Upload folder using huggingface_hub

README.md

@@ -17,7 +17,7 @@ tags:
 ---
 
 # mlx-community/gemma-3n-E2B-bf16
-This model was converted to MLX format from [`google/gemma-3n-E2B`]() using mlx-vlm version **0.3.0**.
+This model was converted to MLX format from [`google/gemma-3n-E2B`]() using mlx-vlm version **0.3.1**.
 Refer to the [original model card](https://huggingface.co/google/gemma-3n-E2B) for more details on the model.
 ## Use with mlx
 

config.json

@@ -63,9 +63,7 @@
         "task_specific_params": null,
         "problem_type": null,
         "_name_or_path": "",
-        "conf_positional_bias_size": 256,
         "model_type": "gemma3n_audio",
-        "sscp_conv_eps": 0.001,
         "input_feat_size": 128,
         "hidden_size": 1536,
         "rms_norm_eps": 1e-06,
@@ -224,9 +222,7 @@
         "task_specific_params": null,
         "problem_type": null,
         "_name_or_path": "",
-        "altup_lr_multiplier": 1.0,
         "model_type": "gemma3n_text",
-        "query_pre_attn_scalar": 256,
         "vocab_size": 262400,
         "vocab_size_per_layer_input": 262144,
         "max_position_embeddings": 32768,
@@ -358,7 +354,7 @@
     "top_k": 50,
     "top_p": 1.0,
     "torchscript": false,
-    "transformers_version": "4.53.1",
+    "transformers_version": "4.53.2",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "vision_config": {
@@ -420,7 +416,7 @@
         "model_type": "gemma3n_vision",
         "num_classes": 2,
         "initializer_range": 0.02,
-        "do_pooling": true,
+        "do_pooling": false,
         "model_args": null,
         "architecture": "mobilenetv5_300m_enc",
         "hidden_size": 2048,

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "top_k": 64,
   "top_p": 0.95,
-  "transformers_version": "4.53.0.dev0"
+  "transformers_version": "4.54.0.dev0"
 }

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3d16516dc964366023a7233fcc5d1d6845602a9df61821fd6ab3e0f167bf80
-size 5350795954
+oid sha256:ec694e0ebc5629f93194e9097406105fb920413d53f9321b8d0791c70f47fc73
+size 5350796197

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 5976833408,
-    "total_size": 10878876416
+    "total_parameters": 5976833472,
+    "total_size": 10878876544
   },
   "weight_map": {
     "model.audio_tower.conformer.0.attention.attn.k_proj.weight": "model-00001-of-00003.safetensors",
@@ -1553,6 +1553,7 @@
     "model.vision_tower.timm_model.blocks.3.9.layer_scale.gamma": "model-00001-of-00003.safetensors",
     "model.vision_tower.timm_model.blocks.3.9.norm.weight": "model-00001-of-00003.safetensors",
     "model.vision_tower.timm_model.conv_stem.bn.weight": "model-00001-of-00003.safetensors",
+    "model.vision_tower.timm_model.conv_stem.conv.bias": "model-00001-of-00003.safetensors",
     "model.vision_tower.timm_model.conv_stem.conv.weight": "model-00001-of-00003.safetensors",
     "model.vision_tower.timm_model.msfa.ffn.pw_exp.bn.weight": "model-00001-of-00003.safetensors",
     "model.vision_tower.timm_model.msfa.ffn.pw_exp.conv.weight": "model-00001-of-00003.safetensors",

preprocessor_config.json

@@ -41,7 +41,7 @@
   "processor_class": "Gemma3nProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "return_tensors": null,
   "sampling_rate": 16000,
   "size": {