Downloads · 30 days
21
3% of all-time downloads
Llama-Prompt-Guard-86M-ONNX
Derbdale/Llama-Prompt-Guard-86M-ONNX
Llama-Prompt-Guard-86M-ONNX is a text classification model from Derbdale. Use it when you need a label for a piece of text. It is set up for onnx. The card lists the license as llama3.1.
All-time downloads
776
Public
Repo size
1.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.onnx1.1 GB · 99%
At a glance
- Task
- Text Classification
- Library
- onnx
- License
- llama3.1
- Model type
- deberta-v2
- Access
- Public
- Created
- Sep 25, 2025
- Updated
- Sep 25, 2025
- SHA
- bf6e7a40
Try a prompt
Base models
Model card
From the Hugging Face model README
Prompt-Guard-86M — ONNX (INT8)
Built with Llama.
This repo provides a quantized ONNX Runtime export of meta-llama/Prompt-Guard-86M.
What’s inside
model.onnx: INT8 quantized graph (ONNX Runtime dynamic quantization)tokenizer.json/tokenizer_config.jsonconfig.jsonLICENSE(Llama 3.1 Community License) andNOTICE
How it was made
- Export: 🤗 Optimum ONNX exporter
- Quantization: ONNX Runtime (dynamic, per-channel where supported)
- Command:
optimum-cli export onnx ...thenonnxruntime.quantization ... - Environment: onnxruntime==<ver>, optimum==<ver> (See Optimum/ONNX docs for details.)
Usage (Python)
import onnxruntime as ort
from transformers import AutoTokenizer
tok = AutoTokenizer.from_pretrained("<you>/Prompt-Guard-86M-onnx-int8")
session = ort.InferenceSession("model.onnx", providers=["CPUExecutionProvider"])
text = "your input"
enc = tok(text, return_tensors="np", padding=True, truncation=True)
outputs = session.run(None, {k: v for k, v in enc.items()})
- Task
- Text Classification
- Library
- onnx
- Type
- deberta-v2
- License
- llama3.1
- Created
- Sep 25, 2025
- Updated
- Sep 25, 2025