update tokenizer bugs
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +9 -9
- tokenizer.model +3 -0
- tokenizer_config.json +9 -9
special_tokens_map.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -3,15 +3,6 @@
|
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
-
{
|
7 |
-
"id": 32011,
|
8 |
-
"content": "<image>",
|
9 |
-
"single_word": false,
|
10 |
-
"lstrip": false,
|
11 |
-
"rstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"special": true
|
14 |
-
},
|
15 |
{
|
16 |
"id": 0,
|
17 |
"content": "<unk>",
|
@@ -137,6 +128,15 @@
|
|
137 |
"rstrip": false,
|
138 |
"normalized": false,
|
139 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
}
|
141 |
],
|
142 |
"normalizer": {
|
|
|
3 |
"truncation": null,
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
{
|
7 |
"id": 0,
|
8 |
"content": "<unk>",
|
|
|
128 |
"rstrip": false,
|
129 |
"normalized": false,
|
130 |
"special": true
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"id": 32011,
|
134 |
+
"content": "<image>",
|
135 |
+
"single_word": false,
|
136 |
+
"lstrip": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"normalized": false,
|
139 |
+
"special": false
|
140 |
}
|
141 |
],
|
142 |
"normalizer": {
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
CHANGED
@@ -2,14 +2,6 @@
|
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
-
"32011": {
|
6 |
-
"content": "<image>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
"0": {
|
14 |
"content": "<unk>",
|
15 |
"lstrip": false,
|
@@ -121,12 +113,20 @@
|
|
121 |
"rstrip": false,
|
122 |
"single_word": false,
|
123 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
}
|
125 |
},
|
126 |
"bos_token": "<s>",
|
127 |
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
128 |
"clean_up_tokenization_spaces": false,
|
129 |
-
"eos_token": "
|
130 |
"legacy": false,
|
131 |
"model_max_length": 4096,
|
132 |
"pad_token": "<|endoftext|>",
|
|
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
|
|
113 |
"rstrip": false,
|
114 |
"single_word": false,
|
115 |
"special": true
|
116 |
+
},
|
117 |
+
"32011": {
|
118 |
+
"content": "<image>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
}
|
125 |
},
|
126 |
"bos_token": "<s>",
|
127 |
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
128 |
"clean_up_tokenization_spaces": false,
|
129 |
+
"eos_token": "<|endoftext|>",
|
130 |
"legacy": false,
|
131 |
"model_max_length": 4096,
|
132 |
"pad_token": "<|endoftext|>",
|