Upload model

config.json

@@ -1,182 +1,71 @@
-{
-  "_name_or_path": "PuppetLover/Title_generator",
-  "architectures": [
-    "EncoderDecoderModel"
-  ],
-  "decoder": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "vinai/phobert-base-v2",
-    "add_cross_attention": true,
-    "architectures": [
-      "RobertaForMaskedLM"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": true,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 258,
-    "min_length": 0,
-    "model_type": "roberta",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "position_embedding_type": "absolute",
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": "PhobertTokenizer",
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "type_vocab_size": 1,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 36340
-  },
-  "decoder_start_token_id": 0,
-  "early_stopping": null,
-  "encoder": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "vinai/phobert-base-v2",
-    "add_cross_attention": false,
-    "architectures": [
-      "RobertaForMaskedLM"
-    ],
-    "attention_probs_dropout_prob": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": null,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 258,
-    "min_length": 0,
-    "model_type": "roberta",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "position_embedding_type": "absolute",
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": "PhobertTokenizer",
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": "float32",
-    "torchscript": false,
-    "type_vocab_size": 1,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 36340
-  },
-  "eos_token_id": 2,
-  "is_encoder_decoder": true,
-  "length_penalty": null,
-  "max_length": null,
-  "model_type": "encoder-decoder",
-  "no_repeat_ngram_size": null,
-  "num_beams": null,
-  "pad_token_id": 2,
-  "tie_encoder_decoder": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
-  "vocab_size": 64001
-}
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "vinai/phobert-base-v2",
+    "add_cross_attention": true,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "classifier_dropout": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 258,
+    "model_type": "roberta",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "position_embedding_type": "absolute",
+    "tokenizer_class": "PhobertTokenizer",
+    "torch_dtype": "float32",
+    "type_vocab_size": 1,
+    "use_cache": true,
+    "vocab_size": 64001
+  },
+  "decoder_start_token_id": 0,
+  "early_stopping": null,
+  "encoder": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "vinai/phobert-base-v2",
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "classifier_dropout": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 258,
+    "model_type": "roberta",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "position_embedding_type": "absolute",
+    "tokenizer_class": "PhobertTokenizer",
+    "torch_dtype": "float32",
+    "type_vocab_size": 1,
+    "use_cache": true,
+    "vocab_size": 64001
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "length_penalty": null,
+  "max_length": null,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": null,
+  "num_beams": null,
+  "pad_token_id": 2,
+  "tie_encoder_decoder": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 64001
+}

generation_config.json

@@ -1,12 +1,12 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "length_penalty": 2.0,
-  "max_length": 64,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
-  "transformers_version": "4.49.0"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baccff8b469e9321a1dcbadf753e50cdb8e64173ec2ca5bdd0b017dce757b12b
-size 571042104
+oid sha256:e22bceb8efde6c16edab581d9b1011a4732e34e442006f2eb6fbb7899ee60a77
+size 656127340