Upload tokenizer
Browse files- added_tokens.json +40 -0
- merges.txt +0 -0
- special_tokens_map.json +46 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|action|>": 50259,
|
| 3 |
+
"<|belief|>": 50257,
|
| 4 |
+
"<|context|>": 50263,
|
| 5 |
+
"<|endofaction|>": 50260,
|
| 6 |
+
"<|endofbelief|>": 50258,
|
| 7 |
+
"<|endofcontext|>": 50264,
|
| 8 |
+
"<|endofresponse|>": 50262,
|
| 9 |
+
"<|endofuseremotion|>": 50268,
|
| 10 |
+
"<|response|>": 50261,
|
| 11 |
+
"<|system|>": 50266,
|
| 12 |
+
"<|useremotion|>": 50267,
|
| 13 |
+
"<|user|>": 50265,
|
| 14 |
+
"[address]": 50269,
|
| 15 |
+
"[area]": 50270,
|
| 16 |
+
"[arriveby]": 50271,
|
| 17 |
+
"[bookday]": 50272,
|
| 18 |
+
"[bookpeople]": 50273,
|
| 19 |
+
"[bookstay]": 50274,
|
| 20 |
+
"[booktime]": 50275,
|
| 21 |
+
"[choice]": 50276,
|
| 22 |
+
"[day]": 50277,
|
| 23 |
+
"[department]": 50278,
|
| 24 |
+
"[departure]": 50279,
|
| 25 |
+
"[destination]": 50280,
|
| 26 |
+
"[duration]": 50281,
|
| 27 |
+
"[entrancefee]": 50282,
|
| 28 |
+
"[food]": 50283,
|
| 29 |
+
"[leaveat]": 50284,
|
| 30 |
+
"[name]": 50285,
|
| 31 |
+
"[openhours]": 50286,
|
| 32 |
+
"[phone]": 50287,
|
| 33 |
+
"[postcode]": 50288,
|
| 34 |
+
"[price]": 50289,
|
| 35 |
+
"[pricerange]": 50290,
|
| 36 |
+
"[ref]": 50291,
|
| 37 |
+
"[stars]": 50292,
|
| 38 |
+
"[trainid]": 50293,
|
| 39 |
+
"[type]": 50294
|
| 40 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|belief|>",
|
| 4 |
+
"<|endofbelief|>",
|
| 5 |
+
"<|action|>",
|
| 6 |
+
"<|endofaction|>",
|
| 7 |
+
"<|response|>",
|
| 8 |
+
"<|endofresponse|>",
|
| 9 |
+
"<|context|>",
|
| 10 |
+
"<|endofcontext|>",
|
| 11 |
+
"<|user|>",
|
| 12 |
+
"<|system|>",
|
| 13 |
+
"<|useremotion|>",
|
| 14 |
+
"<|endofuseremotion|>",
|
| 15 |
+
"[address]",
|
| 16 |
+
"[area]",
|
| 17 |
+
"[arriveby]",
|
| 18 |
+
"[bookday]",
|
| 19 |
+
"[bookpeople]",
|
| 20 |
+
"[bookstay]",
|
| 21 |
+
"[booktime]",
|
| 22 |
+
"[choice]",
|
| 23 |
+
"[day]",
|
| 24 |
+
"[department]",
|
| 25 |
+
"[departure]",
|
| 26 |
+
"[destination]",
|
| 27 |
+
"[duration]",
|
| 28 |
+
"[entrancefee]",
|
| 29 |
+
"[food]",
|
| 30 |
+
"[leaveat]",
|
| 31 |
+
"[name]",
|
| 32 |
+
"[openhours]",
|
| 33 |
+
"[phone]",
|
| 34 |
+
"[postcode]",
|
| 35 |
+
"[price]",
|
| 36 |
+
"[pricerange]",
|
| 37 |
+
"[ref]",
|
| 38 |
+
"[stars]",
|
| 39 |
+
"[trainid]",
|
| 40 |
+
"[type]"
|
| 41 |
+
],
|
| 42 |
+
"bos_token": "<|endoftext|>",
|
| 43 |
+
"eos_token": "<|endoftext|>",
|
| 44 |
+
"pad_token": "<|endoftext|>",
|
| 45 |
+
"unk_token": "<|endoftext|>"
|
| 46 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1024,
|
| 7 |
+
"special_tokens_map_file": "checkpoint-5100/special_tokens_map.json",
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|