arman-longformer-8k / config.json
hofarah's picture
Upload LongformerEncoderDecoderForConditionalGeneration
621d4c7
{
"_name_or_path": "/content/drive/MyDrive/university/Master Of Sience/2/deep learning with nlp/Text Summarization/LED/convert_model_to_long/arman_to_long/arman_8k/",
"activation_dropout": 0.1,
"activation_function": "relu",
"add_bias_logits": false,
"add_final_layer_norm": true,
"architectures": [
"LongformerEncoderDecoderForConditionalGeneration"
],
"attention_dilation": [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
],
"attention_dropout": 0.1,
"attention_probs_dropout_prob": 0.1,
"attention_window": [
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512,
512
],
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 0,
"dropout": 0.1,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 1,
"extra_pos_embeddings": 1,
"force_bos_token_to_be_generated": false,
"forced_eos_token_id": 1,
"gradient_checkpointing": false,
"init_std": 0.02,
"is_encoder_decoder": true,
"length_penalty": 0.8,
"max_decoder_position_embeddings": 512,
"max_encoder_position_embeddings": 8192,
"max_length": 256,
"max_position_embeddings": 8192,
"model_type": "pegasus",
"normalize_before": true,
"normalize_embedding": false,
"num_beams": 8,
"num_hidden_layers": 12,
"pad_token_id": 0,
"scale_embedding": true,
"static_position_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 96103
}