNT_IBAN": 1,
+    "B-ADDRESS": 2,
+    "B-CREDIT_CARD": 3,
+    "B-DATE_DOB": 4,
+    "B-EMAIL": 5,
+    "B-ID_NUMBER": 6,
+    "B-IP": 7,
+    "B-ORG": 8,
+    "B-PERSON": 9,
+    "B-PHONE": 10,
+    "B-USERNAME_URL": 11,
+    "I-ACCOUNT_IBAN": 12,
+    "I-ADDRESS": 13,
+    "I-CREDIT_CARD": 14,
+    "I-DATE_DOB": 15,
+    "I-EMAIL": 16,
+    "I-ID_NUMBER": 17,
+    "I-IP": 18,
+    "I-ORG": 19,
+    "I-PERSON": 20,
+    "I-PHONE": 21,
+    "I-USERNAME_URL": 22,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

labels.json

@@ -0,0 +1,52 @@
+{
+  "labels": [
+    "O",
+    "B-ACCOUNT_IBAN",
+    "B-ADDRESS",
+    "B-CREDIT_CARD",
+    "B-DATE_DOB",
+    "B-EMAIL",
+    "B-ID_NUMBER",
+    "B-IP",
+    "B-ORG",
+    "B-PERSON",
+    "B-PHONE",
+    "B-USERNAME_URL",
+    "I-ACCOUNT_IBAN",
+    "I-ADDRESS",
+    "I-CREDIT_CARD",
+    "I-DATE_DOB",
+    "I-EMAIL",
+    "I-ID_NUMBER",
+    "I-IP",
+    "I-ORG",
+    "I-PERSON",
+    "I-PHONE",
+    "I-USERNAME_URL"
+  ],
+  "id2label": {
+    "0": "O",
+    "1": "B-ACCOUNT_IBAN",
+    "2": "B-ADDRESS",
+    "3": "B-CREDIT_CARD",
+    "4": "B-DATE_DOB",
+    "5": "B-EMAIL",
+    "6": "B-ID_NUMBER",
+    "7": "B-IP",
+    "8": "B-ORG",
+    "9": "B-PERSON",
+    "10": "B-PHONE",
+    "11": "B-USERNAME_URL",
+    "12": "I-ACCOUNT_IBAN",
+    "13": "I-ADDRESS",
+    "14": "I-CREDIT_CARD",
+    "15": "I-DATE_DOB",
+    "16": "I-EMAIL",
+    "17": "I-ID_NUMBER",
+    "18": "I-IP",
+    "19": "I-ORG",
+    "20": "I-PERSON",
+    "21": "I-PHONE",
+    "22": "I-USERNAME_URL"
+  }
+}

manifest.json

@@ -0,0 +1,25 @@
+{
+  "id": "ALF-pii-nano-1.0",
+  "family": "ALF",
+  "track": "pii",
+  "tier": "nano",
+  "version": "1.0",
+  "description": "AtomicoLabs model family bilingual EN+ES PII token classifier. DeBERTa-v3-xsmall finetune.",
+  "files": {
+    "model": "model.safetensors",
+    "config": "config.json",
+    "tokenizer": "tokenizer.json"
+  },
+  "format": "safetensors",
+  "params": "~50M",
+  "max_length": 512,
+  "languages": ["en", "es"],
+  "base": "microsoft/deberta-v3-xsmall",
+  "architecture": "DebertaV2ForTokenClassification",
+  "scores": {
+    "f1_en": 0.897,
+    "f1_es": 0.939,
+    "grok_en": 0.893,
+    "grok_es": 0.895
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:418215e997425e703c41cfd1d46ef306073768b24cb80c4c733fa0feccfe754f
+size 282788220

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}