Upload folder using huggingface_hub

.ipynb_checkpoints/ort_config-checkpoint.json

@@ -0,0 +1,35 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.11.0",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QDQ",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": true,
+    "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
+  },
+  "transformers_version": "4.29.0.dev0",
+  "use_external_data_format": true
+}

config.json

@@ -19,7 +19,8 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.31.0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.0.dev0",
   "use_cache": true,
   "vocab_size": 32000
 }

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210c6485f34cc1c35daa38072b29cb540c7dc7c04326cfd5b81c1429368398e3
-size 19045741
+oid sha256:31d4a369f653d2a017d0d3dac65c323f5367451cfdac16caad96916ac2af10c7
+size 19215765

onnx/decoder_model_merged_quantized.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d312201a36ec7d97cac2fc87c664ef0ec16a681f55ec013b9e3ce383904411e4
+oid sha256:a31b5bc42d63e7f6f344b80b1ea79fb67c734a70ecf47bcdb76c0ed23d19543d
 size 6739214336

onnx/ort_config.json

@@ -0,0 +1,35 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.11.0",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QDQ",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "MatMul",
+      "Attention",
+      "LSTM",
+      "Gather",
+      "Transpose",
+      "EmbedLayerNormalization"
+    ],
+    "per_channel": true,
+    "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
+  },
+  "transformers_version": "4.29.0.dev0",
+  "use_external_data_format": true
+}