clip-vit-b32-int8-ov
OpenVINO IR export of openai/clip-vit-base-patch32, quantized to INT8 — 153 MB.
| Quantization | weight compression (optimum) |
| Lesson | 05 CLIP zero-shot |
| Built by | convert/convert_all.py of the ARCademy OpenVINO courseware |
Use CLIPProcessor.from_pretrained(model_dir) for preprocessing.
from huggingface_hub import snapshot_download
model_dir = snapshot_download("circulus/clip-vit-b32-int8-ov")
- Downloads last month
- 11
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for circulus/clip-vit-b32-int8-ov
Base model
openai/clip-vit-base-patch32