finbert vs deberta-v3-base-prompt-injection-v2
Specs, VRAM requirements and download trends — updated 10 November 2026.
ProsusAI · A · Open weights
Params
110 M
Context
512
30d
3.3 M
cc-by-nc-sa-4.0 · non-commercial
protectai · B · Open weights
Params
180 M
Context
512
30d
521 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | finbert | deberta-v3-base-prompt-injection-v2 |
|---|---|---|
| Parameters | 110 M | 180 M |
| Architecture | BertForSequenceClassification | DebertaV2ForSequenceClassification |
| Context length | 512 | 512 |
| Licence | cc-by-nc-sa-4.0 | apache-2.0 |
| Commercial use | Not allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 3,256,194 | 520,632 |
| Downloads all time | 127.0 M | 8.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-03-02 | 2024-04-20 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
5.5 M309 K
finbert
deberta-v3-base-prompt-injection-v2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
finbert · fp16
1.0 GB / 24 GB
deberta-v3-base-prompt-injection-v2 · fp16
1.3 GB / 24 GB