Upload tokenizer
Browse files- added_tokens.json +0 -1
- special_tokens_map.json +7 -2
- tokenizer.json +2 -2
- tokenizer_config.json +2 -14
added_tokens.json
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
{
|
2 |
-
"<image>": 100353,
|
3 |
"<pad>": 100352
|
4 |
}
|
|
|
1 |
{
|
|
|
2 |
"<pad>": 100352
|
3 |
}
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
4 |
"unk_token": {
|
5 |
"content": "<unk>",
|
6 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"pad_token": {
|
3 |
+
"content": "<pad>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
"unk_token": {
|
10 |
"content": "<unk>",
|
11 |
"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 sha256:02702cce6c4de786d52a3dc624b39e86134c159b7490ea30630739c6f723e7f8
|
3 |
+
size 11091481
|
tokenizer_config.json
CHANGED
@@ -81,7 +81,7 @@
|
|
81 |
"normalized": false,
|
82 |
"rstrip": false,
|
83 |
"single_word": false,
|
84 |
-
"special":
|
85 |
},
|
86 |
"10": {
|
87 |
"content": "<|reserved008|>",
|
@@ -4938,25 +4938,13 @@
|
|
4938 |
"rstrip": false,
|
4939 |
"single_word": false,
|
4940 |
"special": true
|
4941 |
-
},
|
4942 |
-
"100353": {
|
4943 |
-
"content": "<image>",
|
4944 |
-
"lstrip": false,
|
4945 |
-
"normalized": false,
|
4946 |
-
"rstrip": false,
|
4947 |
-
"single_word": false,
|
4948 |
-
"special": true
|
4949 |
}
|
4950 |
},
|
4951 |
"bos_token": null,
|
4952 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
4953 |
"clean_up_tokenization_spaces": false,
|
4954 |
"eos_token": null,
|
4955 |
-
"extra_special_tokens": {
|
4956 |
-
"image_token": "<image>",
|
4957 |
-
"pad_token": "<pad>"
|
4958 |
-
},
|
4959 |
-
"image_token": "<image>",
|
4960 |
"legacy": true,
|
4961 |
"model_max_length": 1000000000000000019884624838656,
|
4962 |
"pad_token": "<pad>",
|
|
|
81 |
"normalized": false,
|
82 |
"rstrip": false,
|
83 |
"single_word": false,
|
84 |
+
"special": true
|
85 |
},
|
86 |
"10": {
|
87 |
"content": "<|reserved008|>",
|
|
|
4938 |
"rstrip": false,
|
4939 |
"single_word": false,
|
4940 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4941 |
}
|
4942 |
},
|
4943 |
"bos_token": null,
|
4944 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
4945 |
"clean_up_tokenization_spaces": false,
|
4946 |
"eos_token": null,
|
4947 |
+
"extra_special_tokens": {},
|
|
|
|
|
|
|
|
|
4948 |
"legacy": true,
|
4949 |
"model_max_length": 1000000000000000019884624838656,
|
4950 |
"pad_token": "<pad>",
|