Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,3 @@
|
|
| 1 |
-
t5-v1_1-small pretrained with mlm task on
|
| 2 |
-
|
| 3 |
-
• kbd (custom latin script) 835K lines: a pile of scraped text from news sites, books etc.
|
| 4 |
-
|
| 5 |
-
• ru 3M lines: wiki corpus from OPUS
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
tokenizer: sentencepiece unigram, 8K, shared vocabulary
|
| 9 |
-
|
| 10 |
-
|
| 11 |
---
|
| 12 |
language:
|
| 13 |
- kbd
|
|
@@ -18,4 +8,13 @@ tags:
|
|
| 18 |
license: unknown
|
| 19 |
datasets:
|
| 20 |
- anzorq/kbd_lat-835k_ru-3M
|
| 21 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- kbd
|
|
|
|
| 8 |
license: unknown
|
| 9 |
datasets:
|
| 10 |
- anzorq/kbd_lat-835k_ru-3M
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
t5-v1_1-small pretrained with mlm task on
|
| 14 |
+
|
| 15 |
+
• kbd (custom latin script) 835K lines: a pile of scraped text from news sites, books etc.
|
| 16 |
+
|
| 17 |
+
• ru 3M lines: wiki corpus from OPUS
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
tokenizer: sentencepiece unigram, 8K, shared vocabulary
|