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
Usage
Make sure that you have installed Transformers, Torch, Pillow, and colpali-engine.
from colpali_engine.models import ColQwen2_5, ColQwen2_5_Processor
model_name = "ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-3B-v1"
model = ColQwen2_5.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="cuda:0", # or "mps" if on Apple Silicon attn_implementation="flash_attention_2" if is_flash_attn_2_available() else None, ).eval()
processor = ColQwen2_5_Processor.from_pretrained(model_name)
scores = processor.score_multi_vector(query_embeddings, image_embeddings) print(scores)
Parameters
All models are fine-tuned by using the Evo-Retriever paradigm with a two-stage training schedule (one epoch per stage). Unless otherwise noted, parameter-efficient fine-tuning is achieved through low-rank adapters (LoRA) with a rank of 32 for both 3B and 7B models. Training is performed in bfloat16 precision with the paged_adamw_8bit optimizer on an 8-GPU H20 server, employing a data-parallel strategy, a learning rate of 2e-5, cosine decay, 2% warm-up steps, and a batch size of 32.