Model Card for Model ID
EvoQwen2.5-VL-Retriever-7B-v1 is a high-performance multimodal retrieval model built upon the Qwen2.5-VL-7B-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-7B-v1
• Parameter Size: 7 billion (7B)
• Features: The 7B version delivers the highest retrieval accuracy across all evaluation benchmarks, making it ideal for applications with stringent performance requirements.
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.