Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+banner.png filter=lfs diff=lfs merge=lfs -text

0_Transformer/config.json

@@ -0,0 +1,23 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30522
+}

0_Transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13a257b8515a108d1bd687e409d8531577a73f7cad72c8342f48b90992922b6
+size 265462608

0_Transformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

0_Transformer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

0_Transformer/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

2_Dense/config.json

@@ -0,0 +1,6 @@
+{
+  "in_features": 768,
+  "out_features": 768,
+  "bias": true,
+  "activation_function": "torch.nn.modules.activation.GELU"
+}

2_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bce0986fa92c8845038b022e5928204a5dab7b730304154d38989a9563c716
+size 2364309

3_Dense/config.json

@@ -0,0 +1,6 @@
+{
+  "in_features": 768,
+  "out_features": 2048,
+  "bias": true,
+  "activation_function": "torch.nn.modules.linear.Identity"
+}

3_Dense/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b4e4ddf2abd0b96bb573f55fb57559d28a056dc7a3658e7ddd1a6eca000dc4
+size 6301589

README.md

@@ -0,0 +1,256 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- visual-document-retrieval
+- cross-modal-distillation
+- knowledge-distillation
+- document-retrieval
+- multilingual
+- nanovdr
+base_model: distilbert/distilbert-base-uncased
+language:
+- en
+- de
+- fr
+- es
+- it
+- pt
+license: apache-2.0
+datasets:
+- openbmb/VisRAG-Ret-Train-Synthetic-data
+- openbmb/VisRAG-Ret-Train-In-domain-data
+- vidore/colpali_train_set
+- llamaindex/vdr-multilingual-train
+model-index:
+- name: NanoVDR-S-Multi
+  results:
+  - task:
+      type: retrieval
+    dataset:
+      name: ViDoRe v1
+      type: vidore/vidore-benchmark-667173f98e70a1c0fa4d
+    metrics:
+    - name: NDCG@5
+      type: ndcg_at_5
+      value: 82.2
+  - task:
+      type: retrieval
+    dataset:
+      name: ViDoRe v2
+      type: vidore/vidore-benchmark-v2
+    metrics:
+    - name: NDCG@5
+      type: ndcg_at_5
+      value: 61.9
+---
+
+<p align="center">
+  <img width="560" src="banner.png" alt="NanoVDR"/>
+</p>
+
+<p align="center">
+  <a href="https://arxiv.org/abs/2502.XXXXX">Paper</a> |
+  <a href="https://github.com/nanovdr/nanovdr">GitHub</a> |
+  <a href="https://huggingface.co/collections/nanovdr/nanovdr">All Models</a>
+</p>
+
+# NanoVDR-S-Multi
+
+**The recommended NanoVDR model for production use.**
+
+NanoVDR-S-Multi is a **69M-parameter multilingual text-only** query encoder for visual document retrieval. It encodes text queries into the same embedding space as a frozen 2B VLM teacher ([Qwen3-VL-Embedding-2B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B)), so you can retrieve document page images using **only a DistilBERT forward pass** — no vision model at query time.
+
+### Highlights
+
+- **95.1% teacher retention** — a 69M text-only model recovers 95% of a 2B VLM teacher across 22 ViDoRe datasets
+- **Outperforms DSE-Qwen2 (2B)** on multilingual v2 (+6.2) and v3 (+4.1) with **32x fewer parameters**
+- **Outperforms ColPali (~3B)** on all three benchmarks with **single-vector cosine** retrieval (no MaxSim)
+- **51 ms CPU query latency** — 50x faster than DSE-Qwen2, 143x faster than ColPali
+- **6 languages**: English, German, French, Spanish, Italian, Portuguese — all >92% teacher retention
+
+---
+
+## Results
+
+| Model | Type | Params | ViDoRe v1 | ViDoRe v2 | ViDoRe v3 | Avg Retention |
+|-------|------|--------|-----------|-----------|-----------|---------------|
+| Tomoro-8B | VLM | 8.0B | 90.6 | 65.0 | 59.0 | — |
+| Qwen3-VL-Emb (Teacher) | VLM | 2.0B | 84.3 | 65.3 | 50.0 | — |
+| DSE-Qwen2 | VLM | 2.2B | 85.1 | 55.7 | 42.4 | — |
+| ColPali | VLM | ~3B | 84.2 | 54.7 | 42.0 | — |
+| **NanoVDR-S-Multi** | **Text-only** | **69M** | **82.2** | **61.9** | **46.5** | **95.1%** |
+
+<sub>NDCG@5 (×100). v1 = 10 English datasets, v2 = 4 multilingual datasets, v3 = 8 multilingual datasets.</sub>
+
+### Per-Language Retention (v2 + v3, 19,537 queries)
+
+| Language | #Queries | Teacher | NanoVDR-S-Multi | Retention |
+|----------|----------|---------|-----------------|-----------|
+| English | 6,237 | 64.0 | 60.3 | 94.3% |
+| French | 2,694 | 51.0 | 47.8 | 93.6% |
+| Portuguese | 2,419 | 48.7 | 46.1 | 94.6% |
+| Spanish | 2,694 | 51.4 | 47.8 | 93.1% |
+| Italian | 2,419 | 49.0 | 45.7 | 93.3% |
+| German | 2,694 | 49.3 | 45.4 | 92.0% |
+
+All 6 languages achieve **>92%** of the 2B teacher's performance.
+
+---
+
+## Quick Start
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("nanovdr/NanoVDR-S-Multi")
+
+queries = [
+    "What was the revenue growth in Q3 2024?",           # English
+    "Quel est le chiffre d'affaires du trimestre?",       # French
+    "Wie hoch war das Umsatzwachstum im dritten Quartal?", # German
+    "¿Cuál fue el crecimiento de ingresos en el Q3?",     # Spanish
+    "Qual foi o crescimento da receita no terceiro trimestre?", # Portuguese
+    "Qual è stata la crescita dei ricavi nel terzo trimestre?", # Italian
+]
+query_embeddings = model.encode(queries)
+print(query_embeddings.shape)  # (6, 2048)
+
+# Cosine similarity against pre-indexed document embeddings
+# scores = query_embeddings @ doc_embeddings.T
+```
+
+### Prerequisites: Document Indexing with Teacher Model
+
+NanoVDR is a **query encoder only**. Documents must be indexed offline using the teacher VLM ([Qwen3-VL-Embedding-2B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B)), which encodes page images into 2048-d embeddings. This is a one-time cost.
+
+```python
+# pip install transformers qwen-vl-utils torch
+from scripts.qwen3_vl_embedding import Qwen3VLEmbedder
+
+teacher = Qwen3VLEmbedder(model_name_or_path="Qwen/Qwen3-VL-Embedding-2B")
+
+# Encode document page images
+documents = [
+    {"image": "page_001.png"},
+    {"image": "page_002.png"},
+    # ... all document pages in your corpus
+]
+doc_embeddings = teacher.process(documents)  # (N, 2048), L2-normalized
+```
+
+> **Note:** The `Qwen3VLEmbedder` class and full usage guide (including vLLM/SGLang acceleration) are available at the [Qwen3-VL-Embedding-2B model page](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B). Document indexing requires a GPU; once indexed, retrieval uses only CPU.
+
+### Full Retrieval Pipeline
+
+```python
+import numpy as np
+from sentence_transformers import SentenceTransformer
+
+# doc_embeddings: (N, 2048) numpy array from teacher indexing above
+
+# Step 1: Encode text queries with NanoVDR (CPU, ~51ms per query)
+student = SentenceTransformer("nanovdr/NanoVDR-S-Multi")
+query_emb = student.encode("Quel est le chiffre d'affaires?")  # shape: (2048,)
+
+# Step 2: Retrieve via cosine similarity
+scores = query_emb @ doc_embeddings.T
+top_k_indices = np.argsort(scores)[-5:][::-1]
+```
+
+---
+
+## How It Works
+
+NanoVDR uses **asymmetric cross-modal distillation** to decouple query and document encoding:
+
+| | Document Encoding (offline) | Query Encoding (online) |
+|-|----------------------------|------------------------|
+| **Model** | Qwen3-VL-Embedding-2B (frozen) | NanoVDR-S-Multi (69M) |
+| **Input** | Page images | Text queries (6 languages) |
+| **Output** | 2048-d embedding | 2048-d embedding |
+| **Hardware** | GPU (one-time indexing) | CPU (real-time serving) |
+
+The student is trained to **align query embeddings** with the teacher's query embeddings via pointwise cosine loss — no document embeddings or hard negatives are needed during training. At inference, student query embeddings are directly compatible with teacher document embeddings.
+
+---
+
+## Training
+
+| | Value |
+|--|-------|
+| Base model | `distilbert/distilbert-base-uncased` (66M) |
+| Projector | 2-layer MLP: 768 → 768 → 2048 (2.4M params) |
+| Total params | 69M |
+| Objective | Pointwise cosine alignment with teacher query embeddings |
+| Training data | 1.49M pairs — 711K original + 778K translated queries |
+| Languages | EN (original) + DE, FR, ES, IT, PT (translated via [Helsinki-NLP Opus-MT](https://huggingface.co/Helsinki-NLP)) |
+| Epochs | 10 |
+| Batch size | 1,024 (effective) |
+| Learning rate | 3e-4 (OneCycleLR, 3% warmup) |
+| Hardware | 1× H200 GPU |
+| Training time | ~10 GPU-hours |
+| Embedding caching | ~1 GPU-hour (teacher encodes all queries in text mode) |
+
+### Multilingual Augmentation Pipeline
+
+1. Extract 489K English queries from the 711K training set
+2. Translate each to 5 languages using Helsinki-NLP Opus-MT → 778K translated queries
+3. Re-encode translated queries with the frozen teacher in text mode (15 min on H200)
+4. Combine: 711K original + 778K translated = **1.49M training pairs**
+5. Train with halved epochs (10 vs 20) and slightly higher lr (3e-4 vs 2e-4) to match total steps
+
+---
+
+## Efficiency
+
+| | NanoVDR-S-Multi | DSE-Qwen2 | ColPali | Tomoro-8B |
+|--|-----------------|-----------|---------|-----------|
+| Parameters | **69M** | 2,209M | ~3B | 8,000M |
+| Query latency (CPU, B=1) | **51 ms** | 2,539 ms | 7,300 ms | GPU only |
+| Checkpoint size | **274 MB** | 8.8 GB | 11.9 GB | 35.1 GB |
+| Index type | Single-vector | Single-vector | Multi-vector | Multi-vector |
+| Scoring | Cosine | Cosine | MaxSim | MaxSim |
+| Index storage (500K pages) | **4.1 GB** | 3.1 GB | 128 GB | 128 GB |
+
+---
+
+## Model Variants
+
+NanoVDR-S-Multi is the **recommended model**. The other variants are provided for research and ablation purposes.
+
+| Model | Backbone | Params | v1 | v2 | v3 | Retention | Latency | Recommended |
+|-------|----------|--------|----|----|----|-----------|---------| ------------|
+| **[NanoVDR-S-Multi](https://huggingface.co/nanovdr/NanoVDR-S-Multi)** | **DistilBERT** | **69M** | **82.2** | **61.9** | **46.5** | **95.1%** | **51 ms** | **Yes** |
+| [NanoVDR-S](https://huggingface.co/nanovdr/NanoVDR-S) | DistilBERT | 69M | 82.2 | 60.5 | 43.5 | 92.4% | 51 ms | EN-only |
+| [NanoVDR-M](https://huggingface.co/nanovdr/NanoVDR-M) | BERT-base | 112M | 82.1 | 62.2 | 44.7 | 94.0% | 101 ms | Ablation |
+| [NanoVDR-L](https://huggingface.co/nanovdr/NanoVDR-L) | ModernBERT | 151M | 82.4 | 61.5 | 44.2 | 93.4% | 109 ms | Ablation |
+
+## Key Properties
+
+| Property | Value |
+|----------|-------|
+| Output dimension | 2048 (aligned with Qwen3-VL-Embedding-2B) |
+| Max sequence length | 512 tokens |
+| Supported languages | EN, DE, FR, ES, IT, PT |
+| Similarity function | Cosine similarity |
+| Pooling | Mean pooling |
+| Normalization | L2-normalized |
+
+## Citation
+
+```bibtex
+@article{nanovdr2026,
+  title={NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval},
+  author={Liu, Zhuchenyang and Zhang, Yao and Xiao, Yu},
+  journal={arXiv preprint arXiv:2502.XXXXX},
+  year={2026}
+}
+```
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,23 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.6",
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,5 @@
+{
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,32 @@
+[
+  {
+    "idx": 0,
+    "name": "0_Transformer",
+    "path": "0_Transformer",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1_Pooling",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2_Dense",
+    "path": "2_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3_Dense",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4_Normalize",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}