fix(tokenizer_config): Adjusts `rstrip` of special tokens.
#53
by
gugarosa
- opened
- tokenizer_config.json +13 -13
tokenizer_config.json
CHANGED
@@ -22,9 +22,9 @@
|
|
22 |
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
"normalized": false,
|
25 |
-
"rstrip":
|
26 |
"single_word": false,
|
27 |
-
"special":
|
28 |
},
|
29 |
"32000": {
|
30 |
"content": "<|endoftext|>",
|
@@ -38,7 +38,7 @@
|
|
38 |
"content": "<|assistant|>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
-
"rstrip":
|
42 |
"single_word": false,
|
43 |
"special": true
|
44 |
},
|
@@ -46,7 +46,7 @@
|
|
46 |
"content": "<|placeholder1|>",
|
47 |
"lstrip": false,
|
48 |
"normalized": false,
|
49 |
-
"rstrip":
|
50 |
"single_word": false,
|
51 |
"special": true
|
52 |
},
|
@@ -54,7 +54,7 @@
|
|
54 |
"content": "<|placeholder2|>",
|
55 |
"lstrip": false,
|
56 |
"normalized": false,
|
57 |
-
"rstrip":
|
58 |
"single_word": false,
|
59 |
"special": true
|
60 |
},
|
@@ -62,7 +62,7 @@
|
|
62 |
"content": "<|placeholder3|>",
|
63 |
"lstrip": false,
|
64 |
"normalized": false,
|
65 |
-
"rstrip":
|
66 |
"single_word": false,
|
67 |
"special": true
|
68 |
},
|
@@ -70,7 +70,7 @@
|
|
70 |
"content": "<|placeholder4|>",
|
71 |
"lstrip": false,
|
72 |
"normalized": false,
|
73 |
-
"rstrip":
|
74 |
"single_word": false,
|
75 |
"special": true
|
76 |
},
|
@@ -78,7 +78,7 @@
|
|
78 |
"content": "<|system|>",
|
79 |
"lstrip": false,
|
80 |
"normalized": false,
|
81 |
-
"rstrip":
|
82 |
"single_word": false,
|
83 |
"special": true
|
84 |
},
|
@@ -86,7 +86,7 @@
|
|
86 |
"content": "<|end|>",
|
87 |
"lstrip": false,
|
88 |
"normalized": false,
|
89 |
-
"rstrip":
|
90 |
"single_word": false,
|
91 |
"special": true
|
92 |
},
|
@@ -94,7 +94,7 @@
|
|
94 |
"content": "<|placeholder5|>",
|
95 |
"lstrip": false,
|
96 |
"normalized": false,
|
97 |
-
"rstrip":
|
98 |
"single_word": false,
|
99 |
"special": true
|
100 |
},
|
@@ -102,7 +102,7 @@
|
|
102 |
"content": "<|placeholder6|>",
|
103 |
"lstrip": false,
|
104 |
"normalized": false,
|
105 |
-
"rstrip":
|
106 |
"single_word": false,
|
107 |
"special": true
|
108 |
},
|
@@ -110,7 +110,7 @@
|
|
110 |
"content": "<|user|>",
|
111 |
"lstrip": false,
|
112 |
"normalized": false,
|
113 |
-
"rstrip":
|
114 |
"single_word": false,
|
115 |
"special": true
|
116 |
}
|
@@ -127,4 +127,4 @@
|
|
127 |
"tokenizer_class": "LlamaTokenizer",
|
128 |
"unk_token": "<unk>",
|
129 |
"use_default_system_prompt": false
|
130 |
-
}
|
|
|
22 |
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
"single_word": false,
|
27 |
+
"special": false
|
28 |
},
|
29 |
"32000": {
|
30 |
"content": "<|endoftext|>",
|
|
|
38 |
"content": "<|assistant|>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
"single_word": false,
|
43 |
"special": true
|
44 |
},
|
|
|
46 |
"content": "<|placeholder1|>",
|
47 |
"lstrip": false,
|
48 |
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
"single_word": false,
|
51 |
"special": true
|
52 |
},
|
|
|
54 |
"content": "<|placeholder2|>",
|
55 |
"lstrip": false,
|
56 |
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
"single_word": false,
|
59 |
"special": true
|
60 |
},
|
|
|
62 |
"content": "<|placeholder3|>",
|
63 |
"lstrip": false,
|
64 |
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
"single_word": false,
|
67 |
"special": true
|
68 |
},
|
|
|
70 |
"content": "<|placeholder4|>",
|
71 |
"lstrip": false,
|
72 |
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
"single_word": false,
|
75 |
"special": true
|
76 |
},
|
|
|
78 |
"content": "<|system|>",
|
79 |
"lstrip": false,
|
80 |
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
"single_word": false,
|
83 |
"special": true
|
84 |
},
|
|
|
86 |
"content": "<|end|>",
|
87 |
"lstrip": false,
|
88 |
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
"single_word": false,
|
91 |
"special": true
|
92 |
},
|
|
|
94 |
"content": "<|placeholder5|>",
|
95 |
"lstrip": false,
|
96 |
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
"single_word": false,
|
99 |
"special": true
|
100 |
},
|
|
|
102 |
"content": "<|placeholder6|>",
|
103 |
"lstrip": false,
|
104 |
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
"single_word": false,
|
107 |
"special": true
|
108 |
},
|
|
|
110 |
"content": "<|user|>",
|
111 |
"lstrip": false,
|
112 |
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
"single_word": false,
|
115 |
"special": true
|
116 |
}
|
|
|
127 |
"tokenizer_class": "LlamaTokenizer",
|
128 |
"unk_token": "<unk>",
|
129 |
"use_default_system_prompt": false
|
130 |
+
}
|