Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,8 @@ WARNING! Load tokenizer as AutoTokenizer.from_pretrained(model_path, use_fast=Tr
|
|
9 |
|
10 |
Up to 60% faster generation and 35% training with HF because of different tokenizer.
|
11 |
|
|
|
|
|
12 |
## Model description
|
13 |
|
14 |
Instruction version (Saiga datasets) of Russian adaptation of LLaMa-2-7B by replacing the tokenizer.
|
|
|
9 |
|
10 |
Up to 60% faster generation and 35% training with HF because of different tokenizer.
|
11 |
|
12 |
+
Colab: https://colab.research.google.com/drive/109ZhEB6STy-0jO-Z_4ttkWr1jg_FCTRW?usp=sharing
|
13 |
+
|
14 |
## Model description
|
15 |
|
16 |
Instruction version (Saiga datasets) of Russian adaptation of LLaMa-2-7B by replacing the tokenizer.
|