Upload folder using huggingface_hub

.gitattributes

@@ -34,4 +34,9 @@ saved_model/**/* 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
-ComfyUI_02427_.png filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

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

@@ -1,37 +1,62 @@
 {
   "architectures": [
-    "Gemma3ForCausalLM"
+    "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": 106,
-  "final_logit_softcapping": null,
-  "head_dim": 256,
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3840,
+  "image_token_index": 262144,
   "initializer_range": 0.02,
-  "intermediate_size": 15360,
-  "max_position_embeddings": 131072,
-  "model_type": "gemma3_text",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 48,
-  "num_key_value_heads": 8,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
   "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000.0,
-  "rope_scaling": {
-    "factor": 8.0,
-    "rope_type": "linear"
+  "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": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "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
   },
-  "rope_theta": 1000000.0,
-  "sliding_window": 1024,
-  "sliding_window_pattern": 6,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.50.0",
-  "use_cache": false,
-  "vocab_size": 262145
+  "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-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f84421f9d8fcac1095dd7308c7a83dc120047b7e9fe82c76be569736a8251d
-size 4939008360
+oid sha256:1d81af47f9085a53ec93c9753a9cc7f289ea6d88d5ed5769897fcc3673e07457
+size 4979902160

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beaf6195b325413298362c380706eeb107c6f7dfcb6905543c494acbf85d301a
-size 4931294512
+oid sha256:970a07d33a4b58765c06c17733170b025e5597ce003d2b19c6d0c5c281219b35
+size 4931296560

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced4802648a35604dc364d4f5c027dad27357e2b182a305f02092763aeb90097
-size 4931294512
+oid sha256:ddc091db1d0e176d0f9f403f529d286f66f9c5eaad266a259851c6f5a95dd9b4
+size 4931296624

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e96504623f1c41473b4a3bb4b5bc2df1a03aac1adb602ff7ce972c696e60a7
-size 4931294512
+oid sha256:6f79da97883ea1db154235414cbaae4398916fe8cc49179e0c29bfe962428292
+size 4931296624

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86cbdff64c30fd71049c9e4da569d992ee3421e54decc40362d10a538d4b3a62
-size 3798765600
+oid sha256:6dbbaa3ec46b178df7aa5736ccbfd9ce7395dfc933f333f472937f15730b3244
+size 4601000896

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"
+}