Update README.md
Browse files
README.md
CHANGED
|
@@ -183,7 +183,7 @@ The models were trained on 1 trillion tokens, following the pre-training recipe
|
|
| 183 |
### Model
|
| 184 |
|
| 185 |
- Architecture: Llama
|
| 186 |
-
- Pretraining tokens:
|
| 187 |
- Precision: bfloat16
|
| 188 |
|
| 189 |
### Hardware
|
|
|
|
| 183 |
### Model
|
| 184 |
|
| 185 |
- Architecture: Llama
|
| 186 |
+
- Pretraining tokens: 1 trillion tokens
|
| 187 |
- Precision: bfloat16
|
| 188 |
|
| 189 |
### Hardware
|