Upload folder using huggingface_hub

config.json

@@ -0,0 +1,141 @@
+{
+  "architectures": [
+    "Gemma3nForConditionalGeneration"
+  ],
+  "audio_config": {
+    "conf_attention_chunk_size": 12,
+    "conf_attention_context_left": 13,
+    "conf_attention_context_right": 0,
+    "conf_attention_logit_cap": 50.0,
+    "conf_conv_kernel_size": 5,
+    "conf_num_attention_heads": 8,
+    "conf_num_hidden_layers": 12,
+    "conf_reduction_factor": 4,
+    "conf_residual_weight": 0.5,
+    "gradient_clipping": 10000000000.0,
+    "hidden_size": 1536,
+    "input_feat_size": 128,
+    "model_type": "gemma3n_audio",
+    "rms_norm_eps": 1e-06,
+    "sscp_conv_channel_size": [
+      128,
+      32
+    ],
+    "sscp_conv_group_norm_eps": 0.001,
+    "sscp_conv_kernel_size": [
+      [
+        3,
+        3
+      ],
+      [
+        3,
+        3
+      ]
+    ],
+    "sscp_conv_stride_size": [
+      [
+        2,
+        2
+      ],
+      [
+        2,
+        2
+      ]
+    ],
+    "torch_dtype": "float32",
+    "vocab_offset": 262272,
+    "vocab_size": 128
+  },
+  "audio_soft_tokens_per_image": 188,
+  "audio_token_id": 262273,
+  "boa_token_id": 256000,
+  "boi_token": "<start_of_image>",
+  "boi_token_id": 64401,
+  "bos_token_id": 1,
+  "eoa_token_id": 262272,
+  "eoi_token": "<end_of_image>",
+  "eoi_token_id": 64402,
+  "eos_token_id": 7,
+  "image_token": "<image_soft_token>",
+  "image_token_id": 64400,
+  "initializer_range": 0.02,
+  "model_type": "gemma3n",
+  "pad_token_id": 0,
+  "text_config": {
+    "architectures": [
+      "Lfm2ForCausalLM"
+    ],
+    "block_auto_adjust_ff_dim": true,
+    "block_dim": 2048,
+    "block_ff_dim": 12288,
+    "block_ffn_dim_multiplier": 1.0,
+    "block_mlp_init_scale": 1.0,
+    "block_multiple_of": 256,
+    "block_norm_eps": 1e-05,
+    "block_out_init_scale": 1.0,
+    "block_use_swiglu": true,
+    "block_use_xavier_init": true,
+    "bos_token_id": 2,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "conv_dim": 2048,
+    "conv_dim_out": 2048,
+    "conv_use_xavier_init": true,
+    "eos_token_id": 1,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+      "conv",
+      "conv",
+      "full_attention",
+      "conv",
+      "conv",
+      "full_attention",
+      "conv",
+      "conv",
+      "full_attention",
+      "conv",
+      "full_attention",
+      "conv",
+      "full_attention",
+      "conv",
+      "full_attention",
+      "conv"
+    ],
+    "max_position_embeddings": 128000,
+    "model_type": "lfm2",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 32,
+    "num_heads": 32,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 8,
+    "rope_theta": 1000000.0,
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "use_pos_enc": true,
+    "vocab_size": 64403
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "vision_config": {
+    "architecture": "mobilenetv5_300m_enc",
+    "do_pooling": false,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "label_names": [
+      "LABEL_0",
+      "LABEL_1"
+    ],
+    "model_args": null,
+    "model_type": "gemma3n_vision",
+    "num_classes": 2,
+    "rms_norm_eps": 1e-06,
+    "torch_dtype": "float32",
+    "vocab_offset": 262144,
+    "vocab_size": 128
+  },
+  "vision_soft_tokens_per_image": 256,
+  "vocab_size": 64403
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.54.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d0f810cd65290ffeed92619b2afcd17396e320c899726ab9e727394f814618
+size 4934196592

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3626fa9c02e6b3f36f3e9a58a651245e049847d1fac42cd22413e7c31b3df3
+size 3671141560