Upload tokenizer
Browse files- special_tokens_map.json +21 -3
- tokenizer.json +2 -2
special_tokens_map.json
CHANGED
@@ -15,9 +15,27 @@
|
|
15 |
"single_word": false
|
16 |
}
|
17 |
],
|
18 |
-
"bos_token":
|
19 |
-
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"unk_token": {
|
22 |
"content": "<unk>",
|
23 |
"lstrip": false,
|
|
|
15 |
"single_word": false
|
16 |
}
|
17 |
],
|
18 |
+
"bos_token": {
|
19 |
+
"content": "<|im_start|>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"eos_token": {
|
26 |
+
"content": "<|im_end|>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"pad_token": {
|
33 |
+
"content": "<|im_end|>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
"unk_token": {
|
40 |
"content": "<unk>",
|
41 |
"lstrip": false,
|
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 sha256:665921e5d3228ccbdcb0a7bdb871b6011f31315544d868447416801df7781583
|
3 |
+
size 16335058
|