rajammanabrolu
commited on
Commit
·
5db0638
1
Parent(s):
d7a65de
Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -34
special_tokens_map.json
CHANGED
@@ -3,26 +3,8 @@
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
6 |
-
"bos_token":
|
7 |
-
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"eos_token": {
|
14 |
-
"content": "<|endoftext|>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
-
},
|
20 |
"pad_token": "<|pad|>",
|
21 |
-
"unk_token":
|
22 |
-
"content": "<|endoftext|>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false
|
27 |
-
}
|
28 |
}
|
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"pad_token": "<|pad|>",
|
9 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
}
|
tokenizer_config.json
CHANGED
@@ -2,40 +2,6 @@
|
|
2 |
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": false,
|
5 |
-
"added_tokens_decoder": {
|
6 |
-
"50256": {
|
7 |
-
"content": "<|endoftext|>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false,
|
12 |
-
"special": true
|
13 |
-
},
|
14 |
-
"50281": {
|
15 |
-
"content": "<|pad|>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false,
|
20 |
-
"special": true
|
21 |
-
},
|
22 |
-
"50282": {
|
23 |
-
"content": "<|im_start|>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": false,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false,
|
28 |
-
"special": true
|
29 |
-
},
|
30 |
-
"50283": {
|
31 |
-
"content": "<|im_end|>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false,
|
36 |
-
"special": true
|
37 |
-
}
|
38 |
-
},
|
39 |
"additional_special_tokens": [
|
40 |
"<|im_start|>",
|
41 |
"<|im_end|>"
|
|
|
2 |
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"additional_special_tokens": [
|
6 |
"<|im_start|>",
|
7 |
"<|im_end|>"
|