Upload folder using huggingface_hub

config.json

@@ -10,7 +10,6 @@
     "conf_conv_kernel_size": 5,
     "conf_num_attention_heads": 8,
     "conf_num_hidden_layers": 12,
-    "conf_positional_bias_size": 256,
     "conf_reduction_factor": 4,
     "conf_residual_weight": 0.5,
     "gradient_clipping": 10000000000.0,
@@ -22,7 +21,6 @@
       128,
       32
     ],
-    "sscp_conv_eps": 0.001,
     "sscp_conv_group_norm_eps": 0.001,
     "sscp_conv_kernel_size": [
       [
@@ -61,7 +59,6 @@
   "image_token_id": 262145,
   "initializer_range": 0.02,
   "model_type": "gemma3n",
-  "pad_token_id": 0,
   "text_config": {
     "activation_sparsity_pattern": [
       0.95,
@@ -98,7 +95,6 @@
     "altup_active_idx": 0,
     "altup_coef_clip": 120.0,
     "altup_correct_scale": true,
-    "altup_lr_multiplier": 1.0,
     "altup_num_inputs": 4,
     "attention_bias": false,
     "attention_dropout": 0.0,
@@ -179,7 +175,6 @@
     "num_hidden_layers": 30,
     "num_key_value_heads": 2,
     "num_kv_shared_layers": 10,
-    "query_pre_attn_scalar": 256,
     "rms_norm_eps": 1e-06,
     "rope_local_base_freq": 10000.0,
     "rope_scaling": null,
@@ -191,11 +186,10 @@
     "vocab_size_per_layer_input": 262144
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.53.0",
-  "unsloth_fixed": true,
+  "transformers_version": "4.54.0.dev0",
   "vision_config": {
     "architecture": "mobilenetv5_300m_enc",
-    "do_pooling": true,
+    "do_pooling": false,
     "hidden_size": 2048,
     "initializer_range": 0.02,
     "label_names": [

generation_config.json

@@ -9,5 +9,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.53.0.dev0"
+  "transformers_version": "4.54.0.dev0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240c15d425fed506f48a0d267fd8bed4d8a4567b7b7907146a8ee561293d169c
+oid sha256:819c6c6e757dbc63ad931336cdd62373abafaf6944973e259ae18a1790cbecca
 size 3077103576

preprocessor_config.json

@@ -10,6 +10,7 @@
   "do_normalize": false,
   "do_rescale": true,
   "do_resize": true,
+  "feature_extractor_type": "Gemma3nAudioFeatureExtractor",
   "feature_size": 128,
   "fft_length": 1024,
   "fft_overdrive": true,
@@ -41,7 +42,7 @@
   "processor_class": "Gemma3nProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "return_tensors": null,
   "sampling_rate": 16000,
   "size": {

special_tokens_map.json

@@ -12,7 +12,7 @@
   "eoa_token": "<end_of_audio>",
   "eoi_token": "<end_of_image>",
   "eos_token": {
-    "content": "<end_of_turn>",
+    "content": "<eos>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
-size 33442553
+oid sha256:c4c19736bf24d1c6805cf49340e31bd02c70fb7857a2cb31065c90c2b5719c4e
+size 33442559

tokenizer_config.json

@@ -2160,7 +2160,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "256000": {
       "content": "<start_of_audio>",
@@ -2168,7 +2168,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "256001": {
       "content": "<unused99>",
@@ -51320,7 +51320,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "262145": {
       "content": "<image_soft_token>",
@@ -51328,7 +51328,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "262146": {
       "content": "<unused_image0>",
@@ -52344,7 +52344,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "262273": {
       "content": "<audio_soft_token>",
@@ -52352,7 +52352,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "262274": {
       "content": "<unused_audio0>",
@@ -53370,7 +53370,7 @@
   "clean_up_tokenization_spaces": false,
   "eoa_token": "<end_of_audio>",
   "eoi_token": "<end_of_image>",
-  "eos_token": "<end_of_turn>",
+  "eos_token": "<eos>",
   "extra_special_tokens": {
     "audio_token": "<audio_soft_token>",
     "boa_token": "<start_of_audio>",
@@ -53380,14 +53380,12 @@
     "image_token": "<image_soft_token>"
   },
   "image_token": "<image_soft_token>",
-  "model_max_length": 32768,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "left",
   "processor_class": "Gemma3nProcessor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
-  "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'] == 'audio' -%}\n                {{ '<audio_soft_token>' }}\n            {%- elif item['type'] == 'image' -%}\n                {{ '<image_soft_token>' }}\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"
-}
+  "use_default_system_prompt": false
+}