Upload tokenizer
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +12 -0
- tokenizer_config.json +51 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000,
|
| 3 |
+
"▁<EOT>": 32004,
|
| 4 |
+
"▁<MID>": 32002,
|
| 5 |
+
"▁<PRE>": 32001,
|
| 6 |
+
"▁<SUF>": 32003
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"▁<PRE>",
|
| 4 |
+
"▁<MID>",
|
| 5 |
+
"▁<SUF>",
|
| 6 |
+
"▁<EOT>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": "<s>",
|
| 9 |
+
"eos_token": "</s>",
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"additional_special_tokens": [
|
| 5 |
+
"▁<PRE>",
|
| 6 |
+
"▁<MID>",
|
| 7 |
+
"▁<SUF>",
|
| 8 |
+
"▁<EOT>"
|
| 9 |
+
],
|
| 10 |
+
"bos_token": {
|
| 11 |
+
"__type": "AddedToken",
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"clean_up_tokenization_spaces": false,
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"__type": "AddedToken",
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"eot_token": "▁<EOT>",
|
| 28 |
+
"fill_token": "<FILL_ME>",
|
| 29 |
+
"legacy": null,
|
| 30 |
+
"middle_token": "▁<MID>",
|
| 31 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 32 |
+
"pad_token": null,
|
| 33 |
+
"padding_side": "right",
|
| 34 |
+
"prefix_token": "▁<PRE>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"spaces_between_special_tokens": false,
|
| 37 |
+
"suffix_first": false,
|
| 38 |
+
"suffix_token": "▁<SUF>",
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"trust_remote_code": false,
|
| 41 |
+
"unk_token": {
|
| 42 |
+
"__type": "AddedToken",
|
| 43 |
+
"content": "<unk>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": true,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
},
|
| 49 |
+
"use_default_system_prompt": false,
|
| 50 |
+
"use_fast": true
|
| 51 |
+
}
|