Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+language:
+- en
+tags:
+- molecules
+- chemistry
+- graph-encoder
+- qformer
+- molecular-understanding
+pipeline_tag: feature-extraction
+---
+
+# DQFormer Encoder (Stage 1)
+
+The pretrained **DQ-Former encoder** from EDT-Former, as described in the ICLR 2026 paper:
+
+> **Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding**
+> Zihao Jing, Qiuhao Zeng, Ruiyi Fang, Yan Sun, Boyu Wang, Pingzhao Hu
+> *ICLR 2026* · [Paper](https://www.arxiv.org/abs/2602.02742) · [Code](https://github.com/selmiss/DQ-Former)
+
+## Model Description
+
+The DQ-Former encoder is a Dual Q-Former that bridges molecular graphs and language. It uses:
+- **Entropy-guided dynamic token selection** to focus on informative molecular patches
+- **BRICS fragment IDs** for substructural awareness
+- **Cross-attention over graph node features** to generate a variable-length token sequence aligned with text
+
+This Stage 1 checkpoint (~699 MB) is trained on the PubChem pretraining corpus and is used to initialize Stage 2 (full model) training.
+
+**Architecture config:**
+- `num_query_tokens`: 32
+- `embed_dim`: 512
+- `cross_attention_freq`: 1
+- `num_layers`: 8 (blending module)
+- `num_heads`: 8
+
+## Usage
+
+Use this checkpoint as the Stage 1 initialization for Stage 2 fine-tuning:
+
+```yaml
+# configs/stage2_dqw2d/model_config.yaml
+stage1_path: path/to/DQFormer-encoder/model.safetensors
+```
+
+Or load directly:
+
+```python
+# First clone the repo and install dependencies (see github.com/selmiss/DQ-Former)
+from models.edt_former import EDTFormerEncoder
+
+encoder = EDTFormerEncoder.from_pretrained("zihaojing/DQFormer-encoder")
+```
+
+To reproduce Stage 1 training from scratch:
+
+```bash
+# Set up environment first (see repo README)
+bash scripts/training/pretraining.sh
+```
+
+## Related Resources
+
+| Resource | Link |
+|----------|------|
+| Pretrain Data | [zihaojing/DQFormer-pretrain-data](https://huggingface.co/datasets/zihaojing/DQFormer-pretrain-data) |
+| SFT Data | [zihaojing/DQFormer-sft-data](https://huggingface.co/datasets/zihaojing/DQFormer-sft-data) |
+| Full Model (Stage 2) | [zihaojing/DQFormer-model](https://huggingface.co/zihaojing/DQFormer-model) |
+| Code | [selmiss/DQ-Former](https://github.com/selmiss/DQ-Former) |
+
+## Citation
+
+```bibtex
+@inproceedings{jing2026edtformer,
+  title={Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding},
+  author={Jing, Zihao and Zeng, Qiuhao and Fang, Ruiyi and Sun, Yan and Wang, Boyu and Hu, Pingzhao},
+  booktitle={International Conference on Learning Representations (ICLR)},
+  year={2026}
+}
+```