Upload MBartForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/BARTpho-finetuned-vi_to_vsl/checkpoint-800",
+  "_name_or_path": "/content/drive/MyDrive/BARTpho-finetuned-vi_to_vsl/checkpoint-4400",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [
@@ -8,17 +8,17 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
+  "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 6,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -26,12 +26,12 @@
   "is_encoder_decoder": true,
   "max_position_embeddings": 1024,
   "model_type": "mbart",
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
   "tokenizer_class": "BartphoTokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.1",
   "use_cache": true,
   "vocab_size": 40030
 }

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.32.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3456d8667ab83840be929e11009726620a0171e2163f44d1e85a29fcd8a23147
-size 1583588317
+oid sha256:a7f75012bc66f5954194cbcedf19a2cab347f5b941ef83efefbfb579cf006e29
+size 526498157