Upload processor
Browse files- chat_template.jinja +47 -0
- preprocessor_config.json +29 -0
- processor_config.json +4 -0
- tokenizer_config.json +0 -1
chat_template.jinja
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{ bos_token }}
|
2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
3 |
+
{%- if messages[0]['content'] is string -%}
|
4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
5 |
+
|
6 |
+
' -%}
|
7 |
+
{%- else -%}
|
8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
9 |
+
|
10 |
+
' -%}
|
11 |
+
{%- endif -%}
|
12 |
+
{%- set loop_messages = messages[1:] -%}
|
13 |
+
{%- else -%}
|
14 |
+
{%- set first_user_prefix = "" -%}
|
15 |
+
{%- set loop_messages = messages -%}
|
16 |
+
{%- endif -%}
|
17 |
+
{%- for message in loop_messages -%}
|
18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
20 |
+
{%- endif -%}
|
21 |
+
{%- if (message['role'] == 'assistant') -%}
|
22 |
+
{%- set role = "model" -%}
|
23 |
+
{%- else -%}
|
24 |
+
{%- set role = message['role'] -%}
|
25 |
+
{%- endif -%}
|
26 |
+
{{ '<start_of_turn>' + role + '
|
27 |
+
' + (first_user_prefix if loop.first else "") }}
|
28 |
+
{%- if message['content'] is string -%}
|
29 |
+
{{ message['content'] | trim }}
|
30 |
+
{%- elif message['content'] is iterable -%}
|
31 |
+
{%- for item in message['content'] -%}
|
32 |
+
{%- if item['type'] == 'image' -%}
|
33 |
+
{{ '<start_of_image>' }}
|
34 |
+
{%- elif item['type'] == 'text' -%}
|
35 |
+
{{ item['text'] | trim }}
|
36 |
+
{%- endif -%}
|
37 |
+
{%- endfor -%}
|
38 |
+
{%- else -%}
|
39 |
+
{{ raise_exception("Invalid content type") }}
|
40 |
+
{%- endif -%}
|
41 |
+
{{ '<end_of_turn>
|
42 |
+
' }}
|
43 |
+
{%- endfor -%}
|
44 |
+
{%- if add_generation_prompt -%}
|
45 |
+
{{'<start_of_turn>model
|
46 |
+
'}}
|
47 |
+
{%- endif -%}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pan_and_scan": null,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"image_mean": [
|
8 |
+
0.5,
|
9 |
+
0.5,
|
10 |
+
0.5
|
11 |
+
],
|
12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
13 |
+
"image_seq_length": 256,
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"pan_and_scan_max_num_crops": null,
|
20 |
+
"pan_and_scan_min_crop_size": null,
|
21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
22 |
+
"processor_class": "Gemma3Processor",
|
23 |
+
"resample": 2,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"height": 896,
|
27 |
+
"width": 896
|
28 |
+
}
|
29 |
+
}
|
processor_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"image_seq_length": 256,
|
3 |
+
"processor_class": "Gemma3Processor"
|
4 |
+
}
|
tokenizer_config.json
CHANGED
@@ -51325,7 +51325,6 @@
|
|
51325 |
},
|
51326 |
"boi_token": "<start_of_image>",
|
51327 |
"bos_token": "<bos>",
|
51328 |
-
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
|
51329 |
"clean_up_tokenization_spaces": false,
|
51330 |
"eoi_token": "<end_of_image>",
|
51331 |
"eos_token": "<eos>",
|
|
|
51325 |
},
|
51326 |
"boi_token": "<start_of_image>",
|
51327 |
"bos_token": "<bos>",
|
|
|
51328 |
"clean_up_tokenization_spaces": false,
|
51329 |
"eoi_token": "<end_of_image>",
|
51330 |
"eos_token": "<eos>",
|