Upload processor
Browse files- chat_template.jinja +20 -0
- processor_config.json +43 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for message in messages %}
|
| 2 |
+
{%- if message['content'] is string %}
|
| 3 |
+
{{ message['content'].rstrip() }}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set ns = namespace(previous_was_image=False) %}
|
| 6 |
+
{%- for content in message['content'] %}
|
| 7 |
+
{%- if content['type'] == 'image' %}
|
| 8 |
+
<image>
|
| 9 |
+
{%- set ns.previous_was_image = True %}
|
| 10 |
+
{%- elif content['type'] == 'text' %}
|
| 11 |
+
{{- ('
|
| 12 |
+
' if ns.previous_was_image else '') + content['text'].rstrip() }}
|
| 13 |
+
{%- set ns.previous_was_image = False %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- endfor %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- if not loop.last %}
|
| 18 |
+
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endfor %}
|
processor_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"base_size": {
|
| 4 |
+
"height": 1024,
|
| 5 |
+
"width": 1024
|
| 6 |
+
},
|
| 7 |
+
"crop_size": null,
|
| 8 |
+
"data_format": "channels_first",
|
| 9 |
+
"device": null,
|
| 10 |
+
"disable_grouping": null,
|
| 11 |
+
"do_center_crop": null,
|
| 12 |
+
"do_convert_rgb": true,
|
| 13 |
+
"do_normalize": true,
|
| 14 |
+
"do_pad": null,
|
| 15 |
+
"do_rescale": true,
|
| 16 |
+
"do_resize": true,
|
| 17 |
+
"dynamic_hd": 36,
|
| 18 |
+
"image_mean": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"image_processor_type": "DeepseekOcrImageProcessorFast",
|
| 24 |
+
"image_std": [
|
| 25 |
+
0.5,
|
| 26 |
+
0.5,
|
| 27 |
+
0.5
|
| 28 |
+
],
|
| 29 |
+
"input_data_format": null,
|
| 30 |
+
"pad_size": null,
|
| 31 |
+
"patch_size": 16,
|
| 32 |
+
"processor_class": "DeepseekOcrProcessor",
|
| 33 |
+
"resample": 3,
|
| 34 |
+
"rescale_factor": 0.00392156862745098,
|
| 35 |
+
"return_tensors": null,
|
| 36 |
+
"size": {
|
| 37 |
+
"height": 1024,
|
| 38 |
+
"width": 1024
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"image_token": "<image>",
|
| 42 |
+
"processor_class": "DeepseekOcrProcessor"
|
| 43 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|User|>",
|
| 4 |
+
"<|Assistant|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<｜▁pad▁｜>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
}
|
| 27 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|