| { | |
| "architectures": [ | |
| "EncoderDecoderModel" | |
| ], | |
| "decoder": { | |
| "_name_or_path": "skt/kogpt2-base-v2", | |
| "_num_labels": 1, | |
| "activation_function": "gelu_new", | |
| "add_cross_attention": true, | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "author": "Heewon Jeon(madjakarta@gmail.com)", | |
| "bos_token_id": 0, | |
| "created_date": "2021-04-28", | |
| "dtype": "float32", | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 1, | |
| "gradient_checkpointing": false, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_decoder": true, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "layer_norm_epsilon": 1e-05, | |
| "license": "CC-BY-NC-SA 4.0", | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": null, | |
| "n_layer": 12, | |
| "n_positions": 1024, | |
| "pad_token_id": 3, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "use_cache": true, | |
| "vocab_size": 51201 | |
| }, | |
| "decoder_start_token_id": 51200, | |
| "dtype": "float32", | |
| "encoder": { | |
| "_name_or_path": "snunlp/KR-FinBert-SC", | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "negative", | |
| "1": "neutral", | |
| "2": "positive" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "negative": 0, | |
| "neutral": 1, | |
| "positive": 2 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "position_embedding_type": "absolute", | |
| "problem_type": "single_label_classification", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 20000 | |
| }, | |
| "eos_token_id": 51200, | |
| "is_encoder_decoder": true, | |
| "model_type": "encoder-decoder", | |
| "pad_token_id": 51200, | |
| "transformers_version": "4.56.1", | |
| "vocab_size": 51201 | |
| } | |