(Trained with Unsloth)
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- chat_template.json +3 -0
- preprocessor_config.json +29 -0
- processor_config.json +4 -0
- special_tokens_map.json +13 -10
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image_soft_token>": 262144
|
3 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"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"
|
3 |
+
}
|
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 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,27 +1,30 @@
|
|
1 |
{
|
|
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
-
"lstrip":
|
5 |
"normalized": false,
|
6 |
-
"rstrip":
|
7 |
"single_word": false
|
8 |
},
|
|
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
-
"lstrip":
|
12 |
"normalized": false,
|
13 |
-
"rstrip":
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
-
"lstrip":
|
19 |
"normalized": false,
|
20 |
-
"rstrip":
|
21 |
"single_word": false
|
22 |
},
|
23 |
"unk_token": {
|
24 |
-
"content": "
|
25 |
"lstrip": false,
|
26 |
"normalized": false,
|
27 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
+
"boi_token": "<start_of_image>",
|
3 |
"bos_token": {
|
4 |
+
"content": "<bos>",
|
5 |
+
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
"single_word": false
|
9 |
},
|
10 |
+
"eoi_token": "<end_of_image>",
|
11 |
"eos_token": {
|
12 |
+
"content": "<end_of_turn>",
|
13 |
+
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
"single_word": false
|
17 |
},
|
18 |
+
"image_token": "<image_soft_token>",
|
19 |
"pad_token": {
|
20 |
+
"content": "<pad>",
|
21 |
+
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
"single_word": false
|
25 |
},
|
26 |
"unk_token": {
|
27 |
+
"content": "<unk>",
|
28 |
"lstrip": false,
|
29 |
"normalized": false,
|
30 |
"rstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
3 |
+
size 4689074
|
tokenizer_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|