Token Classification
Transformers
ONNX
Safetensors
English
Irish
distilbert
pii
de-identification
ireland
irish
gaelic
diffusion-style
denoising
ppsn
eircode
int8
dynamic-quantization
cpu
Eval Results (legacy)
Instructions to use temsa/IrishCore-DiffMask-135M-v1-rc3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use temsa/IrishCore-DiffMask-135M-v1-rc3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="temsa/IrishCore-DiffMask-135M-v1-rc3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("temsa/IrishCore-DiffMask-135M-v1-rc3") model = AutoModel.from_pretrained("temsa/IrishCore-DiffMask-135M-v1-rc3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download qa_config.json from temsa/IrishCore-DiffMask-135M-v1-rc3: direct link, hf CLI and curl.
- Browser
- Download file 656 Bytes
-
https://huggingface.co/temsa/IrishCore-DiffMask-135M-v1-rc3/resolve/main/qa_config.json
- Command line
-
hf download hf://temsa/IrishCore-DiffMask-135M-v1-rc3/qa_config.json
-
curl -L -o qa_config.json https://huggingface.co/temsa/IrishCore-DiffMask-135M-v1-rc3/resolve/main/qa_config.json
656 Bytes
| { | |
| "release": "IrishCore-DiffMask-135M-v1-rc3", | |
| "repo_id": "temsa/IrishCore-DiffMask-135M-v1-rc3", | |
| "decoder": "raw_only_diffmask_token_span", | |
| "diffusion_style_training": true, | |
| "runtime_diffusion": false, | |
| "min_score": 0.5, | |
| "recommended_backend": "onnx_q8_cpu", | |
| "onnx_file": "onnx/model_quantized.onnx", | |
| "full_example": "My PPSN is 1234567TW, my Eircode is D02 X285, and my phone is 087 123 4567.", | |
| "notes": [ | |
| "No scanner or validator layer is required for release behavior.", | |
| "Use the bundled inference scripts or import common.decode_token_presence_segments.", | |
| "The bundled scripts mask with [PII:LABEL] placeholders." | |
| ] | |
| } | |