Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +11 -11
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
-
"
|
6 |
"content": "<|boundary|>",
|
7 |
"lstrip": false,
|
8 |
"normalized": true,
|
@@ -10,7 +10,7 @@
|
|
10 |
"single_word": false,
|
11 |
"special": false
|
12 |
},
|
13 |
-
"
|
14 |
"content": "<|im_start|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": true,
|
@@ -18,7 +18,7 @@
|
|
18 |
"single_word": false,
|
19 |
"special": false
|
20 |
},
|
21 |
-
"
|
22 |
"content": "<|im_end|>",
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
@@ -26,7 +26,7 @@
|
|
26 |
"single_word": false,
|
27 |
"special": false
|
28 |
},
|
29 |
-
"
|
30 |
"content": "<tool_call>",
|
31 |
"lstrip": false,
|
32 |
"normalized": false,
|
@@ -34,7 +34,7 @@
|
|
34 |
"single_word": false,
|
35 |
"special": false
|
36 |
},
|
37 |
-
"
|
38 |
"content": "</tool_call>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
@@ -42,7 +42,7 @@
|
|
42 |
"single_word": false,
|
43 |
"special": false
|
44 |
},
|
45 |
-
"
|
46 |
"content": "<think>",
|
47 |
"lstrip": false,
|
48 |
"normalized": false,
|
@@ -50,7 +50,7 @@
|
|
50 |
"single_word": false,
|
51 |
"special": false
|
52 |
},
|
53 |
-
"
|
54 |
"content": "</think>",
|
55 |
"lstrip": false,
|
56 |
"normalized": false,
|
@@ -58,7 +58,7 @@
|
|
58 |
"single_word": false,
|
59 |
"special": false
|
60 |
},
|
61 |
-
"
|
62 |
"content": "<|unused_special_token_0|>",
|
63 |
"lstrip": false,
|
64 |
"normalized": false,
|
@@ -66,7 +66,7 @@
|
|
66 |
"single_word": false,
|
67 |
"special": true
|
68 |
},
|
69 |
-
"
|
70 |
"content": "<|unused_special_token_1|>",
|
71 |
"lstrip": false,
|
72 |
"normalized": false,
|
@@ -74,7 +74,7 @@
|
|
74 |
"single_word": false,
|
75 |
"special": true
|
76 |
},
|
77 |
-
"
|
78 |
"content": "<|unused_special_token_2|>",
|
79 |
"lstrip": false,
|
80 |
"normalized": false,
|
@@ -82,7 +82,7 @@
|
|
82 |
"single_word": false,
|
83 |
"special": true
|
84 |
},
|
85 |
-
"
|
86 |
"content": "<|unused_special_token_3|>",
|
87 |
"lstrip": false,
|
88 |
"normalized": false,
|
|
|
2 |
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"added_tokens_decoder": {
|
5 |
+
"31989": {
|
6 |
"content": "<|boundary|>",
|
7 |
"lstrip": false,
|
8 |
"normalized": true,
|
|
|
10 |
"single_word": false,
|
11 |
"special": false
|
12 |
},
|
13 |
+
"31990": {
|
14 |
"content": "<|im_start|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": true,
|
|
|
18 |
"single_word": false,
|
19 |
"special": false
|
20 |
},
|
21 |
+
"31991": {
|
22 |
"content": "<|im_end|>",
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
|
|
26 |
"single_word": false,
|
27 |
"special": false
|
28 |
},
|
29 |
+
"31992": {
|
30 |
"content": "<tool_call>",
|
31 |
"lstrip": false,
|
32 |
"normalized": false,
|
|
|
34 |
"single_word": false,
|
35 |
"special": false
|
36 |
},
|
37 |
+
"31993": {
|
38 |
"content": "</tool_call>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
|
|
42 |
"single_word": false,
|
43 |
"special": false
|
44 |
},
|
45 |
+
"31994": {
|
46 |
"content": "<think>",
|
47 |
"lstrip": false,
|
48 |
"normalized": false,
|
|
|
50 |
"single_word": false,
|
51 |
"special": false
|
52 |
},
|
53 |
+
"31995": {
|
54 |
"content": "</think>",
|
55 |
"lstrip": false,
|
56 |
"normalized": false,
|
|
|
58 |
"single_word": false,
|
59 |
"special": false
|
60 |
},
|
61 |
+
"31996": {
|
62 |
"content": "<|unused_special_token_0|>",
|
63 |
"lstrip": false,
|
64 |
"normalized": false,
|
|
|
66 |
"single_word": false,
|
67 |
"special": true
|
68 |
},
|
69 |
+
"31997": {
|
70 |
"content": "<|unused_special_token_1|>",
|
71 |
"lstrip": false,
|
72 |
"normalized": false,
|
|
|
74 |
"single_word": false,
|
75 |
"special": true
|
76 |
},
|
77 |
+
"31998": {
|
78 |
"content": "<|unused_special_token_2|>",
|
79 |
"lstrip": false,
|
80 |
"normalized": false,
|
|
|
82 |
"single_word": false,
|
83 |
"special": true
|
84 |
},
|
85 |
+
"31999": {
|
86 |
"content": "<|unused_special_token_3|>",
|
87 |
"lstrip": false,
|
88 |
"normalized": false,
|