add model

config.json

@@ -1,60 +1,46 @@
 {
-  "_name_or_path": "/home/ec2-user/SageMaker/marian_large",
+  "_name_or_path": "output/marian_large_bt_finetuned",
   "activation_dropout": 0.0,
-  "activation_function": "swish",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "activation_function": "relu",
   "architectures": [
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      62954
+      3
     ]
   ],
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 9,
-  "decoder_start_token_id": 62954,
-  "do_blenderbot_90_layernorm": false,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "decoder_vocab_size": 32000,
   "dropout": 0.1,
-  "encoder_attention_heads": 12,
+  "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 9,
-  "eos_token_id": 0,
-  "extra_pos_embeddings": 2,
-  "force_bos_token_to_be_generated": false,
-  "forced_eos_token_id": 0,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
   "max_length": 512,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 1024,
   "model_type": "marian",
-  "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": 6,
-  "num_hidden_layers": 9,
-  "pad_token_id": 62954,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 3,
   "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.12.0.dev0",
+  "transformers_version": "4.19.0.dev0",
   "use_cache": true,
-  "vocab_size": 62955
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dced33fde86920378b4a0189ee91983072e2d712154c1bc15dabc9463ea4dfa4
-size 902523465
+oid sha256:f41589ae763f571855cfba7e1da8198054e0e632aeb5083fec7832c1c2c2916e
+size 836716765