Upload 2 files

ort_config .json

@@ -0,0 +1,47 @@
+{
+  "one_external_file": true,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.18.1",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QDQ",
+    "is_static": true,
+    "mode": "QLinearOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "Conv",
+      "ConvTranspose",
+      "Gemm",
+      "Clip",
+      "Relu",
+      "Reshape",
+      "Transpose",
+      "Squeeze",
+      "Unsqueeze",
+      "Resize",
+      "MaxPool",
+      "AveragePool",
+      "MatMul",
+      "Split",
+      "Gather",
+      "Softmax",
+      "Where",
+      "InstanceNormalization",
+      "LayerNormalization"
+    ],
+    "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
+  },
+  "transformers_version": "4.38.2",
+  "use_external_data_format": false
+}

quantized_config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/tmp/tmpxucq6v8k",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}