docs: add official Zenodo DOI 10.5281/zenodo.22856047 and citation
Browse files
README.md
CHANGED
|
@@ -38,6 +38,7 @@ widget:
|
|
| 38 |
Rather than increasing parameter count to memorize factual records inside dense neural weights, AViGPT separates syntactic reasoning from factual storage. It couples a compact 183M reasoning core with a dedicated local NVMe SSD hardware memory bus. The model emits explicit control tokens to pause inference, execute sub-millisecond SQLite FTS5 full-text lookups on local storage, inject verified records into context, and complete generations with verified factual precision.
|
| 39 |
|
| 40 |
* **Author:** Avinash Ricky Yadlapalli ([@AvinashRicky](https://huggingface.co/AvinashRicky))
|
|
|
|
| 41 |
* **Code Repository:** [GitHub - Avinashricky211/AviGPT](https://github.com/Avinashricky211/AviGPT)
|
| 42 |
* **License:** MIT Open Source License
|
| 43 |
|
|
@@ -214,8 +215,9 @@ print(f"Total Response Latency: {metrics['total_latency_s']:.2f} s")
|
|
| 214 |
title={AViGPT: Decoupling Neural Reasoning from Parametric Memory via a Sub-Millisecond Native NVMe Hardware Bus},
|
| 215 |
author={Avinash Ricky Yadlapalli},
|
| 216 |
year={2026},
|
| 217 |
-
journal={
|
| 218 |
-
|
|
|
|
| 219 |
url={https://github.com/Avinashricky211/AviGPT}
|
| 220 |
}
|
| 221 |
```
|
|
|
|
| 38 |
Rather than increasing parameter count to memorize factual records inside dense neural weights, AViGPT separates syntactic reasoning from factual storage. It couples a compact 183M reasoning core with a dedicated local NVMe SSD hardware memory bus. The model emits explicit control tokens to pause inference, execute sub-millisecond SQLite FTS5 full-text lookups on local storage, inject verified records into context, and complete generations with verified factual precision.
|
| 39 |
|
| 40 |
* **Author:** Avinash Ricky Yadlapalli ([@AvinashRicky](https://huggingface.co/AvinashRicky))
|
| 41 |
+
* **DOI:** [10.5281/zenodo.22856047](https://doi.org/10.5281/zenodo.22856047)
|
| 42 |
* **Code Repository:** [GitHub - Avinashricky211/AviGPT](https://github.com/Avinashricky211/AviGPT)
|
| 43 |
* **License:** MIT Open Source License
|
| 44 |
|
|
|
|
| 215 |
title={AViGPT: Decoupling Neural Reasoning from Parametric Memory via a Sub-Millisecond Native NVMe Hardware Bus},
|
| 216 |
author={Avinash Ricky Yadlapalli},
|
| 217 |
year={2026},
|
| 218 |
+
journal={Zenodo},
|
| 219 |
+
doi={10.5281/zenodo.22856047},
|
| 220 |
+
howpublished={\url{https://doi.org/10.5281/zenodo.22856047}},
|
| 221 |
url={https://github.com/Avinashricky211/AviGPT}
|
| 222 |
}
|
| 223 |
```
|