Upload processor
Browse files- special_tokens_map.json +3 -21
- tokenizer.json +1 -8
- tokenizer_config.json +1 -6
special_tokens_map.json
CHANGED
|
@@ -1,26 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "<image>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"content": "<end_of_utterance>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
],
|
| 25 |
"bos_token": {
|
| 26 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<fake_token_around_image>",
|
| 4 |
+
"<image>",
|
| 5 |
+
"<end_of_utterance>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
],
|
| 7 |
"bos_token": {
|
| 8 |
"content": "<s>",
|
tokenizer.json
CHANGED
|
@@ -1,14 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
-
"padding":
|
| 5 |
-
"strategy": "BatchLongest",
|
| 6 |
-
"direction": "Left",
|
| 7 |
-
"pad_to_multiple_of": null,
|
| 8 |
-
"pad_id": 0,
|
| 9 |
-
"pad_type_id": 0,
|
| 10 |
-
"pad_token": "<unk>"
|
| 11 |
-
},
|
| 12 |
"added_tokens": [
|
| 13 |
{
|
| 14 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -59,15 +59,10 @@
|
|
| 59 |
"bos_token": "<s>",
|
| 60 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. {% for message in messages %}{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}{% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}{% if add_generation_prompt %}ASSISTANT: {% endif %}",
|
| 61 |
"clean_up_tokenization_spaces": false,
|
| 62 |
-
"do_image_splitting": true,
|
| 63 |
"eos_token": "</s>",
|
| 64 |
-
"legacy":
|
| 65 |
-
"max_length": null,
|
| 66 |
"model_max_length": 1000000000000000019884624838656,
|
| 67 |
-
"pad_to_multiple_of": null,
|
| 68 |
"pad_token": "<unk>",
|
| 69 |
-
"pad_token_type_id": 0,
|
| 70 |
-
"padding_side": "left",
|
| 71 |
"processor_class": "Idefics2Processor",
|
| 72 |
"sp_model_kwargs": {},
|
| 73 |
"spaces_between_special_tokens": false,
|
|
|
|
| 59 |
"bos_token": "<s>",
|
| 60 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. {% for message in messages %}{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}{% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}{% if add_generation_prompt %}ASSISTANT: {% endif %}",
|
| 61 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 62 |
"eos_token": "</s>",
|
| 63 |
+
"legacy": false,
|
|
|
|
| 64 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 65 |
"pad_token": "<unk>",
|
|
|
|
|
|
|
| 66 |
"processor_class": "Idefics2Processor",
|
| 67 |
"sp_model_kwargs": {},
|
| 68 |
"spaces_between_special_tokens": false,
|