| { | |
| "_name_or_path": "google/flan-t5-large", | |
| "adapters": { | |
| "adapters": { | |
| "question_answering_union": "1f8ebc8c4a9631dd" | |
| }, | |
| "config_map": { | |
| "1f8ebc8c4a9631dd": { | |
| "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 | |
| } | |
| ] | |
| } | |
| }, | |
| "fusion_config_map": {}, | |
| "fusions": {} | |
| }, | |
| "architectures": [ | |
| "T5ForConditionalGeneration" | |
| ], | |
| "d_ff": 2816, | |
| "d_kv": 64, | |
| "d_model": 1024, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 24, | |
| "num_heads": 16, | |
| "num_layers": 24, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.26.1", | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| } | |