Add tokenizer files
Browse files- tokenizer.model +3 -0
- tokenizer.vocab +0 -0
- tokenizer_config.json +11 -0
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcea7b417395ecf731062d1d241db13069e60e23ccc7cad4a77535900c38fe37
|
| 3 |
+
size 1302086
|
tokenizer.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "hindi_embedding",
|
| 3 |
+
"tokenizer_class": "HindiSentencePieceTokenizer",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"vocab_size": 50000
|
| 11 |
+
}
|