Downloads · 30 days
20
15% of all-time downloads
athrael-soju/DualHead-GritLM-Qwen3.5-4B
DualHead-GritLM-Qwen3.5-4B is a visual document retrieval model from athrael-soju. Use it for the visual document retrieval task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
GritLM-style joint training ablation for the Hydra paper. Trained with alternating retrieval (80%) and generation (20%) batches.
Downloads · 30 days
20
15% of all-time downloads
All-time downloads
132
Public
Repo size
1.4 GB
Likes
1
Public
Click a slice to open those files.
.pt1.3 GB · 89%
From the Hugging Face model README
GritLM-style joint training ablation for the Hydra paper. Trained with alternating retrieval (80%) and generation (20%) batches.
Joint training adds complexity with zero benefit. LoRA-on generation fails catastrophically (single token "The" with p=0.91, image-blind). Both functional modes (LoRA-on retrieval, LoRA-off generation) are equivalent to Hydra's retrieval-only training.
| Mode | Result |
|---|---|
| LoRA on, bidirectional (retrieval) | 0.8893 nDCG@5 |
| LoRA off, causal (generation) | 0.561 ANLS, 76.5% match |
| LoRA on, causal (joint-training goal) | image-blind |
adapter_config.json + adapter_model.safetensors -- LoRA adapterlm_head.pt -- Base model lm_headresults/ -- Raw evaluation JSONs@article{georgiou2026hydra,
title={Hydra: Unifying Document Retrieval and Generation in a Single Vision-Language Model},
author={Georgiou, Athos},
year={2026}
}