Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ Fast and accurate.
|
|
| 8 |
|
| 9 |
Sentencepiece tokenizer fitted on 269 million Russian search queries log.
|
| 10 |
|
| 11 |
-
|
| 12 |
|
| 13 |
The data set for validation with manual markup consisted of 362 thousand examples.
|
| 14 |
|
|
|
|
| 8 |
|
| 9 |
Sentencepiece tokenizer fitted on 269 million Russian search queries log.
|
| 10 |
|
| 11 |
+
Short sequence length is used to use less memory.
|
| 12 |
|
| 13 |
The data set for validation with manual markup consisted of 362 thousand examples.
|
| 14 |
|