Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1 @@
+  {"<image_soft_token>": 262144} 

chat_template.json

@@ -0,0 +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

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "boi_token_index": 255999,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eoi_token_index": 256000,
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 128,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 5376,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "intermediate_size": 21504,
+  "max_position_embeddings": 131072,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 168,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "rope_type": "linear"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 1024,
+  "sliding_window_pattern": 6,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 128,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 5376,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 16,
+    "query_pre_attn_scalar": 168,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  },
+  "vocab_size": 262208
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f29f0135dbabb68461757e57aea036f121a39e0e1bf844b2c04f484de44d7d0
+size 3797563736

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3abb59fb3791d4684c692bf3389b4f82f7947c795fefa8964b417577d68b7eb
+size 3765617568

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d5ec6a59cf696b4de5582893fb28aa878b7964d98153950bb19c0d78c83ef5
+size 3666571832

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6069c9919fbc61c7311246e95d610d0be2e886c8c3b5fff64af84e293cba4492
+size 3765617608

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb43f12a6f12521c08035e2c08358249b5aafe175faa7588b83208a73fd324a
+size 3666571896

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c36a42af2a4d90208c68201e0df281cfb70650bd1a94f8e25a988e5ea58923
+size 3765617624

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0fef1d7963f16432c54123552b20169aada5d1d8fcde921f11a7aebfaf4c55
+size 3666571896

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578b00231c27001ea8d92c4e3e7ee6b4ae15a47da049ed0717cd2e08831402d7
+size 3765617624

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5434dc7facbc32c1578e2d712b7ea9d6374ffed57d6929e568d55b46c0ac5b7
+size 3666571896

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83c58b0d91566a0f7de5a3b2f351ddde806132720a64ca917a70910d051de54
+size 3765617624

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2825663456adcd39fe600fedfa1bdb9feb26f26df4bd4a002768ef3aeb62e336
+size 3666571896

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1050fa3c446b907372d584c0514a3af42df16dcac0a9343aa839b02cf837d1f
+size 3765617624

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc1df870c38045592dfbf8e0be4e9e0e124a2756b5d8167f67f3724942d68e9
+size 3666571896

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b4a4d608a4c97d1e6b4ba7cc7837edcc1a11363aa4fc1bf55ced8e1f6575a2
+size 3765617624

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5be896bd5272e9bab554a16c729a9bc0bc79fb162e2bda3ae5a1d58ef08762c
+size 2708662040

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc4e5175c98bdedf44a9b12b28a0c369b0db9bc25a36b9b5469f0db5564e71b
+size 2819260560

preprocessor_config.json

@@ -0,0 +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

@@ -0,0 +1 @@
+   {"image_seq_length": 256, "processor_class": "Gemma3Processor"}  

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074