Upload processor
Browse files- chat_template.jinja +2 -0
- processor_config.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +27 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
|
| 2 |
+
{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
processor_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_image_splitting": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_pad": true,
|
| 7 |
+
"do_rescale": true,
|
| 8 |
+
"do_resize": true,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_processor_type": "Idefics3ImageProcessor",
|
| 15 |
+
"image_std": [
|
| 16 |
+
0.5,
|
| 17 |
+
0.5,
|
| 18 |
+
0.5
|
| 19 |
+
],
|
| 20 |
+
"max_image_size": {
|
| 21 |
+
"longest_edge": 512
|
| 22 |
+
},
|
| 23 |
+
"resample": 1,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"longest_edge": 2048
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"image_seq_len": 64,
|
| 30 |
+
"processor_class": "Idefics3Processor"
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|im_start|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<end_of_utterance>",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<fake_token_around_image>",
|
| 9 |
+
"<image>",
|
| 10 |
+
"<end_of_utterance>"
|
| 11 |
+
],
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"legacy": false,
|
| 14 |
+
"max_length": 4096,
|
| 15 |
+
"model_max_length": 8192,
|
| 16 |
+
"pad_to_multiple_of": null,
|
| 17 |
+
"pad_token": "<|im_end|>",
|
| 18 |
+
"pad_token_type_id": 0,
|
| 19 |
+
"padding_side": "right",
|
| 20 |
+
"processor_class": "Idefics3Processor",
|
| 21 |
+
"stride": 0,
|
| 22 |
+
"tokenizer_class": "TokenizersBackend",
|
| 23 |
+
"truncation_side": "left",
|
| 24 |
+
"truncation_strategy": "longest_first",
|
| 25 |
+
"unk_token": "<|endoftext|>",
|
| 26 |
+
"vocab_size": 49152
|
| 27 |
+
}
|