Upload config.json with huggingface_hub

config.json

@@ -1,28 +1,29 @@
 {
-  "activation_dropout": 0.1,
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classif_dropout": 0.1,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "dtype": "float32",
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 12,
   "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
   "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
@@ -40,28 +41,19 @@
   "max_position_embeddings": 1024,
   "model_type": "bart",
   "normalize_before": false,
-  "normalize_embedding": true,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
+  "prefix": " ",
   "scale_embedding": false,
   "task_specific_params": {
     "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
+      "early_stopping": true,
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
+      "no_repeat_ngram_size": 3,
       "num_beams": 4
-    },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
     }
   },
   "tie_word_embeddings": true,