d-matrix/clip-vit-base-patch32

This is a d-Matrix functional reference of the clip-vit-base-patch32 model. The reference provides the following functional configurations:

Configuration	Explanation
BASELINE	a reference functionally equivalent to the original model
BASIC	all linear algebraic operands quantized to MXINT8-64, and all other operations transformed to approximated kernel simulations

Usage

Install d-Matrix Dmx_Compressor first.

pip install dmx_compressor

The following is an example model and its evaluation.

from PIL import Image
import requests

from transformers import CLIPProcessor, CLIPModel
from dmx.compressor.modeling import DmxModel

model = CLIPModel.from_pretrained("d-matrix/clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("d-matrix/clip-vit-base-patch32")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(
    text=["a photo of a cat", "a photo of a dog"],
    images=image,
    return_tensors="pt",
    padding=True,
)

model = DmxModel.from_torch(model)
outputs = model(**inputs)