Adding onnx model

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def6d28a63f3837de771f6c0237e3dea3e54bfa6c5e656c8ad837a2203ae4b46
+size 343401684

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5d0ce18a9b0d97d6acd2a5faae839229516b36351b3f0f9e90f548d1328b7c
+size 51450006

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e099f060fbaf7598d98bd69e7848bff8c5de376079844b66b3b8243db4c1ac8
+size 171801442

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159fae69f5eedd75ccd483a1c8bd71a0253ceae49cc3298ed85f2d56778ce951
+size 87333625

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef507d238dd96624d49352b410c86384be9e4439b5b9bc5babe459457958240c
+size 56757894

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3966047c4740713f077f7c81adba103c5968e307d13b23bd5474d2fab42c325d
+size 49718645

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dafb38d4c2fa357691b4c3cdf0568e397392c90c4f40e788aac56a87f2d6bb7
+size 87333625

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dafb38d4c2fa357691b4c3cdf0568e397392c90c4f40e788aac56a87f2d6bb7
+size 87333625

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}