danielhanchen
commited on
Commit
•
c0a63ef
1
Parent(s):
7db945d
Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer.json +2 -2
- tokenizer_config.json +21 -0
special_tokens_map.json
CHANGED
@@ -1,4 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<bos>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
"bos_token": {
|
7 |
"content": "<bos>",
|
8 |
"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 sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
|
3 |
+
size 17477929
|
tokenizer_config.json
CHANGED
@@ -33,9 +33,30 @@
|
|
33 |
"rstrip": false,
|
34 |
"single_word": false,
|
35 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
},
|
|
|
|
|
|
|
|
|
38 |
"bos_token": "<bos>",
|
|
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "<eos>",
|
41 |
"legacy": null,
|
|
|
33 |
"rstrip": false,
|
34 |
"single_word": false,
|
35 |
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<start_of_turn>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<end_of_turn>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
}
|
53 |
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
57 |
+
],
|
58 |
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
60 |
"clean_up_tokenization_spaces": false,
|
61 |
"eos_token": "<eos>",
|
62 |
"legacy": null,
|