Update README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,10 @@ The name `nekomata` comes from the Japanese word [`猫又/ねこまた/Nekomata`
|
|
| 44 |
- [Wikipedia](https://dumps.wikimedia.org/other/cirrussearch)
|
| 45 |
- rinna curated Japanese dataset
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
* **Authors**
|
| 48 |
|
| 49 |
- [Tianyu Zhao](https://huggingface.co/tianyuz)
|
|
|
|
| 44 |
- [Wikipedia](https://dumps.wikimedia.org/other/cirrussearch)
|
| 45 |
- rinna curated Japanese dataset
|
| 46 |
|
| 47 |
+
* **Training Infrastructure**
|
| 48 |
+
|
| 49 |
+
`nekomata-14B` was trained on 16 nodes of Amazon EC2 trn1.32xlarge instance powered by AWS Trainium purpose-built ML accelerator chip. The pre-training job was completed within a timeframe of approximately 7 days.
|
| 50 |
+
|
| 51 |
* **Authors**
|
| 52 |
|
| 53 |
- [Tianyu Zhao](https://huggingface.co/tianyuz)
|