Upload 13 files

config.json

@@ -1,37 +1,60 @@
 {
   "architectures": [
-    "Gemma3ForCausalLM"
+    "Gemma3ForConditionalGeneration"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": null,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
   "eos_token_id": 1,
-  "final_logit_softcapping": null,
-  "head_dim": 256,
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 2560,
+  "image_token_index": 262144,
   "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,
-  "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000,
-  "rope_scaling": {
-    "factor": 8.0,
-    "rope_type": "linear"
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "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,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": false,
+    "vocab_size": 262208
   },
-  "rope_theta": 1000000,
-  "sliding_window": 1024,
-  "sliding_window_pattern": 6,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.3",
+  "transformers_version": "4.51.3",
   "use_cache": true,
-  "vocab_size": 262208
+  "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

@@ -7,5 +7,5 @@
   ],
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.52.3"
+  "transformers_version": "4.51.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27871ac0ee0bbc0568416fce9b5db8b288929de1364d85905cb777195e9933d
-size 4960531344
+oid sha256:7ba679363e38f5d88eb81d7002334ff5b00ced57842edaff45e962721152d9e9
+size 4961251752

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db8903141fa8991a75e1c724102131598f7fde4bdbde9c053e3dc4d1c53842c
-size 2800046672
+oid sha256:14f5587b851f4da83c9ab81c31c8c01fc6c93780fa061d76e599350008104c2f
+size 3639026128

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_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>",
@@ -51334,12 +51335,8 @@
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "max_length": null,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
   "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,