Add files using upload-large-folder tool

.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 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "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 +1,141 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "bos_token_id": 2,
+  "eoi_token_index": 256000,
+  "eos_token_id": 106,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection",
+      "vision_tower.vision_model.encoder.layers.23.self_attn",
+      "language_model.model.layers.5.mlp",
+      "vision_tower.vision_model.encoder.layers.26.self_attn",
+      "language_model.model.layers.4.mlp",
+      "language_model.model.layers.3.mlp",
+      "vision_tower.vision_model.encoder.layers.18.self_attn",
+      "vision_tower.vision_model.encoder.layers.19.self_attn",
+      "vision_tower.vision_model.encoder.layers.21.self_attn",
+      "language_model.model.layers.1.mlp",
+      "vision_tower.vision_model.encoder.layers.17.mlp",
+      "vision_tower.vision_model.encoder.layers.24.self_attn",
+      "vision_tower.vision_model.encoder.layers.21.mlp",
+      "vision_tower.vision_model.encoder.layers.19.mlp",
+      "vision_tower.vision_model.encoder.layers.24.mlp",
+      "vision_tower.vision_model.encoder.layers.20.self_attn",
+      "vision_tower.vision_model.encoder.layers.22.self_attn",
+      "vision_tower.vision_model.encoder.layers.20.mlp",
+      "vision_tower.vision_model.encoder.layers.25.mlp",
+      "language_model.model.layers.2.self_attn",
+      "vision_tower.vision_model.encoder.layers.17.self_attn",
+      "language_model.model.layers.0.mlp",
+      "vision_tower.vision_model.encoder.layers.16.mlp",
+      "vision_tower.vision_model.encoder.layers.23.mlp",
+      "vision_tower.vision_model.encoder.layers.22.mlp",
+      "vision_tower.vision_model.encoder.layers.13.mlp",
+      "vision_tower.vision_model.encoder.layers.15.mlp",
+      "vision_tower.vision_model.encoder.layers.18.mlp",
+      "vision_tower.vision_model.encoder.layers.16.self_attn",
+      "vision_tower.vision_model.encoder.layers.10.mlp",
+      "vision_tower.vision_model.encoder.layers.7.mlp",
+      "vision_tower.vision_model.encoder.layers.14.mlp",
+      "vision_tower.vision_model.encoder.layers.14.self_attn",
+      "vision_tower.vision_model.encoder.layers.9.mlp",
+      "vision_tower.vision_model.encoder.layers.12.mlp",
+      "vision_tower.vision_model.encoder.layers.15.self_attn",
+      "vision_tower.vision_model.encoder.layers.5.mlp",
+      "vision_tower.vision_model.encoder.layers.11.mlp",
+      "vision_tower.vision_model.encoder.layers.10.self_attn",
+      "vision_tower.vision_model.encoder.layers.8.mlp",
+      "vision_tower.vision_model.encoder.layers.8.self_attn",
+      "vision_tower.vision_model.encoder.layers.13.self_attn",
+      "vision_tower.vision_model.encoder.layers.12.self_attn",
+      "vision_tower.vision_model.encoder.layers.11.self_attn",
+      "vision_tower.vision_model.encoder.layers.4.mlp",
+      "vision_tower.vision_model.encoder.layers.4.self_attn",
+      "vision_tower.vision_model.encoder.layers.6.mlp",
+      "vision_tower.vision_model.encoder.layers.9.self_attn",
+      "vision_tower.vision_model.encoder.layers.2.mlp",
+      "vision_tower.vision_model.encoder.layers.7.self_attn",
+      "vision_tower.vision_model.encoder.layers.1.mlp",
+      "vision_tower.vision_model.encoder.layers.3.mlp",
+      "vision_tower.vision_model.encoder.layers.1.self_attn",
+      "vision_tower.vision_model.encoder.layers.5.self_attn",
+      "vision_tower.vision_model.encoder.layers.6.self_attn",
+      "vision_tower.vision_model.encoder.layers.3.self_attn",
+      "vision_tower.vision_model.encoder.layers.0.self_attn",
+      "vision_tower.vision_model.encoder.layers.2.self_attn",
+      "vision_tower.vision_model.encoder.layers.0.mlp",
+      "vision_tower.vision_model.encoder.layers.26.mlp"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "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",
+  "unsloth_fixed": 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
+  }
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb7283c0e0e8173641ec970b1374ca7b006350cfbe76c8518173cefecfcca4a
+size 4437712931

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "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 +1,4 @@
+{
+  "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": "<end_of_turn>",
+    "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