Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,13 @@ license: apache-2.0
|
|
| 4 |
language:
|
| 5 |
- ru
|
| 6 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
## Training procedure
|
| 8 |
|
| 9 |
ruadapt mistral trained on saiga corpuses.
|
|
|
|
| 4 |
language:
|
| 5 |
- ru
|
| 6 |
---
|
| 7 |
+
|
| 8 |
+
Use in the same way as IlyaGusev/saiga2_7b_lora.
|
| 9 |
+
|
| 10 |
+
WARNING! Load tokenizer as AutoTokenizer.from_pretrained(model_path, use_fast=True)
|
| 11 |
+
|
| 12 |
+
Up to 60% faster generation and 35% training with HF because of different tokenizer.
|
| 13 |
+
|
| 14 |
## Training procedure
|
| 15 |
|
| 16 |
ruadapt mistral trained on saiga corpuses.
|