Aligner

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -3,7 +3,6 @@
     "Gemma3ForConditionalGeneration"
   ],
   "boi_token_index": 255999,
-  "dtype": "bfloat16",
   "eoi_token_index": 256000,
   "eos_token_id": [
     1,
@@ -14,109 +13,28 @@
   "mm_tokens_per_image": 256,
   "model_type": "gemma3",
   "text_config": {
-    "_sliding_window_pattern": 6,
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "attn_logit_softcapping": null,
-    "final_logit_softcapping": null,
     "head_dim": 128,
-    "hidden_activation": "gelu_pytorch_tanh",
     "hidden_size": 5376,
-    "initializer_range": 0.02,
     "intermediate_size": 21504,
-    "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",
-      "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"
-    ],
-    "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,
-    "use_bidirectional_attention": false,
-    "use_cache": true,
-    "vocab_size": 262208
+    "sliding_window": 1024
   },
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.57.6",
   "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,
     "vision_use_head": false

generation_config.json

@@ -1,5 +1,6 @@
 {
   "bos_token_id": 2,
+  "cache_implementation": "hybrid",
   "do_sample": true,
   "eos_token_id": [
     1,

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"
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef
-size 33384722
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

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

tokenizer_config.json

@@ -51325,6 +51325,7 @@
   },
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
+  "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",
   "clean_up_tokenization_spaces": false,
   "eoi_token": "<end_of_image>",
   "eos_token": "<eos>",