Add proper model card with research links

README.md

@@ -0,0 +1,27 @@
+---
+license: cc-by-4.0
+tags:
+- research
+- reproducibility
+- state-space-model
+---
+
+# Eyla v1 — audit & reproducibility artifacts
+
+Artifacts accompanying **"Eyla: Toward an Identity-Anchored LLM Architecture with
+Integrated Biological Priors"** ([arXiv:2604.00009](https://arxiv.org/abs/2604.00009)):
+
+- `eyla_transplant_base_fp16.pt` — the transplant base checkpoint (fp16)
+- `lora_adapters/lora_c3_soul_final.pt` — the final "Soul Pass" identity LoRA
+- `model/` — architecture source: SSM block (HiPPO-initialized), brain orchestrator, memory injector, heuristic gates
+- `tokenizer/` — tokenizer used in the experiments
+
+Published so the paper's claims — including its documented failures — can be audited.
+Not intended for production use.
+
+## Author & research
+
+- 🌐 Website: [arifadito.com](https://arifadito.com)
+- 💻 GitHub: [github.com/Adiuk24](https://github.com/Adiuk24)
+- 📄 Eyla identity paper: [arXiv:2604.00009](https://arxiv.org/abs/2604.00009)
+- 🔧 Rust ML training verification tooling: [gradient-flow-arbiter](https://github.com/Adiuk24/gradient-flow-arbiter)