Init converted model

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "vinai/vinai-translate-en2vi-v2",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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,
+  "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,
+  "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": 1024,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "tokenizer_class": "MBartTokenizer",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 66773
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 1024,
+  "num_beams": 5,
+  "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 sha256:291ad084911f8c17624414f52c8df55ddcc684d882f59673c83034e95d908b91
+size 1084788703

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d87fcc832bd577b34cfdf698c77707ad98d59ef19461b0575380f7527145fa
+size 1085273533

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:346f44022b846ecb4890facd1f068d20b2fe2d9faa32d74e42c4af40e6397cf3
+size 274419740

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2e63b3854c09e9317fb44ba2857170b984d585a7fbaa116c15b2fe60d8fd6d
+size 273659676

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdc37d98c34dff7895e2c0ad27aecc7fdf16f61676a54d95fc4c7f105c2046a
+size 983947344

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94fd456c94e2b07ae2d341c0712081b04ab716fdb89a28d726a5a5562fcd959a
+size 248140667

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11edc600ffd184c8c451d78485bee3a6eacbca2057831d964c720b9ceff6156
+size 882572291

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d66b3430a72c0526bc9616f6580e02d152004aaaa7d3f753314ab6c7c82fa5e
+size 222015172

quantize_config.json

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbd2277deee13a943b702c0131ea9034d00c2288f332ee0c5fea520b07ea936
+size 1411795

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBartTokenizer",
+  "unk_token": "<unk>"
+}