Upload folder using huggingface_hub

README.md

@@ -15,47 +15,7 @@ This tiny model is for debugging. It is randomly initialized with the config ada
 ### Example usage:
 
 ```python
-import torch
-
-from transformers import pipeline
-
-model_id = "tiny-random/gemma-3n-dim4"
-pipe = pipeline(
-    task="image-text-to-text",
-    model=model_id,
-    device=0,
-    torch_dtype=torch.bfloat16
-)
-
-# temporary patch for audio tower
-from accelerate.hooks import ModelHook, add_hook_to_module
-
-class EnsureDtype(ModelHook):
-    def pre_forward(self, module, *args, **kwargs):
-        args = list(args)
-        args[0] = args[0].to(module.dtype)
-        return super().pre_forward(module, *args, **kwargs)
-add_hook_to_module(pipe.model.audio_tower, EnsureDtype())
-
-messages = [
-    {
-        "role": "system",
-        "content": [
-            {"type": "text", "text": "You are a helpful assistant."}
-        ]
-    },
-    {
-        "role": "user",
-        "content": [
-            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
-            # audio is buggy for now: bf16 x fp32
-            {"type": "audio", "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Audio/glass-breaking-151256.mp3"},
-            {"type": "text", "text": "Which image is cuter?"},
-        ]
-    },
-]
-result = pipe(messages, min_new_tokens=512, max_new_tokens=512, do_sample=True)
-print(result)
+{code_to_run.strip()}
 ```
 
 ### Codes to create this repo:

config.json

@@ -10,7 +10,6 @@
     "conf_conv_kernel_size": 5,
     "conf_num_attention_heads": 2,
     "conf_num_hidden_layers": 2,
-    "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": [
       [
@@ -71,7 +69,6 @@
     "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,
@@ -100,7 +97,6 @@
     "num_hidden_layers": 4,
     "num_key_value_heads": 1,
     "num_kv_shared_layers": 2,
-    "query_pre_attn_scalar": 256,
     "rms_norm_eps": 1e-06,
     "rope_local_base_freq": 10000.0,
     "rope_scaling": null,
@@ -115,7 +111,7 @@
   "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": [

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": {