README.md

---
language: pt
license: mit
tags:
  - document-understanding
  - document-retrieval
  - metric-learning
  - siamese-network
  - internvl
  - cosdoc
datasets:
  - LA-CDIP
metrics:
  - eer
model-index:
  - name: CosDoc (Attention nq=1 (baseline))
    results:
      - task:
          type: document-retrieval
        dataset:
          name: LA-CDIP
          type: la-cdip
        metrics:
          - type: eer
            value: 0.0144
---

# CosDoc — Attention nq=1 (baseline)

**CosDoc** is a visual document embedding model trained with supervised metric learning
and hard-example selection via a Reinforcement Learning professor network.

Pooler variant: **Attention nq=1 (baseline)** — Standard attention pooler, num_queries=1.

## Architecture

| Component | Value |
|---|---|
| Backbone | InternVL3-2B (`OpenGVLab/InternVL3-2B`) |
| Cut layer | 27 |
| Pooler | attention (num_queries=1) |
| Embedding dim | 1536 |
| Loss | Sub-Center CosFace (m=0.35, s=32, k=3) |
| Embedding prompt | `<image> Analyze this document` |

## Performance (LA-CDIP, full validation pairs)

| Dataset | EER |
|---|---|
| LA-CDIP (5-fold CV) | **1.44%** |

Source run: `Sprint3b_S0_subcenter_cosface_seed42_s32k3_fase1_E10`

## Usage

```python
import torch
from huggingface_hub import hf_hub_download
from cavl_doc.models.backbone_loader import load_model
from cavl_doc.models.modeling_cavl import build_cavl_model

device = "cuda" if torch.cuda.is_available() else "cpu"

# Download fine-tuned weights
ckpt_path = hf_hub_download(repo_id="Jpcosta90/cosdoc", filename="best_model.pt")
ckpt = torch.load(ckpt_path, map_location=device, weights_only=False)
cfg  = ckpt["config"]

backbone, _, tokenizer, _, _ = load_model("InternVL3-2B")
model = build_cavl_model(
    backbone=backbone,
    cut_layer=cfg["cut_layer"],
    pooler_type=cfg["pooler_type"],
    num_queries=cfg.get("num_queries", 1),
)
model.pool.load_state_dict(ckpt["siam_pool"])
model.head.load_state_dict(ckpt["siam_head"])
model.eval().to(device)
```

## Citation

```bibtex
@misc{cosdoc2026,
  title  = {CosDoc: Cosine-Margin Document Embeddings with RL-guided Hard Mining},
  author = {Costa, João Paulo},
  year   = {2026},
  url    = {https://huggingface.co/Jpcosta90/cosdoc}
}
```