Commit
•
c28c1ea
1
Parent(s):
44d2a6f
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,16 @@ Datasets comprise Bangla, English, and Codes data. We mixed Bangla data with Eng
|
|
| 29 |
|
| 30 |
Token-wise distribution will be added soon below.
|
| 31 |
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
## How to Use
|
| 35 |
The basic use cases to generate text using this model are simple. Follow the below code to generate text using this model.
|
|
|
|
| 29 |
|
| 30 |
Token-wise distribution will be added soon below.
|
| 31 |
|
| 32 |
+
| Data chunk | Language | Token count |
|
| 33 |
+
|----------------|----------|-------------|
|
| 34 |
+
| Redpajama Arxiv | English | 00 |
|
| 35 |
+
| Redpajama Book | English | 00 |
|
| 36 |
+
| Redpajama Wikipedia | English | 00 |
|
| 37 |
+
| Redpajama Github Code | English | 00 |
|
| 38 |
+
| Redpajama StackExchange | English | 00 |
|
| 39 |
+
| Redpajama Common crawl | English | 00 |
|
| 40 |
+
| Redpajama C4 | English | 00 |
|
| 41 |
+
| Bangla (culturax, books, news, Wikipedia, Banglapedia) | Bangla | 00 |
|
| 42 |
|
| 43 |
## How to Use
|
| 44 |
The basic use cases to generate text using this model are simple. Follow the below code to generate text using this model.
|