Add baseline image-classification model files

README.md

@@ -0,0 +1,6 @@
+---
+library_name: transformers
+pipeline_tag: image-classification
+---
+
+# StreetVision baseline submission

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/deit-tiny-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 192,
+  "id2label": {
+    "0": "no_roadwork",
+    "1": "roadwork"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "label2id": {
+    "no_roadwork": 0,
+    "roadwork": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 3,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c289ea698e000f8b0f26c5e3557864f303315206981ec7f7e5e018356ad072db
+size 22121920

model_card.json

@@ -1,7 +1,7 @@
 {
   "model_name": "mackom/sn72-tinyllama",
-  "description": "TinyLlama 1.1B Chat served via vLLM for SN72 mining.",
-  "version": "0.1.0",
+  "description": "Baseline StreetVision binary image classifier (starter submission).",
+  "version": "v0.0.2",
   "submitted_by": "5Cw2ryLWmcR5mAT9Tsc2fZskb63h2mVvhGuHmRmy1K5ktg3t",
-  "submission_time": 176642348864
-}
+  "submission_time": 176643226136
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}