Update README.md
Browse files
README.md
CHANGED
|
@@ -127,7 +127,7 @@ The tokenizer is specifically designed for script-diverse languages, avoiding th
|
|
| 127 |
- **Batch size**: 512K tokens
|
| 128 |
- **Learning rate**: 3e-4 (cosine decay)
|
| 129 |
- **Optimizer**: AdamW
|
| 130 |
-
|
| 131 |
|
| 132 |
### SFT
|
| 133 |
- **Hardware**: 1× g6e.xlarge (L40S 48GB)
|
|
|
|
| 127 |
- **Batch size**: 512K tokens
|
| 128 |
- **Learning rate**: 3e-4 (cosine decay)
|
| 129 |
- **Optimizer**: AdamW
|
| 130 |
+
|
| 131 |
|
| 132 |
### SFT
|
| 133 |
- **Hardware**: 1× g6e.xlarge (L40S 48GB)
|