obi / token-classification updated 1 year ago

deid_roberta_i2b2

Name: deid_roberta_i2b2
Author: obi

A RoBERTa [[Liu et al., 2019]](https://arxiv.org/pdf/1907.11692.pdf) model fine-tuned for de-identification of medical notes. Sequence Labeling (token classification): The model was trained to predict protected health information (PHI/PII) entities (spans). A list of protected health information categories is given by HIPAA. A token can either be classified as non-PHI or as one of the 11 PHI types. Token predictions...

Params

350 M

Context

512

Downloads 30d

423 K

Likes

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

432 K418 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	1.4 GB	2.1 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: RobertaForTokenClassification
Parameters: 350 M
Tensor type: F32
Context length: 512
Vocabulary: 50,265
Layers / heads: 24 / 16
Licence: mit
First seen on the Hub: 2022-03-02
Training datasets: I2B2
Added to our catalog: 2026-07-28

Compare with

indonesian-roberta-base-posp-tagger 3.1 M stanford-deidentifier-base 1.9 M punctuate-all 708 K bert-large-cased-finetuned-conll03-english 699 K ner-english-fast 543 K bert-portuguese-ner 452 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB