Upload 16 files

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "sana-ngu/t5-small-finetuned-summarize-scientific-articles",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

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": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d74e91bd9dbcc80435c607c298cc729c6f7940b0b7d71f553734218153ec79
+size 166670419

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0466b0590ef90b8a35110944fc4b85ef65ae007be704a494fd68f28296039078
+size 166832597

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9b973964b5628ab2e74f72f99372af3d1fa44dbde1588af6e31fe4ff0477d4
+size 42431407

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e03d0f80915ddfa8bcb2c26722dcb283f25d84aa70e1a71298f0e41bad2268f
+size 42154655

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b575adb682333d1915c478c3f60b1b3c2d4d30bbe006d0493f2cb03642f2525a
+size 154076559

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932f54c2fb84f71ca048120dfdedea2b4f42f6dc13aedf127cd228b0cc868b2d
+size 38952122

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec73af18e347bbb53ae58e20afff6cfc1d710f550d3ed134c32e921e74a5102b
+size 141404302

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ac87a380d93f717208962ac259e564a3dd7a503d6435c42c0345ee76da99fd
+size 35640019

quantize_config.json

@@ -0,0 +1,139 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Cast",
+                "Min",
+                "Gather",
+                "Where",
+                "Shape",
+                "Reshape",
+                "Range",
+                "Sqrt",
+                "LessOrEqual",
+                "Log",
+                "Expand",
+                "Div",
+                "Add",
+                "Slice",
+                "Unsqueeze",
+                "MatMul",
+                "ReduceMean",
+                "Relu",
+                "Softmax",
+                "Pow",
+                "Neg",
+                "Less",
+                "Constant",
+                "Tile",
+                "Mul",
+                "Transpose",
+                "Sub",
+                "ConstantOfShape",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Cast",
+                "Min",
+                "Gather",
+                "Where",
+                "Shape",
+                "Reshape",
+                "Range",
+                "Sqrt",
+                "LessOrEqual",
+                "Log",
+                "Expand",
+                "Div",
+                "Add",
+                "Unsqueeze",
+                "MatMul",
+                "ReduceMean",
+                "Relu",
+                "Softmax",
+                "Pow",
+                "Neg",
+                "Less",
+                "Constant",
+                "Tile",
+                "Mul",
+                "Transpose",
+                "Sub",
+                "ConstantOfShape",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Cast",
+                "Min",
+                "Gather",
+                "Where",
+                "Shape",
+                "Reshape",
+                "Range",
+                "Sqrt",
+                "Log",
+                "Greater",
+                "Div",
+                "Add",
+                "Unsqueeze",
+                "MatMul",
+                "Abs",
+                "ReduceMean",
+                "Relu",
+                "Softmax",
+                "Pow",
+                "Less",
+                "Constant",
+                "Mul",
+                "Transpose",
+                "Sub",
+                "ConstantOfShape",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Cast",
+                "Min",
+                "Gather",
+                "Where",
+                "Shape",
+                "Reshape",
+                "Range",
+                "Sqrt",
+                "LessOrEqual",
+                "Log",
+                "Expand",
+                "Div",
+                "Add",
+                "Slice",
+                "Unsqueeze",
+                "MatMul",
+                "ReduceMean",
+                "Relu",
+                "Softmax",
+                "Pow",
+                "Neg",
+                "Less",
+                "Constant",
+                "Tile",
+                "Mul",
+                "Transpose",
+                "Sub",
+                "If",
+                "ConstantOfShape",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}