neshkatrapati
commited on
Commit
•
f1697d9
1
Parent(s):
4cf72d5
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +28 -9
- tokenizer.json +2 -2
- tokenizer.model +3 -0
- tokenizer_config.json +3 -7
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,11 +1,30 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"<
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
}
|
tokenizer.json
CHANGED
@@ -34,8 +34,8 @@
|
|
34 |
"id": 32000,
|
35 |
"content": "<pad>",
|
36 |
"single_word": false,
|
37 |
-
"lstrip":
|
38 |
-
"rstrip":
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
}
|
|
|
34 |
"id": 32000,
|
35 |
"content": "<pad>",
|
36 |
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
}
|
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
@@ -26,18 +26,14 @@
|
|
26 |
},
|
27 |
"32000": {
|
28 |
"content": "<pad>",
|
29 |
-
"lstrip":
|
30 |
"normalized": false,
|
31 |
-
"rstrip":
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
}
|
35 |
},
|
36 |
-
"additional_special_tokens": [
|
37 |
-
"<unk>",
|
38 |
-
"<s>",
|
39 |
-
"</s>"
|
40 |
-
],
|
41 |
"bos_token": "<s>",
|
42 |
"chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
43 |
"clean_up_tokenization_spaces": false,
|
|
|
26 |
},
|
27 |
"32000": {
|
28 |
"content": "<pad>",
|
29 |
+
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
}
|
35 |
},
|
36 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
|
|
37 |
"bos_token": "<s>",
|
38 |
"chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
39 |
"clean_up_tokenization_spaces": false,
|