You can deploy this model and start earning money today!

ApsaraStackMaaS/
EvoQwen2.5-VL-Retriever-3B-v1

Name: EvoQwen2.5-VL-Retriever-3B-v1
Availability: InStock

safetensors

qwen2_5_vl

visual-document-retrieval

vidore/colpali_train_set

openbmb/VisRAG-Ret-Train-Synthetic-data

openbmb/VisRAG-Ret-Train-In-domain-data

2603.16455

vidore/colqwen2.5-base

finetune

apache-2.0

Views

No views yet

Model Card for Model ID

EvoQwen2.5-VL-Retriever-3B-v1 is a high-performance multimodal retrieval model built upon the Qwen2.5-VL-3B-Instruct backbone and employing multi-vector late-interaction. The model is fine-tuned by using an innovative evolutionary training framework (Evo-Retriever), enabling accurate retrieval of complex visual documents.

Version Specificity

• Base Model: ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-3B-v1

• Parameter Size: 3 billion (3B)

• Features: As a smaller-weight model in this series, this model outperforms other models of similar size on evaluation benchmarks, delivering higher retrieval accuracy in resource-constrained scenarios.

Performance

Model	ViDoRe V2 (nDCG@5)	MMEB VisDoc (ndcg_linear@5)
ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-3B-v1	63.00	75.96
ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-7B-v1	65.24	77.10

Usage

Make sure that you have installed Transformers, Torch, Pillow, and colpali-engine.

javascript

  import torch
from PIL import Image
from transformers.utils.import_utils import is_flash_attn_2_available
[object Object]
[object Object]
[object Object]
[object Object]
[object Object]
images = [
    Image.new("RGB", (128, 128), color="white"),
    Image.new("RGB", (64, 32), color="black"),
]
queries = [
    "Is attention really all you need?",
    "What is the amount of bananas farmed in Salvador?",
]
[object Object]
batch_images = processor.process_images(images).to(model.device)
batch_queries = processor.process_queries(queries).to(model.device)
[object Object]
with torch.no_grad():
    image_embeddings = model(**batch_images)
    query_embeddings = model(**batch_queries)
[object Object]

javascript

[object Object]
[object Object]
[object Object]

    [object Object]