Create tokenizers/tokenizer.json
Browse files- tokenizers/tokenizer.json +17 -0
tokenizers/tokenizer.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens": [],
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"embedding_size": 768,
|
| 6 |
+
"max_len": 512,
|
| 7 |
+
"model_input_names": ["input_ids", "attention_mask"],
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"special_tokens": {
|
| 10 |
+
"unk_token": "<unk>",
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"bos_token": "<bos>",
|
| 13 |
+
"eos_token": "<eos>"
|
| 14 |
+
},
|
| 15 |
+
"tokenizer_class": "BertTokenizer",
|
| 16 |
+
"vocab_size": 30522
|
| 17 |
+
}
|