Upload tokenizer
Browse files- .gitattributes +1 -0
- special_tokens_map.json +5 -6
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +38 -14
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
special_tokens_map.json
CHANGED
@@ -1,24 +1,23 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
"<
|
4 |
-
"<
|
5 |
-
"</s>"
|
6 |
],
|
7 |
"bos_token": {
|
8 |
-
"content": "<
|
9 |
"lstrip": false,
|
10 |
"normalized": false,
|
11 |
"rstrip": false,
|
12 |
"single_word": false
|
13 |
},
|
14 |
"eos_token": {
|
15 |
-
"content": "
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
-
"pad_token": "
|
22 |
"unk_token": {
|
23 |
"content": "<unk>",
|
24 |
"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,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
11 |
"single_word": false
|
12 |
},
|
13 |
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
+
"pad_token": "<eos>",
|
21 |
"unk_token": {
|
22 |
"content": "<unk>",
|
23 |
"lstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
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 sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,9 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "<
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
@@ -9,7 +11,7 @@
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
-
"content": "<
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
@@ -17,7 +19,31 @@
|
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
-
"content": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
@@ -26,21 +52,19 @@
|
|
26 |
}
|
27 |
},
|
28 |
"additional_special_tokens": [
|
29 |
-
"<
|
30 |
-
"<
|
31 |
-
"</s>"
|
32 |
],
|
33 |
-
"bos_token": "<
|
34 |
-
"chat_template": "{% for message in messages %}
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
-
"eos_token": "
|
37 |
-
"legacy":
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
39 |
-
"pad_token": "
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
42 |
-
"tokenizer_class": "
|
43 |
-
"truncation_side": "left",
|
44 |
"unk_token": "<unk>",
|
45 |
-
"use_default_system_prompt":
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
"lstrip": false,
|
8 |
"normalized": false,
|
9 |
"rstrip": false,
|
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
|
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
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,
|
|
|
52 |
}
|
53 |
},
|
54 |
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
|
|
57 |
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{{ bos_token }}{% 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,
|
63 |
"model_max_length": 1000000000000000019884624838656,
|
64 |
+
"pad_token": "<eos>",
|
65 |
"sp_model_kwargs": {},
|
66 |
"spaces_between_special_tokens": false,
|
67 |
+
"tokenizer_class": "GemmaTokenizer",
|
|
|
68 |
"unk_token": "<unk>",
|
69 |
+
"use_default_system_prompt": false
|
70 |
}
|