Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
openobscure
/
tinybert4l-pii-ner-int8
like
0
Follow
openobscure
1
Token Classification
ONNX
BramVanroy/conll2003
leondz/wnut_17
English
bert
ner, pii, pii-detection, privacy, token-classification, onnx, int8, quantized
Eval Results (legacy)
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
README.md exists but content is empty.
Downloads last month
11
Inference Providers
NEW
Token Classification
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for
openobscure/tinybert4l-pii-ner-int8
Base model
huawei-noah/TinyBERT_General_4L_312D
Quantized
(
6
)
this model
Datasets used to train
openobscure/tinybert4l-pii-ner-int8
leondz/wnut_17
Updated
Jan 18, 2024
•
2.89k
•
19
BramVanroy/conll2003
Viewer
•
Updated
Nov 14, 2025
•
20.7k
•
470
•
2
Evaluation results
F1
on openobscure-pii-eval
OpenObscure NER Benchmark (760 samples, INT8 ONNX, Apple M-series)
0.856
Recall
on openobscure-pii-eval
OpenObscure NER Benchmark (760 samples, INT8 ONNX, Apple M-series)
0.970
Precision
on openobscure-pii-eval
OpenObscure NER Benchmark (760 samples, INT8 ONNX, Apple M-series)
0.950
Inference Latency p50 (ms)
on openobscure-pii-eval
OpenObscure NER Benchmark (760 samples, INT8 ONNX, Apple M-series)
0.750
Inference Latency p95 (ms)
on openobscure-pii-eval
OpenObscure NER Benchmark (760 samples, INT8 ONNX, Apple M-series)
0.950