Upload special_tokens_map.json
Browse files- special_tokens_map.json +33 -30
special_tokens_map.json
CHANGED
|
@@ -1,54 +1,57 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|extra_id_0|>",
|
| 4 |
-
"<|endoftext|>",
|
| 5 |
-
"<|fim_prefix|>",
|
| 6 |
-
"<|fim_middle|>",
|
| 7 |
-
"<|fim_suffix|>",
|
| 8 |
-
"|||PHONE_NUMBER|||",
|
| 9 |
-
"|||EMAIL_ADDRESS|||",
|
| 10 |
-
"|||IP_ADDRESS|||",
|
| 11 |
-
"<|im_start|>",
|
| 12 |
-
"<|im_end|>",
|
| 13 |
-
"<|extra_id_1|>",
|
| 14 |
-
"<|extra_id_2|>",
|
| 15 |
-
"<|extra_id_3|>",
|
| 16 |
-
"<|extra_id_4|>",
|
| 17 |
-
"<|extra_id_5|>",
|
| 18 |
-
"<|extra_id_6|>",
|
| 19 |
-
"<|extra_id_7|>",
|
| 20 |
-
"<|extra_id_8|>",
|
| 21 |
-
"<|extra_id_9|>",
|
| 22 |
-
"<|extra_id_10|>",
|
| 23 |
-
"<|endofprompt|>",
|
| 24 |
-
"<|pad|>"
|
| 25 |
-
],
|
| 26 |
"bos_token": {
|
| 27 |
"content": "<|endoftext|>",
|
| 28 |
"lstrip": false,
|
| 29 |
"normalized": false,
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
},
|
| 33 |
"eos_token": {
|
| 34 |
"content": "<|endoftext|>",
|
| 35 |
"lstrip": false,
|
| 36 |
"normalized": false,
|
| 37 |
"rstrip": false,
|
| 38 |
-
"single_word": false
|
|
|
|
| 39 |
},
|
| 40 |
"pad_token": {
|
| 41 |
"content": "<|pad|>",
|
| 42 |
"lstrip": false,
|
| 43 |
"normalized": false,
|
| 44 |
"rstrip": false,
|
| 45 |
-
"single_word": false
|
|
|
|
| 46 |
},
|
| 47 |
"unk_token": {
|
| 48 |
"content": "<|endoftext|>",
|
| 49 |
"lstrip": false,
|
| 50 |
"normalized": false,
|
| 51 |
"rstrip": false,
|
| 52 |
-
"single_word": false
|
| 53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<|endoftext|>",
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
+
"single_word": false,
|
| 7 |
+
"special": true
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
"content": "<|endoftext|>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"special": true
|
| 16 |
},
|
| 17 |
"pad_token": {
|
| 18 |
"content": "<|pad|>",
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": false,
|
| 21 |
"rstrip": false,
|
| 22 |
+
"single_word": false,
|
| 23 |
+
"special": true
|
| 24 |
},
|
| 25 |
"unk_token": {
|
| 26 |
"content": "<|endoftext|>",
|
| 27 |
"lstrip": false,
|
| 28 |
"normalized": false,
|
| 29 |
"rstrip": false,
|
| 30 |
+
"single_word": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
"additional_special_tokens": [
|
| 34 |
+
"<|extra_id_0|>",
|
| 35 |
+
"<|endoftext|>",
|
| 36 |
+
"<|fim_prefix|>",
|
| 37 |
+
"<|fim_middle|>",
|
| 38 |
+
"<|fim_suffix|>",
|
| 39 |
+
"|||PHONE_NUMBER|||",
|
| 40 |
+
"|||EMAIL_ADDRESS|||",
|
| 41 |
+
"|||IP_ADDRESS|||",
|
| 42 |
+
"<|im_start|>",
|
| 43 |
+
"<|im_end|>",
|
| 44 |
+
"<|extra_id_1|>",
|
| 45 |
+
"<|extra_id_2|>",
|
| 46 |
+
"<|extra_id_3|>",
|
| 47 |
+
"<|extra_id_4|>",
|
| 48 |
+
"<|extra_id_5|>",
|
| 49 |
+
"<|extra_id_6|>",
|
| 50 |
+
"<|extra_id_7|>",
|
| 51 |
+
"<|extra_id_8|>",
|
| 52 |
+
"<|extra_id_9|>",
|
| 53 |
+
"<|extra_id_10|>",
|
| 54 |
+
"<|endofprompt|>",
|
| 55 |
+
"<|pad|>"
|
| 56 |
+
]
|
| 57 |
}
|