| { | |
| "config": { | |
| "architecture": "union", | |
| "configs": [ | |
| { | |
| "alpha": 1, | |
| "architecture": "lora", | |
| "attn_matrices": [ | |
| "q", | |
| "v" | |
| ], | |
| "composition_mode": "scale", | |
| "dropout": 0.0, | |
| "init_weights": "ia3", | |
| "intermediate_lora": true, | |
| "output_lora": false, | |
| "r": 1, | |
| "selfattn_lora": true, | |
| "use_gating": false | |
| }, | |
| { | |
| "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": true, | |
| "non_linearity": "swish", | |
| "original_ln_after": true, | |
| "original_ln_before": false, | |
| "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": 8, | |
| "residual_before_ln": true, | |
| "scaling": 1.0, | |
| "shared_W_phm": false, | |
| "shared_phm_rule": true, | |
| "use_gating": false | |
| } | |
| ] | |
| }, | |
| "hidden_size": 1024, | |
| "model_class": "T5ForConditionalGeneration", | |
| "model_name": "google/flan-t5-large", | |
| "model_type": "t5", | |
| "name": "question_answering_union", | |
| "version": "3.2.1" | |
| } |