Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +1 -0
- chat_template.json +1 -0
- config.json +63 -0
- generation_config.json +13 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model-00008-of-00016.safetensors +3 -0
- model-00009-of-00016.safetensors +3 -0
- model-00010-of-00016.safetensors +3 -0
- model-00011-of-00016.safetensors +3 -0
- model-00012-of-00016.safetensors +3 -0
- model-00013-of-00016.safetensors +3 -0
- model-00014-of-00016.safetensors +3 -0
- model-00015-of-00016.safetensors +3 -0
- model-00016-of-00016.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +1 -0
- processor_config.json +1 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -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 @@
|
|
|
|
|
1 |
+
{"<image_soft_token>": 262144}
|
chat_template.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"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"}
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Gemma3ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"boi_token_index": 255999,
|
6 |
+
"eoi_token_index": 256000,
|
7 |
+
"eos_token_id": [
|
8 |
+
1,
|
9 |
+
106
|
10 |
+
],
|
11 |
+
"image_token_index": 262144,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"mm_tokens_per_image": 256,
|
14 |
+
"model_type": "gemma3",
|
15 |
+
"text_config": {
|
16 |
+
"attention_bias": false,
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"attn_logit_softcapping": null,
|
19 |
+
"cache_implementation": "hybrid",
|
20 |
+
"final_logit_softcapping": null,
|
21 |
+
"head_dim": 128,
|
22 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
23 |
+
"hidden_size": 5376,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 21504,
|
26 |
+
"max_position_embeddings": 131072,
|
27 |
+
"model_type": "gemma3_text",
|
28 |
+
"num_attention_heads": 32,
|
29 |
+
"num_hidden_layers": 62,
|
30 |
+
"num_key_value_heads": 16,
|
31 |
+
"query_pre_attn_scalar": 168,
|
32 |
+
"rms_norm_eps": 1e-06,
|
33 |
+
"rope_local_base_freq": 10000.0,
|
34 |
+
"rope_scaling": {
|
35 |
+
"factor": 8.0,
|
36 |
+
"rope_type": "linear"
|
37 |
+
},
|
38 |
+
"rope_theta": 1000000.0,
|
39 |
+
"sliding_window": 1024,
|
40 |
+
"sliding_window_pattern": 6,
|
41 |
+
"torch_dtype": "bfloat16",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 262208
|
44 |
+
},
|
45 |
+
"torch_dtype": "bfloat16",
|
46 |
+
"transformers_version": "4.51.3",
|
47 |
+
"vision_config": {
|
48 |
+
"attention_dropout": 0.0,
|
49 |
+
"hidden_act": "gelu_pytorch_tanh",
|
50 |
+
"hidden_size": 1152,
|
51 |
+
"image_size": 896,
|
52 |
+
"intermediate_size": 4304,
|
53 |
+
"layer_norm_eps": 1e-06,
|
54 |
+
"model_type": "siglip_vision_model",
|
55 |
+
"num_attention_heads": 16,
|
56 |
+
"num_channels": 3,
|
57 |
+
"num_hidden_layers": 27,
|
58 |
+
"patch_size": 14,
|
59 |
+
"torch_dtype": "bfloat16",
|
60 |
+
"vision_use_head": false
|
61 |
+
},
|
62 |
+
"_name_or_path": "bigband/AlmightyAshur"
|
63 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 2,
|
3 |
+
"cache_implementation": "hybrid",
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": [
|
6 |
+
1,
|
7 |
+
106
|
8 |
+
],
|
9 |
+
"pad_token_id": 0,
|
10 |
+
"top_k": 64,
|
11 |
+
"top_p": 0.95,
|
12 |
+
"transformers_version": "4.51.3"
|
13 |
+
}
|
model-00001-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61cd34abea77010c637b830353d30a6a0785e9eda6e6f90704c10a4ea553cb48
|
3 |
+
size 3753522688
|
model-00002-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e795d92ec9ca54f9310e5ff714467e5abb34ef0a96dab76a6d4a0db33f59f183
|
3 |
+
size 3578447552
|
model-00003-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7f17e957a238d841aed47856eb0dd14b46daf50d884919982fc497bc3a1d204
|
3 |
+
size 3534406472
|
model-00004-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:861b6f2ceb9a7ba23abb1e634199df319d47899f5b06f208590e9077f0cc3f84
|
3 |
+
size 3666571920
|
model-00005-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9edf16e7cb6135cdc610c7796da1053a345175fb2b92c1eb4f9afd892fa0f426
|
3 |
+
size 3534406528
|
model-00006-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55cc861513467f82889f21ca52ad84d058745197513fe087a26afdc874840121
|
3 |
+
size 3534406520
|
model-00007-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87cf0582217e4ea4c4142ad6172b759210610a03bc538fe3889d03d4636f2e87
|
3 |
+
size 3666571928
|
model-00008-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30c6ffbde7e3d2dd789bb61546fb11a66b9e9080e951972c89b7069101042fdd
|
3 |
+
size 3534406528
|
model-00009-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72e86036bd637c96046dfbf989e349d8a39f4365e16f3cecfceeb327110d2da5
|
3 |
+
size 3534406520
|
model-00010-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa2d2d8961cacd9fb464d67c4b5c11f4668f9d9d81ef5ddedcff6f8226d50e92
|
3 |
+
size 3666571928
|
model-00011-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaf1e6d708cbf91717e9564f534edcf7111bcb5e0970ac28bc32050e6df06d0a
|
3 |
+
size 3534406528
|
model-00012-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbed1c1e3258bc0dc60828b51a0b04158cc64a8c9a5f54f750005a0a094d330d
|
3 |
+
size 3534406520
|
model-00013-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0bfb1ec04c56d76b40bce1f5a9f75d6cbda58d6fed3252820ed8f27f1160bac
|
3 |
+
size 3666571928
|
model-00014-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:121cf503687eabf5c8723c14115ee79411331bdad13b197cc198eaf8d55ee0c7
|
3 |
+
size 3534406528
|
model-00015-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8d640a896f755b96afa76f1f93b2185597a0c0c746299ad04ebf9f3c46cb1cb
|
3 |
+
size 3534406520
|
model-00016-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dddc6127de2f27e137404689a2d0263c6118ff268d08ea5bc3def7963e01004b
|
3 |
+
size 1057064408
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_convert_rgb": null, "do_normalize": true, "do_pan_and_scan": null, "do_rescale": true, "do_resize": true, "image_mean": [0.5, 0.5, 0.5], "image_processor_type": "Gemma3ImageProcessor", "image_seq_length": 256, "image_std": [0.5, 0.5, 0.5], "pan_and_scan_max_num_crops": null, "pan_and_scan_min_crop_size": null, "pan_and_scan_min_ratio_to_activate": null, "processor_class": "Gemma3Processor", "resample": 2, "rescale_factor": 0.00392156862745098, "size": {"height": 896, "width": 896}}
|
processor_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"image_seq_length": 256, "processor_class": "Gemma3Processor"}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<eos>",
|
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,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
3 |
+
size 33384568
|
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
ADDED
The diff for this file is too large to render.
See raw diff
|
|