Upload 9 files

onnx/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 32128
+}

onnx/decoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d07dfadf10c8fe4fbfbef43b1e4603b26276a4c6b761235e05293ed61ef7419
-size 1899943049
+oid sha256:977ed19bda46c45ff550a99684b5a03b79501dc5f7ca9c0413de8e5f6ace094c
+size 1900001850

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17fa73a5763ce1472db7482c8f2123f308fdc4238d777ccfecbcb4411c415d32
-size 478997710
+oid sha256:6dbe3452d6a7734b24d7c69e1814930ed6152f507e871449f929c9d90077000d
+size 426079888

onnx/decoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0f65ab3d9b41705ab508e2bbbd6c44c0c6b78fb60b44d74f0c0aea28579dee
-size 477977453
+oid sha256:d1a5466b48370cd3ac5115cbaf11f4703d19a8d63fed645b603c71c87815c147
+size 476553495

onnx/decoder_with_past_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9228b8e3e66d6cee1a342a76e766525d1b9b4f37182b71fcf21e501a81b3cc3b
-size 1698480827
+oid sha256:31b6bf3ea2f35045728ab035263492c5cacdeaffb6682770b63decf00638f866
+size 1698604354

onnx/encoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06a07c9db4a1dc0acb489391ca1ab916b606ae446d666ac7adaaefde4e2f27e
-size 1365287559
+oid sha256:d02a1ea1fb82287e35577bd5b389186cc1f1364dcf19a511abd8ef87837a7bbe
+size 1365296185

onnx/encoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e549954378992e0dff8a3bccd0a39188f10da1ceb7ef97351e546489b843da9
-size 343223433
+oid sha256:9a2f7b64e965964bf84d23a19b71c9513b61c5196029853c2e9de9a061420de8
+size 342183032

onnx/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}

onnx/ort_config.json

@@ -0,0 +1,33 @@
+{
+  "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
+}