Upload MBartForConditionalGeneration

config.json

@@ -1,28 +1,29 @@
 {
-  "_name_or_path": "facebook/bart-base",
-  "activation_dropout": 0.1,
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
   "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "add_final_layer_norm": true,
   "architectures": [
-    "BartForConditionalGeneration"
+    "MBartForConditionalGeneration"
   ],
-  "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,
   "early_stopping": null,
-  "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,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -38,37 +39,20 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "max_length": null,
   "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": null,
-  "normalize_before": false,
+  "model_type": "mbart",
+  "normalize_before": true,
   "normalize_embedding": true,
   "num_beams": null,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": 1,
-  "scale_embedding": false,
-  "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
-    }
-  },
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.45.1",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 250054
 }

generation_config.json

@@ -3,11 +3,10 @@
   "decoder_start_token_id": 2,
   "early_stopping": true,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "max_length": 200,
   "max_new_tokens": 16,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
+  "num_beams": 5,
   "pad_token_id": 1,
   "transformers_version": "4.45.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23d205f0e762d06e3df3cb19ce19e7c5a4d8ea3a6b96429630b445097f2fcf2
-size 557912620
+oid sha256:268b05f7cf509c0434c1927067ba2881f783308599d80b1f5addcd58cfc4f6af
+size 2444578688