Switch model file to safetensors format

.gitignore

@@ -0,0 +1 @@
+backup/

README.md

@@ -9,13 +9,13 @@ tags:
 - materials-science
 - nffa-di
 base_model:
-- google/vit-base-patch16-224-in21k
+- google/vit-base-patch32-224-in21k
 pipeline_tag: image-classification
 ---
 
 # Vision Transformer for STM Multi-Tip Artifact Detection
 
-This is a fine-tuned **Vision Transformer (ViT-B/16)** model for classifying Scanning Tunneling Microscopy (STM) images. It is designed to detect the presence of **multi-tip artifacts**, a common distortion that results in duplicated signals and complicates data interpretation.
+This is a fine-tuned **Vision Transformer (ViT-B/32)** model for classifying Scanning Tunneling Microscopy (STM) images. It is designed to detect the presence of **multi-tip artifacts**, a common distortion that results in duplicated signals and complicates data interpretation.
 
 This model was developed as part of the **NFFA-DI (Nano Foundries and Fine Analysis Digital Infrastructure)** project, funded by the European Union's NextGenerationEU program.
 
@@ -23,7 +23,7 @@ This model was developed as part of the **NFFA-DI (Nano Foundries and Fine Analy
 
 ## Model Description 
 
-The model is a `ViT-B/16` pre-trained on ImageNet-21k. It was fine-tuned to classify an STM image as either `Artifact-Free` or `Multi-Tip Artifact`.
+The model is a `ViT-B/32` pre-trained on ImageNet-21k. It was fine-tuned to classify an STM image as either `Artifact-Free` or `Multi-Tip Artifact`.
 
 A key feature of this model is its use of a **Fast Fourier Transform (FFT)** based preprocessing method. The model's input is not a standard image but a 3-channel tensor composed of:
 1. The grayscale STM image.

config.json

@@ -1,16 +1,31 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "google/vit-base-patch32-224-in21k",
   "architectures": [
     "ViTForImageClassification"
   ],
-  "model_type": "vit",
-  "num_labels": 2,
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "Artifact-Free",
     "1": "Multi-Tip Artifact"
   },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Artifact-Free": 0,
     "Multi-Tip Artifact": 1
-  }
-}
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 32,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2"
+}

pytorch_model.bin → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3aaaf677542934b42ab898915c555d07337b4a904bd533eb6f50720a92f8d3
-size 343264618
+oid sha256:3b314f59f218e478a5f78cca820c95f0848da4f74ae7f55ffd1dbeabdbd3e5a5
+size 349850288