Upload folder using huggingface_hub

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "vblagoje/bart_lfqa",
+  "_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,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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_position_embeddings": 1024,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64506de577f5270cc62d4043e90363d206b4d85055c84810e24757616559a73c
+size 1017137359

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a82f66eff1a639c093ef3ff900e67437a4acc4888c2c19dce4f8f2d5864cda7
+size 1017651574

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd51b3af2cbdff9d1f0e8de85fb84b77138a0e6097ea2ee49627330a3f321e8d
+size 257536382

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49949d756d0325411afad0cb7a07e9685f033bb56b9ad19f4baa15f0281690f
+size 256735888

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54856402faf7472d14e52302edf9889ec4c0b0c08902a1335da6337f9085ead9
+size 916285696

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6cb5532e893076c49ccfa4fca5f10e8b813fd901fbf4abd83d8b03b63ee4ff2
+size 231202581

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c593e4d0abb8f3cc593c3331e3b001f5f5bde39fe8e3ac4936973b7eb0acd0e
+size 814966601

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2953262e5e374ac848155d56f2d1e7b84e240852ed3574027fe492864d59a0d3
+size 205128906

quantize_config.json

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