Model card: link the canonical leaderboard; declare the fine-tune relation to the base model
Browse files
README.md
CHANGED
|
@@ -7,6 +7,7 @@ pipeline_tag: token-classification
|
|
| 7 |
tags: [pii, ner, privacy, dlp, onnx, xlm-roberta]
|
| 8 |
library_name: onnxruntime
|
| 9 |
base_model: FacebookAI/xlm-roberta-base
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: scnsoft-pii-encoder
|
| 12 |
results:
|
|
@@ -60,7 +61,7 @@ XML, SQL, CSV, key=value, log lines, Markdown tables, OCR output — as well as
|
|
| 60 |
comprises 3,500 rows, 500 from each of seven third-party datasets. Precision, recall and F1 are
|
| 61 |
computed over characters and are label-agnostic, micro-averaged within each dataset and then
|
| 62 |
averaged across the seven. Live results for every entrant:
|
| 63 |
-
[leaderboard](https://huggingface.co/spaces/
|
| 64 |
|
| 65 |
**Conflict of interest.** PII Bench is built and published by ScienceSoft, the developer of
|
| 66 |
this model. Four of its seven datasets (TAB, FactRuEval, MEDDOCAN, IAHLT) informed changes to
|
|
|
|
| 7 |
tags: [pii, ner, privacy, dlp, onnx, xlm-roberta]
|
| 8 |
library_name: onnxruntime
|
| 9 |
base_model: FacebookAI/xlm-roberta-base
|
| 10 |
+
base_model_relation: finetune
|
| 11 |
model-index:
|
| 12 |
- name: scnsoft-pii-encoder
|
| 13 |
results:
|
|
|
|
| 61 |
comprises 3,500 rows, 500 from each of seven third-party datasets. Precision, recall and F1 are
|
| 62 |
computed over characters and are label-agnostic, micro-averaged within each dataset and then
|
| 63 |
averaged across the seven. Live results for every entrant:
|
| 64 |
+
[leaderboard](https://huggingface.co/spaces/ScienceSoft/piibench-leaderboard).
|
| 65 |
|
| 66 |
**Conflict of interest.** PII Bench is built and published by ScienceSoft, the developer of
|
| 67 |
this model. Four of its seven datasets (TAB, FactRuEval, MEDDOCAN, IAHLT) informed changes to
|