Upload config.json with huggingface_hub

config.json

@@ -2,35 +2,47 @@
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "architectures": [
-    "MBartModel"
+    "T5EncoderModel"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
+  "dense_act_fn": "relu",
   "dropout": 0.1,
+  "dropout_rate": 0.1,
   "dtype": "float32",
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
+  "feed_forward_proj": "relu",
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "init_std": 0.02,
-  "is_encoder_decoder": true,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": false,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
   "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "num_hidden_layers": 12,
+  "model_type": "t5",
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 12,
   "pad_token_id": 1,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
   "scale_embedding": false,
   "tokenizer_class": "BartphoTokenizer",
   "transformers_version": "4.57.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 40030
 }