Upload model

config.json

@@ -1,27 +1,32 @@
 {
-  "activation_dropout": 0.0,
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
     "BartModel"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
+  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
-  "d_ff": 64,
-  "d_kv": 2,
-  "d_model": 16,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 24,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 2,
-  "decoder_start_token_id": 0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "dtype": "float32",
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 2,
+  "encoder_layers": 6,
   "eos_token_id": 2,
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -36,13 +41,34 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
-  "num_heads": 8,
-  "num_hidden_layers": 2,
-  "num_layers": 6,
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0.dev0",
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
-  "vocab_size": 50270
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57960e1016c1d2c3dcb3203703f21da17ca8deeb994e6df897d0ad03548917d
-size 5548584
+oid sha256:1e084613a2e5c4331736b335962f0ef2f5f4ca01be6bd55986c91ceafcebd1c8
+size 12454840