Commit
·
47a3712
1
Parent(s):
c1658c2
Create tokenizer/special_tokens_map.json
Browse files
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
| 25 |
+
|
| 26 |
+
{
|
| 27 |
+
"bos_token": {
|
| 28 |
+
"content": "<|startoftext|>",
|
| 29 |
+
"single_word": false,
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"normalized": true
|
| 33 |
+
},
|
| 34 |
+
"eos_token": {
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false, "rstrip": false,
|
| 38 |
+
"normalized": true
|
| 39 |
+
},
|
| 40 |
+
"unk_token": {"content": "<|endoftext|>",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": true
|
| 45 |
+
},
|
| 46 |
+
"pad_token": "<|endoftext|>"
|
| 47 |
+
}
|