Add model card with project links and citation

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: apache-2.0
+tags:
+- memory-decoder
+- parametric-memory
+- long-term-memory
+- memorydecoder-at-scale
+- text-generation
+- olmo
+- law
+datasets:
+- Rubin-Wei/MemoryDecoder-at-Scale-domain-data
+---
+# MemoryDecoder-OLMo-1.7B-law
+
+This repository contains the **1.7B law Memory Decoder** released
+with [Memory Decoder at Scale](https://arxiv.org/abs/2607.27919). It is a pretrained parametric long-term
+memory that can be swapped into a compatible frozen language-model backbone.
+
+This OLMo-vocabulary memory was trained for two epochs on the law CPT corpus. The released configuration uses the OLMo vocabulary so that the memory can be combined with a vocabulary-compatible frozen OLMo backbone.
+
+This checkpoint is a memory component, not a standalone chat- or
+instruction-tuned model. The memory and backbone must use compatible token IDs
+and vocabularies.
+
+## Model details
+
+| Field | Value |
+|---|---|
+| Memory size | 1.7B class |
+| Architecture/tokenizer family | Qwen3-style 1.7B memory; OLMo tokenizer/vocabulary |
+| Domain | Law |
+| Evaluation benchmark | LawBench |
+| Intended backbone | Frozen OLMo-family model with the matching tokenizer/vocabulary |
+| Release contents | Inference weights, configuration, and tokenizer files |
+
+Optimizer states and training-resume artifacts are not part of this release.
+
+## Usage
+
+Install the matching environment from the [GitHub repository](https://github.com/LUMIA-Group/MemoryDecoder-at-Scale), then
+set `MODEL_PATH` to a compatible frozen backbone and `MEMDEC_PATH` to this
+repository:
+
+```bash
+MODEL_PATH=/path/to/compatible-base-model \
+MEMDEC_PATH=Rubin-Wei/MemoryDecoder-OLMo-1.7B-law \
+bash eval/opencompass/scripts/domain/evaluate_lawbench.sh
+```
+
+See the repository documentation and launcher for benchmark-specific options,
+including interpolation weights and batch settings.
+
+## Intended use and limitations
+
+This checkpoint is intended for research and evaluation in the law
+domain. Its outputs depend on the backbone, prompt, and interpolation settings.
+Domain specialization does not guarantee factual correctness or safety, and the
+model may inherit biases and errors from its training sources.
+
+## Links
+
+- [Project page](https://rubin-wei.github.io/memory-decoder-at-scale/)
+- [GitHub repository](https://github.com/LUMIA-Group/MemoryDecoder-at-Scale)
+- [Paper](https://arxiv.org/abs/2607.27919)
+- [Model and data collection](https://huggingface.co/collections/Rubin-Wei/memorydecoder-at-scale)
+- [Released domain data](https://huggingface.co/datasets/Rubin-Wei/MemoryDecoder-at-Scale-domain-data/tree/main/law)
+
+## Citation
+
+If you use this checkpoint, please cite:
+
+```bibtex
+@misc{wei2026memorydecoderscalepretrained,
+      title={Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory},
+      author={Rubin Wei and Jiaqi Cao and Jiarui Wang and Junming Zhang and Qipeng Guo and Bowen Zhou and Zhouhan Lin},
+      year={2026},
+      eprint={2607.27919},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2607.27919},
+}
+```