--- title: EVIE-8B canonical_url: "https://www.modelscope.ai/models/Tencent-Hunyuan/EVIE-8B" md_url: "https://www.modelscope.ai/models/Tencent-Hunyuan/EVIE-8B.md" repository: Tencent-Hunyuan/EVIE-8B last_updated: 2026-09-07 license: apache-2.0 model_type: - qwen3_5 architectures: - ColQwen3_5 base_model: - Qwen/Qwen3.5 base_model_relation: finetune parameters: 8.4B tensor_type: - BF16 library_name: - pytorch - safetensors frameworks: - pytorch downloads: 7 stars: 0 tags: - colpali-engine - qwen3_5 - vision-language - colbert - late-interaction - multi-vector - vidore - document-retrieval - multimodal --- # EVIE-8B > EVIE-8B - An open-source model by Tencent-Hunyuan on ModelScope. 🏆 EVIE-8B: The Most Accurate Visual Document Retriever Evidence-Vector-Informed Embedding (EVIE-8B Flagship Teacher) Tencent-Hunyuan/EVIE-8B is a 8.4B-parameter machine learning model on ModelScope. licensed under apache-2.0. derived from Qwen/Qwen3.5. - **Repository**: Tencent-Hunyuan/EVIE-8B - **License**: apache-2.0 - **Parameters**: 8.4B - **Base model**: Qwen/Qwen3.5 - **Tags**: colpali-engine, qwen3_5, vision-language, colbert, late-interaction, multi-vector, vidore, document-retrieval, multimodal - **Downloads**: 7 - **Stars**: 0 - **Last updated**: 2026-09-07 Source: https://www.modelscope.ai/models/Tencent-Hunyuan/EVIE-8B ---

# 🏆 EVIE-8B: The Most Accurate Visual Document Retriever ### Evidence-Vector-Informed Embedding (EVIE-8B Flagship Teacher)

4096-Dimensional Token Representation • Bidirectional Full-Attention • Teacher for EVIE-4.5B Prefix-MRL

🤗 EVIE-8B (Flagship Teacher) • 🤗 EVIE-4.5B (Prefix-MRL & HAC) • 🐙 GitHub: Tencent/EVIE

--- > 📢 **Release Announcement**: All model weights, inference pipelines, and evaluation suites have been fully open-sourced. Full technical details, architectural ablations, and the formal research paper will be updated in an upcoming release. Training code and distillation recipes are available in the [Tencent/EVIE](https://github.com/Tencent/EVIE) repository. --- ## 🌟 Highlights - **Highest Retrieval Accuracy**: **66.75** nDCG@10 on ViDoRe V3, delivering industry-leading visual document retrieval accuracy. - **High-Capacity 4096D Representations**: Full per-token multi-vector embeddings preserving fine-grained layout, typography, charts, and table structures. - **Teacher Foundation**: Provides capacity-aware relation and margin distillation targets for the lightweight [EVIE-4.5B](https://huggingface.co/tencent/EVIE-4.5B) Prefix-MRL model. - **Multi-Benchmark 138-Task Coverage**: Thoroughly validated across 138 tasks (ViDoRe V1, V2, V3, and JinaVDR) across 4 standard metric families (nDCG, Recall, MAP, MRR @1/5/10). --- ## 🧠 Architecture & Technical Highlights ```text Query Text ────────► ColQwen3.5 (BiDir Attention) ────► 4096D Per-Token Embeddings │ MaxSim Matching │ Doc Image ────────► ColQwen3.5 (Vision Encoder) ────► Full Multi-Vector Patch Embeddings ``` - **Late-Interaction Token Embeddings**: Rather than compressing visual documents into an information-lossy single vector, EVIE-8B preserves spatial nuances, typography, and tabular relations with per-token late-interaction representations. Relevance is scored using MaxSim: $$ S(Q, D) = \sum_{i=1}^{|Q|} \max_{j=1}^{|D|} (q_i \cdot d_j) $$ - **Full Bidirectional Attention**: Employs bidirectional self-attention across multimodal vision-text sequences to facilitate cross-modal interaction between visual patch tokens and prompt contexts. - **Foundational Distillation Teacher**: Serves as the high-capacity anchor model for training the compact [EVIE-4.5B](https://huggingface.co/tencent/EVIE-4.5B) student via topological relation transfer and hard-negative margin supervision (ARD). --- ## 📊 Comprehensive ViDoRe Leaderboard Comparison Performance comparison across modern multi-vector late-interaction visual document retrievers on ViDoRe: | Rank | Model | Base Model | Param | Embed Dim | ViDoRe V1 (nDCG@5) | ViDoRe V2 (nDCG@5) | ViDoRe V3 (nDCG@10) | | :---: | :--- | :---: | :---: | :---: | :---: | :---: | :---: | | 🥇 | **[EVIE-8B](https://huggingface.co/tencent/EVIE-8B)** | Qwen3.5-9B | 8.41B | 4096D | **92.18** | **74.23** | **66.75** | | 🥈 | **[EVIE-4.5B](https://huggingface.co/tencent/EVIE-4.5B)** | Qwen3.5-4B | 4.61B | 64–2048D Prefix-MRL | **92.07** | **73.38** | **66.02** | | 🥉 | **EVIE-Preview-4.5B** | Qwen3.5-4B | 4.54B | 128D | 91.73 | 70.87 | 65.36 | | 4 | webAI-ColVec1.1-8b | Qwen2.5-VL | 8.40B | 640D | 91.30 | 65.82 | 65.32 | | 5 | VultronRetrieverPrime-8B | Qwen3.5-9B | 8.40B | 320D | 92.08 | 68.18 | 64.26 | | 6 | webAI-ColVec1.1-4b | Qwen2.5-VL | 4.54B | 640D | 90.49 | 63.60 | 63.90 | | 7 | VultronRetrieverCore-4.5B | Qwen3.5-4B | 4.50B | 320D | 92.21 | 66.12 | 63.57 | | 8 | nemotron-colembed-vl-8b-v2 | Nemotron-8B | 8.80B | 4096D | 92.65 | 65.16 | 63.54 | | 9 | tomoro-colqwen3-embed-8b | Qwen2.5-VL | 8.00B | 320D | 90.76 | 65.40 | 61.60 | | 10 | nemotron-colembed-vl-4b-v2 | Nemotron-4B | 4.80B | 2560D | 91.62 | 64.49 | 61.42 | | 11 | athrael-soju/colqwen3.5-4.5B-v3 | Qwen3.5-4B | 4.60B | 128D | 91.54 | 64.25 | 61.46 | | 12 | tomoro-colqwen3-embed-4b | Qwen2.5-VL | 4.00B | 320D | 90.57 | 64.69 | 60.16 | | 13 | VultronRetrieverFlash-0.8B | Qwen3.5-0.8B | 0.85B | 320D | 88.15 | 60.36 | 56.16 | --- ### 🔍 ViDoRe V3 Per-Domain Breakdown (nDCG@10) | Model | Avg | CompSci | Energy | Finance EN | Finance FR | HR | Industrial | Pharma | Physics | | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | **EVIE-8B** | **66.75** | **81.86** | **72.51** | **71.23** | **56.40** | **69.29** | **59.77** | **70.81** | **52.11** | | [EVIE-4.5B](https://huggingface.co/tencent/EVIE-4.5B) | 66.02 | 81.72 | 72.32 | 70.00 | 54.90 | 67.82 | 59.40 | 70.27 | 51.69 | | webAI-ColVec1.1-8b | 65.32 | 80.08 | 70.12 | 71.90 | 54.87 | 68.55 | 57.65 | 67.88 | 51.50 | | nemotron-colembed-vl-8b-v2 | 63.54 | 79.30 | 69.82 | 67.29 | 51.54 | 66.32 | 56.03 | 67.19 | 50.84 | | VultronRetrieverPrime-8B | 64.26 | 79.80 | 70.30 | 69.00 | 54.50 | 66.80 | 57.40 | 68.20 | 51.70 | | VultronRetrieverCore-4.5B | 63.57 | 79.80 | 69.20 | 68.90 | 52.00 | 66.10 | 56.10 | 67.50 | 50.20 | | tomoro-colqwen3-embed-8b | 61.60 | 75.35 | 68.41 | 65.08 | 49.10 | 63.98 | 54.41 | 66.36 | 50.13 | --- ## 📋 Complete 138-Task Evaluation Matrix Protocol `paired-all-pages-dedup+process_queries+ndcg2r-20260827` ($\text{MVT} = 1024$, bidirectional attention): - **ViDoRe V1**: 10 tasks, 3,943 queries, 6,729 docs - **ViDoRe V2**: 4 tasks, 1,152 queries, 4,544 docs - **ViDoRe V3**: 48 tasks, 14,514 queries, 115,512 docs - **JinaVDR**: 76 tasks, 43,375 queries, 55,398 docs | Metric | ViDoRe V1 | ViDoRe V2 | ViDoRe V3 | JinaVDR | 4-Board Macro Avg | | :--- | :---: | :---: | :---: | :---: | :---: | | **nDCG@1** | 88.51 | 75.58 | 62.14 | 75.50 | 75.43 | | **nDCG@5** | 92.18 | 74.23 | 64.16 | 82.45 | 78.26 | | **nDCG@10** | **92.64** | **75.35** | **66.75** | **83.30** | **79.51** | | **Recall@1** | 88.51 | 37.87 | 30.79 | 75.50 | 58.17 | | **Recall@5** | 95.07 | 66.65 | 58.69 | 88.07 | 77.12 | | **Recall@10** | 96.43 | 76.34 | 70.10 | 90.65 | 83.38 | | **MAP@1** | 88.51 | 75.99 | 65.94 | 75.50 | 76.49 | | **MAP@5** | 91.21 | 67.30 | 55.82 | 80.56 | 73.72 | | **MAP@10** | 91.40 | 66.81 | 56.32 | 80.92 | 73.86 | | **MRR@1** | 88.51 | 75.99 | 65.94 | 75.50 | 76.49 | | **MRR@5** | 91.21 | 82.85 | 75.39 | 80.56 | 82.50 | | **MRR@10** | 91.40 | 83.23 | 76.09 | 80.92 | 82.91 | --- ## ⚡ Quick Start ### Installation ```bash git clone https://github.com/Tencent/EVIE.git cd EVIE pip install -r requirements.txt export PYTHONPATH="$(pwd)/colpali${PYTHONPATH:+:$PYTHONPATH}" ``` ### Python Inference ```python import torch from PIL import Image from colpali_engine.models import ColQwen3_5, ColQwen3_5Processor model_id = "tencent/EVIE-8B" # 1. Load model with FlashAttention and bidirectional attention model = ColQwen3_5.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="cuda", attn_implementation="flash_attention_2", ).eval() model.enable_bidirectional_attention() # 2. Process query and document image processor = ColQwen3_5Processor.from_pretrained(model_id) images = [Image.open("examples/demo/pages/q3_revenue.png").convert("RGB")] queries = ["What is the total quarterly revenue?"] image_batch = processor.process_images(images).to(model.device) query_batch = processor.process_queries(queries).to(model.device) # 3. Generate 4096D multi-vectors and late-interaction score with torch.inference_mode(): image_embeddings = model(**image_batch) model.rope_deltas = None # Reset RoPE deltas before text query forward query_embeddings = model(**query_batch) scores = processor.score(query_embeddings, image_embeddings) print("Late-interaction MaxSim Relevance Score:", scores) ``` --- ## 📂 Repository Layout ```text Evie-8B/ ├── model.safetensors # EVIE-8B weights (safetensors) ├── config.json # Model configuration (4096D) ├── infer.py # Standalone inference & scoring CLI ├── colpali/ # ColQwen3.5 inference engine ├── code/shared/ # 138-task eval harness ├── examples/demo/ # 8-page retrieval demo (run.sh) └── env.sh.example # Environment variables template ``` --- ## 🔬 Released Checkpoint EVIE-8B was trained on 775,635 document-query pairs across multilingual domains. Hard negatives were mined and classified into answerable (promoted to positives), ambiguous (masked), and strict negatives (negative cross-entropy loss). The released **a40** checkpoint represents a weight-space mix ($\alpha = 0.40$) of two independently trained arms, achieving the peak **66.75** nDCG@10 on ViDoRe V3. Full training reproduction scripts are provided in the companion repository [Tencent/EVIE](https://github.com/Tencent/EVIE). --- ## 📚 Citation ```bibtex @misc{tencent2026evie8b, title = {EVIE-8B: High-Capacity Visual Document Retrieval with 4096-Dimensional Embeddings}, author = {{Tencent}}, year = {2026}, howpublished = {\url{https://github.com/Tencent/EVIE}} } ``` --- ## 📄 License This model and codebase are released under the [Apache-2.0 License](LICENSE).