Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta_base_qa_onnx",
+  "_name_or_path": "microsoft/phi-2",
   "architectures": [
     "PhiForCausalLM"
   ],

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.2"
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed32f3280929a5a355b44d4fb2e42a38fbcd3d58ea769b044af4d360774fd1f
+size 1628979

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b530fa988b74eee7a9a874998f95ea2e5bf2dfe4bccf6eb62b2255997fd33418
+size 22237470720

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb904a32b7edfe037e89206228d729ccc0a46395476a96de38f3d7bf7909e8a5
+size 2784697161

quantize_config.json

@@ -0,0 +1,38 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Sub",
+                "Cast",
+                "Less",
+                "Add",
+                "ConstantOfShape",
+                "Concat",
+                "Reshape",
+                "Mul",
+                "MatMul",
+                "Shape",
+                "ReduceMean",
+                "Slice",
+                "Softmax",
+                "Neg",
+                "Transpose",
+                "Div",
+                "Where",
+                "Range",
+                "Unsqueeze",
+                "Squeeze",
+                "Equal",
+                "Gather",
+                "Pow",
+                "Tanh",
+                "Sqrt",
+                "Expand",
+                "Constant"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}