Upload BartForConditionalGeneration

config.json

@@ -1,34 +1,75 @@
 {
-  "_name_or_path": "model/patent_classifier",
+  "_name_or_path": "model/summarizer_myds_v9",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BartForConditionalGeneration"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classifier_dropout": null,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
-    "0": "LABEL_0"
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
   },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
   "label2id": {
-    "LABEL_0": 0
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "problem_type": "regression",
+  "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
+    }
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
-  "type_vocab_size": 1,
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -9,5 +9,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f10e82746330fddc98f2771f1c466f15338fe5e1cebf19f8561ecbf910557b8
-size 498609748
+oid sha256:eb70fdab00537437a55c30ea3fcc3124a24e59f72204ed7c10309247288dc1df
+size 557912620