Ops-Colqwen3-4B

pillow
transformers>=4.57.0
qwen-vl-utils>=0.0.14
torch==2.8.0

import torch
from PIL import Image
from scripts.ops_colqwen3_embedder import OpsColQwen3Embedder

images = [Image.new("RGB", (32, 32), color="white"), Image.new("RGB", (16, 16), color="black")]
queries = ["Is attention really all you need?", "What is the amount of bananas farmed in Salvador?"]

embedder = OpsColQwen3Embedder(
    model_name="OpenSearch-AI/Ops-Colqwen3-4B",
    dims=2560,
    dtype=torch.float16,
    attn_implementation="flash_attention_2",
)

query_embeddings = embedder.encode_queries(queries)
image_embeddings = embedder.encode_images(images)
print(query_embeddings[0].shape, image_embeddings[0].shape) # (23, 2560) (18, 2560)

scores = embedder.compute_scores(query_embeddings, image_embeddings)

print(f"Scores:\n{scores}")