temsa's picture
Add rc6 release with decoder repair improvements
c487a4b verified
{
"repo_id": "temsa/OpenMed-mLiteClinical-IrishCorePII-135M-v2-rc6",
"recommended_inference": {
"full_checkpoint": {
"script": "inference_mask.py",
"ppsn_decoder": "word_aligned",
"general_decoder": "irish_core_label_aware",
"ppsn_min_score": 0.55,
"other_min_score": 0.5,
"device": "cpu"
},
"onnx_q8": {
"script": "inference_mask_onnx.py",
"onnx_artifact": "onnx/model_quantized.onnx",
"ppsn_decoder": "word_aligned",
"general_decoder": "irish_core_label_aware",
"ppsn_min_score": 0.55,
"other_min_score": 0.5,
"device": "cpu"
}
},
"smoke_texts": [
"Duradh liom mo uimhir 1234567T a sholatar agus me ag denamh iarratais.",
"Is e mo upsp na 1234567tw agus teastaionn uaim eolas faoi liuntas curamora.",
"My PPSN is 1234567T and my sort code is 90-00-17.",
"Please provide your passport: NN5123456 and call me on 0851234567.",
"My IBAN is IE29AIBK93115212345678 and my email is aidan.oiarraidh@example.ie."
],
"known_limit_texts": [
"Passport PA 1234567 was used to board the flight.",
"Card 4242 4242 4242 4242 in very short contexts should still be QA tested.",
"Compact mobile numbers in very short mixed-numeric contexts should still be QA tested."
]
}