unipelt / config.json
dvssr's picture
Model save
5abd34e verified
{
"_name_or_path": "mse30/bart-base-finetuned-pubmed",
"activation_dropout": 0.1,
"activation_function": "gelu",
"adapters": {
"adapters": {
"unipelt": "0815dd75d5ff5808"
},
"config_map": {
"0815dd75d5ff5808": {
"architecture": "union",
"configs": [
{
"alpha": 8,
"architecture": "lora",
"attn_matrices": [
"q",
"v"
],
"composition_mode": "add",
"dropout": 0.0,
"init_weights": "lora",
"intermediate_lora": false,
"leave_out": [],
"output_lora": false,
"r": 8,
"selfattn_lora": true,
"use_gating": true
},
{
"architecture": "prefix_tuning",
"bottleneck_size": 512,
"cross_prefix": true,
"dropout": 0.0,
"encoder_prefix": true,
"flat": false,
"leave_out": [],
"non_linearity": "tanh",
"prefix_length": 10,
"shared_gating": true,
"use_gating": true
},
{
"adapter_residual_before_ln": false,
"cross_adapter": false,
"factorized_phm_W": true,
"factorized_phm_rule": false,
"hypercomplex_nonlinearity": "glorot-uniform",
"init_weights": "bert",
"inv_adapter": null,
"inv_adapter_reduction_factor": null,
"is_parallel": false,
"learn_phm": true,
"leave_out": [],
"ln_after": false,
"ln_before": false,
"mh_adapter": false,
"non_linearity": "relu",
"original_ln_after": true,
"original_ln_before": true,
"output_adapter": true,
"phm_bias": true,
"phm_c_init": "normal",
"phm_dim": 4,
"phm_init_range": 0.0001,
"phm_layer": false,
"phm_rank": 1,
"reduction_factor": 16,
"residual_before_ln": true,
"scaling": 1.0,
"shared_W_phm": false,
"shared_phm_rule": true,
"use_gating": true
}
]
}
},
"fusion_config_map": {},
"fusions": {}
},
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"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,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"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,
"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": "4.36.2",
"use_cache": true,
"vocab_size": 50265
}