Upload tokenizer
Browse files- added_tokens.json +4 -0
- tokenizer.model +3 -0
- tokenizer_config.json +1 -1
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
CHANGED
@@ -45,7 +45,7 @@
|
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
48 |
-
"chat_template": "{% for message in messages %}{
|
49 |
"clean_up_tokenization_spaces": false,
|
50 |
"eos_token": "<|im_end|>",
|
51 |
"legacy": true,
|
|
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
48 |
+
"chat_template": "{% for message in messages %}a{% if not loop.last %} {% endif %}{% endfor %}",
|
49 |
"clean_up_tokenization_spaces": false,
|
50 |
"eos_token": "<|im_end|>",
|
51 |
"legacy": true,
|