| { |
| "adapters": { |
| "adapters": { |
| "compacter_k8s": "73ee74d76d532be7" |
| }, |
| "config_map": { |
| "73ee74d76d532be7": { |
| "adapter_residual_before_ln": false, |
| "cross_adapter": false, |
| "dropout": 0.0, |
| "factorized_phm_W": true, |
| "factorized_phm_rule": false, |
| "hypercomplex_nonlinearity": "glorot-uniform", |
| "init_weights": "bert", |
| "init_weights_seed": null, |
| "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": 1, |
| "reduction_factor": 16, |
| "residual_before_ln": true, |
| "scaling": 1.0, |
| "shared_W_phm": false, |
| "shared_phm_rule": true, |
| "stochastic_depth": 0.0, |
| "use_gating": false |
| } |
| }, |
| "fusion_config_map": {}, |
| "fusion_name_map": {}, |
| "fusions": {} |
| }, |
| "architectures": [ |
| "T5ForConditionalGeneration" |
| ], |
| "bos_token_id": 1, |
| "classifier_dropout": 0.0, |
| "d_ff": 3072, |
| "d_kv": 64, |
| "d_model": 768, |
| "decoder_start_token_id": 0, |
| "dense_act_fn": "relu", |
| "dropout_rate": 0.1, |
| "eos_token_id": 2, |
| "feed_forward_proj": "relu", |
| "gradient_checkpointing": false, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_factor": 1.0, |
| "is_encoder_decoder": true, |
| "is_gated_act": false, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "t5", |
| "n_positions": 512, |
| "num_decoder_layers": 12, |
| "num_heads": 12, |
| "num_layers": 12, |
| "output_past": true, |
| "pad_token_id": 0, |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "task_specific_params": { |
| "summarization": { |
| "early_stopping": true, |
| "length_penalty": 2.0, |
| "max_length": 200, |
| "min_length": 30, |
| "no_repeat_ngram_size": 3, |
| "num_beams": 4, |
| "prefix": "summarize: " |
| }, |
| "translation_en_to_de": { |
| "early_stopping": true, |
| "max_length": 300, |
| "num_beams": 4, |
| "prefix": "translate English to German: " |
| }, |
| "translation_en_to_fr": { |
| "early_stopping": true, |
| "max_length": 300, |
| "num_beams": 4, |
| "prefix": "translate English to French: " |
| }, |
| "translation_en_to_ro": { |
| "early_stopping": true, |
| "max_length": 300, |
| "num_beams": 4, |
| "prefix": "translate English to Romanian: " |
| } |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "vocab_size": 32100 |
| } |
|
|