|
{ |
|
"_name_or_path": "xlm-roberta-large", |
|
"adapters": { |
|
"adapters": { |
|
"myadapter": "779363b34fd3bd94" |
|
}, |
|
"config_map": { |
|
"779363b34fd3bd94": { |
|
"alpha": 16, |
|
"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": false |
|
} |
|
}, |
|
"fusion_config_map": {}, |
|
"fusions": {} |
|
}, |
|
"architectures": [ |
|
"XLMRobertaAdapterModel" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"bos_token_id": 0, |
|
"classifier_dropout": null, |
|
"eos_token_id": 2, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"id2label": null, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4096, |
|
"label2id": null, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 514, |
|
"model_type": "xlm-roberta", |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 24, |
|
"output_past": true, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
"prediction_heads": { |
|
"default": { |
|
"activation_function": "gelu", |
|
"bias": true, |
|
"embedding_size": 1024, |
|
"head_type": "masked_lm", |
|
"label2id": null, |
|
"layer_norm": true, |
|
"layers": 2, |
|
"shift_labels": false, |
|
"vocab_size": 250002 |
|
}, |
|
"myadapter": { |
|
"head_type": "PEThead", |
|
"id2tokenid": { |
|
"0": [ |
|
81793 |
|
], |
|
"1": [ |
|
35943 |
|
] |
|
}, |
|
"id2tokenid_values": [ |
|
35943, |
|
81793 |
|
], |
|
"vocab_size": 250002 |
|
} |
|
}, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.43.4", |
|
"type_vocab_size": 1, |
|
"use_cache": true, |
|
"vocab_size": 250002 |
|
} |
|
|