Add <|im_start|> as a special token to tokenizer_config.json (#4)
Browse files- Add <|im_start|> as a special token to tokenizer_config.json (d20f49278c006877741954898e3e4e546ea2b5b8)
Co-authored-by: Bartowski <[email protected]>
- tokenizer_config.json +8 -0
tokenizer_config.json
CHANGED
@@ -27,6 +27,14 @@
|
|
27 |
"single_word": false,
|
28 |
"special": true
|
29 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"7": {
|
31 |
"content": "<|im_end|>",
|
32 |
"lstrip": false,
|
|
|
27 |
"single_word": false,
|
28 |
"special": true
|
29 |
},
|
30 |
+
"6": {
|
31 |
+
"content": "<|im_start|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
"7": {
|
39 |
"content": "<|im_end|>",
|
40 |
"lstrip": false,
|