fixed onnx models

README.md

@@ -1,3 +0,0 @@
----
-license: mit
----

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/roberta_spam_onnx",
+  "_name_or_path": "mshenoda/roberta-spam",
   "architectures": [
     "RobertaForSequenceClassification"
   ],

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1caec77e221ec39fe677b7836d67cc3d1791da7b275da2957fe8e06fc507b8
-size 125560622
+oid sha256:804fff842b1aa8b6be84b7edd7d637e46de5825836ce44ef68eb0717c26401eb
+size 498929126

model.onnx → onnx/model_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1caec77e221ec39fe677b7836d67cc3d1791da7b275da2957fe8e06fc507b8
-size 125560622
+oid sha256:26ce7a8751f305708280b70d2fbbc6143aeceee68b39daf202c7064d1c08f20f
+size 206977448

model_quantized.onnx → onnx/model_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86293e47c297202d38d98dd78e172dfc2ac2b65456c35fa090c90119d45fe406
-size 125528143
+oid sha256:28e5e0b08fee7828d01f5206d2c4133e17a59d22af83c825f5cee67c54f862b2
+size 249634581

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a458427ec6698a6bbb97178179d533d3b109b79fdaf6bcdfb042db1d322798
+size 125871653

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07eb1ec785cdf605a91342afcbd7d4c352295929f078f3961e1fa3478f8b1fcf
+size 212285336

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cbcccccd763e14239b982405fd5b2897533557ae3e42919e98e7075386f767
+size 127551784

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86293e47c297202d38d98dd78e172dfc2ac2b65456c35fa090c90119d45fe406
-size 125528143
+oid sha256:b2a458427ec6698a6bbb97178179d533d3b109b79fdaf6bcdfb042db1d322798
+size 125871653

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361dffbe10a45dc8bc1c2678560eee86b1f76b86a9d2880d79ff856d5fa5869a
+size 125871652

ort_config.json

@@ -1,33 +0,0 @@
-{
-  "one_external_file": true,
-  "opset": null,
-  "optimization": {},
-  "quantization": {
-    "activations_dtype": "QUInt8",
-    "activations_symmetric": false,
-    "format": "QOperator",
-    "is_static": false,
-    "mode": "IntegerOps",
-    "nodes_to_exclude": [],
-    "nodes_to_quantize": [],
-    "operators_to_quantize": [
-      "Conv",
-      "MatMul",
-      "Attention",
-      "LSTM",
-      "Gather",
-      "Transpose",
-      "EmbedLayerNormalization"
-    ],
-    "per_channel": false,
-    "qdq_add_pair_to_weight": false,
-    "qdq_dedicated_pair": false,
-    "qdq_op_type_per_channel_support_to_axis": {
-      "MatMul": 1
-    },
-    "reduce_range": false,
-    "weights_dtype": "QInt8",
-    "weights_symmetric": true
-  },
-  "use_external_data_format": false
-}

quantize_config.json

@@ -0,0 +1,17 @@
+{
+    "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
+}