first commit

README.md

@@ -0,0 +1 @@
+# mbart for 9-3

config.json

@@ -0,0 +1,49 @@
+{
+    "_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,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 3,
+    "dropout": 0.1,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 9,
+    "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": "mbart",
+    "normalize_before": true,
+    "normalize_embedding": true,
+    "task_specific_params": {},
+    "num_beams": 5,
+    "max_length": 1024,
+    "num_hidden_layers": 12,
+    "output_past": true,
+    "pad_token_id": 1,
+    "scale_embedding": true,
+    "static_position_embeddings": false,
+    "vocab_size": 57526
+  }

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245