Initial tokenizer upload
Browse files- special_tokens_map.json +2 -28
- tokenizer.json +2 -2
- tokenizer_config.json +2 -20
special_tokens_map.json
CHANGED
@@ -1,33 +1,7 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
|
4 |
-
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "[/KNOWLEDGE]",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"content": "[REASONING]",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"content": "[/REASONING]",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
}
|
31 |
],
|
32 |
"bos_token": {
|
33 |
"content": "<|begin_of_text|>",
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"[KNOWLEDGE]",
|
4 |
+
"[REASONING]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
"bos_token": {
|
7 |
"content": "<|begin_of_text|>",
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c3e39f7ef233dc92fc002889a496eb1c1d3282824fd32e594f3e52bda70c0fc
|
3 |
+
size 17210576
|
tokenizer_config.json
CHANGED
@@ -2063,29 +2063,11 @@
|
|
2063 |
"rstrip": false,
|
2064 |
"single_word": false,
|
2065 |
"special": true
|
2066 |
-
},
|
2067 |
-
"128258": {
|
2068 |
-
"content": "[/KNOWLEDGE]",
|
2069 |
-
"lstrip": false,
|
2070 |
-
"normalized": false,
|
2071 |
-
"rstrip": false,
|
2072 |
-
"single_word": false,
|
2073 |
-
"special": true
|
2074 |
-
},
|
2075 |
-
"128259": {
|
2076 |
-
"content": "[/REASONING]",
|
2077 |
-
"lstrip": false,
|
2078 |
-
"normalized": false,
|
2079 |
-
"rstrip": false,
|
2080 |
-
"single_word": false,
|
2081 |
-
"special": true
|
2082 |
}
|
2083 |
},
|
2084 |
"additional_special_tokens": [
|
2085 |
"[KNOWLEDGE]",
|
2086 |
-
"[
|
2087 |
-
"[REASONING]",
|
2088 |
-
"[/REASONING]"
|
2089 |
],
|
2090 |
"bos_token": "<|begin_of_text|>",
|
2091 |
"clean_up_tokenization_spaces": true,
|
@@ -2102,7 +2084,7 @@
|
|
2102 |
"pad_token_type_id": 0,
|
2103 |
"padding_side": "right",
|
2104 |
"stride": 0,
|
2105 |
-
"tokenizer_class": "
|
2106 |
"truncation_side": "right",
|
2107 |
"truncation_strategy": "longest_first"
|
2108 |
}
|
|
|
2063 |
"rstrip": false,
|
2064 |
"single_word": false,
|
2065 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2066 |
}
|
2067 |
},
|
2068 |
"additional_special_tokens": [
|
2069 |
"[KNOWLEDGE]",
|
2070 |
+
"[REASONING]"
|
|
|
|
|
2071 |
],
|
2072 |
"bos_token": "<|begin_of_text|>",
|
2073 |
"clean_up_tokenization_spaces": true,
|
|
|
2084 |
"pad_token_type_id": 0,
|
2085 |
"padding_side": "right",
|
2086 |
"stride": 0,
|
2087 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
2088 |
"truncation_side": "right",
|
2089 |
"truncation_strategy": "longest_first"
|
2090 |
}
|