| { | |
| "_name_or_path": "./compacter-final", | |
| "adapters": { | |
| "adapters": { | |
| "orca": "e6dace882b5a44db" | |
| }, | |
| "config_map": { | |
| "e6dace882b5a44db": { | |
| "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": "gelu", | |
| "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": true, | |
| "phm_rank": 256, | |
| "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": [ | |
| "LlamaAdapterModel" | |
| ], | |
| "attention_bias": false, | |
| "bos_token_id": 32013, | |
| "custom_heads": {}, | |
| "eos_token_id": 32021, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5504, | |
| "label2id": null, | |
| "max_position_embeddings": 16384, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "prediction_heads": { | |
| "default": { | |
| "activation_function": null, | |
| "bias": false, | |
| "dropout_prob": null, | |
| "embedding_size": 2048, | |
| "head_type": "causal_lm", | |
| "label2id": null, | |
| "layer_norm": false, | |
| "layers": 1, | |
| "shift_labels": true, | |
| "vocab_size": 32256 | |
| } | |
| }, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 4.0, | |
| "type": "linear" | |
| }, | |
| "rope_theta": 100000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.35.2", | |
| "use_cache": true, | |
| "vocab_size": 32256 | |
| } | |