Upload 2 files
Browse files- ort_config .json +47 -0
- quantized_config.json +28 -0
ort_config .json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"one_external_file": true,
|
| 3 |
+
"opset": null,
|
| 4 |
+
"optimization": {},
|
| 5 |
+
"optimum_version": "1.18.1",
|
| 6 |
+
"quantization": {
|
| 7 |
+
"activations_dtype": "QUInt8",
|
| 8 |
+
"activations_symmetric": false,
|
| 9 |
+
"format": "QDQ",
|
| 10 |
+
"is_static": true,
|
| 11 |
+
"mode": "QLinearOps",
|
| 12 |
+
"nodes_to_exclude": [],
|
| 13 |
+
"nodes_to_quantize": [],
|
| 14 |
+
"operators_to_quantize": [
|
| 15 |
+
"Conv",
|
| 16 |
+
"ConvTranspose",
|
| 17 |
+
"Gemm",
|
| 18 |
+
"Clip",
|
| 19 |
+
"Relu",
|
| 20 |
+
"Reshape",
|
| 21 |
+
"Transpose",
|
| 22 |
+
"Squeeze",
|
| 23 |
+
"Unsqueeze",
|
| 24 |
+
"Resize",
|
| 25 |
+
"MaxPool",
|
| 26 |
+
"AveragePool",
|
| 27 |
+
"MatMul",
|
| 28 |
+
"Split",
|
| 29 |
+
"Gather",
|
| 30 |
+
"Softmax",
|
| 31 |
+
"Where",
|
| 32 |
+
"InstanceNormalization",
|
| 33 |
+
"LayerNormalization"
|
| 34 |
+
],
|
| 35 |
+
"per_channel": false,
|
| 36 |
+
"qdq_add_pair_to_weight": false,
|
| 37 |
+
"qdq_dedicated_pair": false,
|
| 38 |
+
"qdq_op_type_per_channel_support_to_axis": {
|
| 39 |
+
"MatMul": 1
|
| 40 |
+
},
|
| 41 |
+
"reduce_range": false,
|
| 42 |
+
"weights_dtype": "QInt8",
|
| 43 |
+
"weights_symmetric": true
|
| 44 |
+
},
|
| 45 |
+
"transformers_version": "4.38.2",
|
| 46 |
+
"use_external_data_format": false
|
| 47 |
+
}
|
quantized_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/tmp/tmpxucq6v8k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.38.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 250002
|
| 28 |
+
}
|