(Trained with Unsloth)

config.json

@@ -0,0 +1,99 @@
+{
+    "architectures": [
+        "Gemma3ForConditionalGeneration"
+    ],
+    "boi_token_index": 255999,
+    "bos_token_id": 2,
+    "torch_dtype": "bfloat16",
+    "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,
+    "text_config": {
+        "_sliding_window_pattern": 6,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_logit_softcapping": null,
+        "cache_implementation": "hybrid",
+        "torch_dtype": "bfloat16",
+        "final_logit_softcapping": null,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2560,
+        "initializer_range": 0.02,
+        "intermediate_size": 10240,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention"
+        ],
+        "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,
+        "use_cache": true,
+        "vocab_size": 262208
+    },
+    "transformers_version": "4.56.2",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.10.4",
+    "vision_config": {
+        "attention_dropout": 0.0,
+        "torch_dtype": "bfloat16",
+        "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,
+        "vision_use_head": false
+    }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14053c1f3b38a060236792c0f799c08c2ce6e5f338e046bbf910069c8e53f382
-size 33384822
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer_config.json

@@ -51336,11 +51336,12 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 131072,
   "pad_token": "<pad>",
-  "padding_side": "right",
+  "padding_side": "left",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}
+  "use_default_system_prompt": false,
+  "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"
+}