Upload tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +49 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|reserved_special_token_248|>",
|
4 |
+
"<|reserved_special_token_249|>",
|
5 |
+
"<|reserved_special_token_250|>",
|
6 |
+
"<|reserved_special_token_251|>",
|
7 |
+
"<|reserved_special_token_252|>",
|
8 |
+
"<|reserved_special_token_253|>",
|
9 |
+
"<|reserved_special_token_254|>",
|
10 |
+
"<|reserved_special_token_255|>",
|
11 |
+
"<|reserved_special_token_256|>",
|
12 |
+
"<|reserved_special_token_257|>",
|
13 |
+
"<|reserved_special_token_258|>",
|
14 |
+
"<|reserved_special_token_259|>",
|
15 |
+
"<|reserved_special_token_260|>",
|
16 |
+
"<|reserved_special_token_261|>",
|
17 |
+
"<|reserved_special_token_262|>",
|
18 |
+
"<|reserved_special_token_263|>",
|
19 |
+
"<|reserved_special_token_264|>",
|
20 |
+
"<|reserved_special_token_265|>",
|
21 |
+
"<|reserved_special_token_266|>",
|
22 |
+
"<|reserved_special_token_267|>",
|
23 |
+
"<|reserved_special_token_268|>",
|
24 |
+
"<|reserved_special_token_269|>",
|
25 |
+
"<|reserved_special_token_270|>",
|
26 |
+
"<|reserved_special_token_271|>",
|
27 |
+
"<|reserved_special_token_272|>",
|
28 |
+
"<|reserved_special_token_273|>",
|
29 |
+
"<|reserved_special_token_274|>",
|
30 |
+
"<|reserved_special_token_275|>",
|
31 |
+
"<|reserved_special_token_276|>",
|
32 |
+
"<|reserved_special_token_277|>"
|
33 |
+
],
|
34 |
+
"bos_token": {
|
35 |
+
"content": "<|begin_of_text|>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"eos_token": {
|
42 |
+
"content": "<|end_of_text|>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"pad_token": "!"
|
49 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d62e27ffbfa24d9281f432757b1abca3e118b3dac7e1dce146f64aea37153e3
|
3 |
+
size 18727752
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|