| ---
|
| license: mit
|
| language:
|
| - en
|
| tags:
|
| - dami
|
| - linear-attention
|
| - long-context
|
| - initialization
|
| - ruler
|
| - arxiv:2610.41994
|
| ---
|
|
|
| # DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
|
|
|
| <div align="center">
|
|
|
| [](https://huggingface.co/SpeedAI-Lab/DAMI/blob/main/LICENSE)
|
| [](https://arxiv.org/abs/2610.41994)
|
| [](https://github.com/SpeedAI-Lab/DAMI)
|
| [](https://huggingface.co/SpeedAI-Lab/DAMI)
|
|
|
| </div>
|
|
|
| Zhangchi Feng 路 Harry Jiang 路 Yangyifei Luo 路 Ray Zhang 路 Richong Zhang
|
|
|
| [Project page](https://speedai.com/research/dami) 路 [Code, evaluation data and scripts](https://cnb.cool/speed-ai/research/DAMI)
|
|
|
| DAMI allocates memory timescales across heads and input responses across layers to improve long-context retrieval. This repository contains the 15 paper checkpoints: five architectures (GDN, KDA, GDN2, Mamba-2, RWKV-7) with three initialization conditions (Random, PoST, DAMI). Each model has approximately 100M parameters and was trained for approximately 5B tokens with a 4096-token training context.
|
|
|
| ## Checkpoints
|
|
|
| All checkpoints are stored under `checkpoints/`, using the directory names below. Each directory contains the full model weights (`model.safetensors`), `config.json`, `generation_config.json`, `tokenizer.json`, and `tokenizer_config.json`.
|
|
|
| | Architecture | Random | PoST | DAMI |
|
| | --- | --- | --- | --- |
|
| | GDN | `main_gdn_random` | `main_gdn_PoST` | `main_gdn_DAMI` |
|
| | KDA | `main_kda_random` | `main_kda_PoST` | `main_kda_DAMI` |
|
| | GDN2 | `main_gdn2_random` | `main_gdn2_PoST` | `main_gdn2_DAMI` |
|
| | Mamba-2 | `main_mamba2_random` | `main_mamba2_PoST` | `main_mamba2_DAMI` |
|
| | RWKV-7 | `main_rwkv7_random` | `main_rwkv7_PoST` | `main_rwkv7_DAMI` |
|
|
|
| ## Download and evaluation
|
|
|
| Clone the code repository and install its dependencies as described in its README. From the code repository root, download the checkpoints:
|
|
|
| ```python
|
| from huggingface_hub import snapshot_download
|
|
|
| snapshot_download(
|
| repo_id="SpeedAI-Lab/DAMI",
|
| local_dir=".",
|
| allow_patterns=["checkpoints/**"],
|
| )
|
| ```
|
|
|
| To download only GDN + DAMI, use `allow_patterns=["checkpoints/main_gdn_DAMI/*"]`. Access to this repository requires authentication while it is private.
|
|
|
| Run all 15 checkpoints on the fixed RULER evaluation data in Linux/WSL with CUDA:
|
|
|
| ```bash
|
| python evaluate_ruler.py --preflight --all --models-root checkpoints
|
| python evaluate_ruler.py --all --models-root checkpoints \
|
| --output-dir outputs/ruler-retest --skip-done
|
| ```
|
|
|
| For a single checkpoint, replace `--all` with `--architecture gdn --initialization dami`. The evaluator includes the architecture-specific FLA and RWKV adaptations required by these checkpoints; use the provided loading path for evaluation.
|
|
|
| The code repository includes 5,500 fixed samples across 11 RULER task/length settings and 82,500 original predictions. Evaluation uses greedy decoding with up to 128 new tokens. Scores use case-insensitive answer containment; the average weights all 11 settings equally.
|
|
|
| ## RULER results
|
|
|
| Average accuracy (%), as reported in the paper:
|
|
|
| | Architecture | Random | PoST | DAMI |
|
| | --- | ---: | ---: | ---: |
|
| | GDN | 30.42 | 33.49 | 44.36 |
|
| | KDA | 26.38 | 33.67 | 43.09 |
|
| | GDN2 | 30.27 | 33.47 | 43.71 |
|
| | Mamba-2 | 9.95 | 13.73 | 24.42 |
|
| | RWKV-7 | 23.87 | 20.69 | 29.16 |
|
|
|
| ## Citation
|
|
|
| ```bibtex
|
| @article{feng2026dami,
|
| title={DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention},
|
| author={Feng, Zhangchi and Jiang, Harry and Luo, Yangyifei and Zhang, Ray and Zhang, Richong},
|
| journal={arXiv preprint arXiv:2610.41994},
|
| year={2026}
|
| }
|
| ```
|
|
|
| ## Acknowledgement
|
|
|
| We thank the authors and developers of [FLA](https://github.com/fla-org/flash-linear-attention), [RWKV](https://github.com/BlinkDL/RWKV-LM), [GatedDeltaNet](https://github.com/NVlabs/GatedDeltaNet), [GatedDeltaNet-2](https://github.com/NVlabs/GatedDeltaNet-2), [Kimi-Linear](https://github.com/MoonshotAI/Kimi-Linear), and [Mamba](https://github.com/state-spaces/mamba) for their contributions to the architectures and implementations used in this work. We also thank [Transformers](https://github.com/huggingface/transformers) and [FLAME](https://github.com/fla-org/flame) for their training infrastructure.
|
|
|
| Our retrieval evaluation uses [RULER](https://github.com/NVIDIA/RULER). Benchmark attribution and data notices are provided in [data/ruler/NOTICE.md](https://github.com/SpeedAI-Lab/DAMI/blob/main/data/ruler/NOTICE.md). We thank the authors and developers for making their work available. Please cite the corresponding papers when using these resources.
|
|
|
| ## License
|
|
|
| These checkpoints are released under the MIT License. See the LICENSE file. Benchmark attribution and data notices are provided in the code repository.
|
|
|
