Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ fit on the [llm-japanese-dataset](https://github.com/masanorihirano/llm-japanese
|
|
| 14 |
|
| 15 |
This version of the weights was trained with the following hyperparameters:
|
| 16 |
|
| 17 |
-
- Epochs:
|
| 18 |
- Batch size: 128
|
| 19 |
- Cutoff length: 256
|
| 20 |
- Learning rate: 3e-4
|
|
@@ -41,9 +41,9 @@ To see more latest information, please go to [llm.msuzuki.me](https://llm.msuzuk
|
|
| 41 |
|
| 42 |
## Details
|
| 43 |
|
| 44 |
-
- Japanese Paper:
|
| 45 |
- English Paper:
|
| 46 |
-
- GitHub:
|
| 47 |
- Website: [llm.msuzuki.me](https://llm.msuzuki.me).
|
| 48 |
|
| 49 |
Citation:
|
|
|
|
| 14 |
|
| 15 |
This version of the weights was trained with the following hyperparameters:
|
| 16 |
|
| 17 |
+
- Epochs: 5
|
| 18 |
- Batch size: 128
|
| 19 |
- Cutoff length: 256
|
| 20 |
- Learning rate: 3e-4
|
|
|
|
| 41 |
|
| 42 |
## Details
|
| 43 |
|
| 44 |
+
- Japanese Paper: [https://jxiv.jst.go.jp/index.php/jxiv/preprint/view/422](https://jxiv.jst.go.jp/index.php/jxiv/preprint/view/422)
|
| 45 |
- English Paper:
|
| 46 |
+
- GitHub: [https://github.com/retarfi/jallm]
|
| 47 |
- Website: [llm.msuzuki.me](https://llm.msuzuki.me).
|
| 48 |
|
| 49 |
Citation:
|