Upload tokenizer
Browse files- special_tokens_map.json +16 -16
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -1,22 +1,22 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
],
|
6 |
-
"bos_token":
|
7 |
-
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"eos_token": {
|
14 |
-
"content": "<|im_end|>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
-
},
|
20 |
"pad_token": "<|im_end|>",
|
21 |
"unk_token": {
|
22 |
"content": "<|endoftext|>",
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|im_start|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|im_end|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
],
|
18 |
+
"bos_token": "<|im_start|>",
|
19 |
+
"eos_token": "<|im_end|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"pad_token": "<|im_end|>",
|
21 |
"unk_token": {
|
22 |
"content": "<|endoftext|>",
|
tokenizer_config.json
CHANGED
@@ -143,7 +143,7 @@
|
|
143 |
"<|im_end|>"
|
144 |
],
|
145 |
"bos_token": "<|im_start|>",
|
146 |
-
"chat_template": "{% for message in messages %}{
|
147 |
"clean_up_tokenization_spaces": false,
|
148 |
"eos_token": "<|im_end|>",
|
149 |
"extra_special_tokens": {},
|
|
|
143 |
"<|im_end|>"
|
144 |
],
|
145 |
"bos_token": "<|im_start|>",
|
146 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
147 |
"clean_up_tokenization_spaces": false,
|
148 |
"eos_token": "<|im_end|>",
|
149 |
"extra_special_tokens": {},
|