meta-llama / text-classification updated 8 months ago

Prompt-Guard-86M

Params
280 M
Context
Downloads 30d
4.5 M
Likes
383
Commercial use: conditional · llama3.1 Gated — accept licence SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
4.5 M4.4 M
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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f32 1.1 GB 1.8 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
DebertaV2ForSequenceClassification
Parameters
280 M
Tensor type
F32
Licence
llama3.1
First seen on the Hub
2024-07-21
Training datasets
undisclosed
Added to our catalog
2026-07-28