Upload folder using huggingface_hub

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "facebook/bart-large-xsum",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "eos_token_ids": [
+    2
+  ],
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 62,
+  "max_position_embeddings": 1024,
+  "min_length": 11,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 6,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 62,
+  "min_length": 11,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 6,
+  "pad_token_id": 1,
+  "transformers_version": "4.34.0.dev0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb0322cebe94cc57913ee8d209193e36d176df7dcb31377aa38190671af4e62
+size 1017091776

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34898789dfcbbc072dee4e75c4bb9f581b8ab88012185424ae08ceff906ba23
+size 1017574814

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535680b6ecc65fcdaebf1c6701688004b7cd33f01c01b35f0354438f86de41e7
+size 257435745

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c80421902dd755dccebbc30d0e9db5b5f0b959e79a23e952d7ea3d61d6b9cbe
+size 256677944

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764394c33210abe42a6cd210dc2ecd9f37133e6729ee0ee180740b26c60858d8
+size 916250419

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e56986e32eb7e72b106b4f6572305fc821a7bce4ab149d0278e2491fc9224858
+size 231158860

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78768cc2dca525b9cc8418d26025532fb246408d86990fbeed0094d33fdd3ef
+size 814942257

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b76633e637a65b021dad21df98b1dd1191808b8fd7ceb065ea9a4003c5a9a34
+size 205100092

quantize_config.json

@@ -0,0 +1,125 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Softmax",
+                "Sqrt",
+                "Slice",
+                "Squeeze",
+                "Reshape",
+                "ReduceMean",
+                "Equal",
+                "Transpose",
+                "MatMul",
+                "Expand",
+                "Mul",
+                "ConstantOfShape",
+                "Pow",
+                "Less",
+                "Cast",
+                "Constant",
+                "Gather",
+                "Range",
+                "Where",
+                "Unsqueeze",
+                "Add",
+                "Concat",
+                "Shape",
+                "Div",
+                "Erf",
+                "Sub"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Softmax",
+                "Sqrt",
+                "Reshape",
+                "ReduceMean",
+                "Equal",
+                "Transpose",
+                "MatMul",
+                "Expand",
+                "Mul",
+                "ConstantOfShape",
+                "Pow",
+                "Cast",
+                "Constant",
+                "Gather",
+                "Range",
+                "Where",
+                "Unsqueeze",
+                "Add",
+                "Concat",
+                "Shape",
+                "Div",
+                "Erf",
+                "Sub"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Softmax",
+                "Sqrt",
+                "Slice",
+                "Squeeze",
+                "Reshape",
+                "ReduceMean",
+                "Equal",
+                "Transpose",
+                "MatMul",
+                "Expand",
+                "Mul",
+                "ConstantOfShape",
+                "Pow",
+                "If",
+                "Less",
+                "Cast",
+                "Constant",
+                "Gather",
+                "Range",
+                "Where",
+                "Unsqueeze",
+                "Add",
+                "Concat",
+                "Shape",
+                "Div",
+                "Erf",
+                "Sub"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Softmax",
+                "Sqrt",
+                "Reshape",
+                "ReduceMean",
+                "Equal",
+                "Transpose",
+                "MatMul",
+                "Expand",
+                "Mul",
+                "ConstantOfShape",
+                "Pow",
+                "Cast",
+                "Constant",
+                "Gather",
+                "Range",
+                "Where",
+                "Unsqueeze",
+                "Add",
+                "Concat",
+                "Shape",
+                "Div",
+                "Erf",
+                "Sub"
+            ],
+            "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>"
+}