diff --git a/config.json b/config.json new file mode 100644 index 0000000..cd1f7be --- /dev/null +++ b/config.json @@ -0,0 +1,53 @@ +{ + "activation_dropout": 0.0, + "architectures": null, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classif_dropout": 0.0, + "d_model": 1024, + "decoder_attention_heads": 16, + "decoder_ffn_dim": 4096, + "decoder_layerdrop": 0.0, + "decoder_layers": 12, + "do_sample": false, + "dropout": 0.1, + "encoder_attention_heads": 16, + "encoder_ffn_dim": 4096, + "encoder_layerdrop": 0.0, + "encoder_layers": 12, + "eos_token_id": 2, + "eos_token_ids": 0, + "finetuning_task": null, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1", + "2": "LABEL_2" + }, + "init_std": 0.02, + "is_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1, + "LABEL_2": 2 + }, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 1024, + "model_type": "bart", + "num_beams": 1, + "num_hidden_layers": 12, + "num_labels": 3, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_past": false, + "pad_token_id": 1, + "pruned_heads": {}, + "repetition_penalty": 1.0, + "temperature": 1.0, + "top_k": 50, + "top_p": 1.0, + "torchscript": false, + "use_bfloat16": false, + "vocab_size": 50264 +}