Adding Onnx

.gitattributes

@@ -1,3 +1,4 @@
+*.onnx filter=lfs diff=lfs merge=lfs -text
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "howdyaendra/xblock-large-patch2-224",
+  "_name_or_path": "howdyaendra/xblock-large-patch3-224",
   "_num_labels": 11,
   "architectures": [
     "ViTForImageClassification"
@@ -46,6 +46,5 @@
   "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.33.2"
 }

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:710946dd65108af1e4e30fff5935e07d6cd91e681e9a49fbe433459b31110831
+size 1213774922

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828c2fc83ea040a0fcfc347f251ebdb3600d074c4bcc4b582ce84873c77e5861
+size 306878201

quantize_config.json

@@ -0,0 +1,35 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Add",
+                "ReduceMean",
+                "Pow",
+                "Erf",
+                "ConstantOfShape",
+                "Slice",
+                "Sqrt",
+                "Concat",
+                "Equal",
+                "Shape",
+                "Transpose",
+                "Constant",
+                "Mul",
+                "Gemm",
+                "Expand",
+                "Unsqueeze",
+                "Where",
+                "Softmax",
+                "Sub",
+                "MatMul",
+                "Conv",
+                "Div",
+                "Gather",
+                "Reshape"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}