{ "activation_function": "gelu_new", "architecture": "wayrappl_multilingual", "architectures": [ "WayraPPL" ], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "enable_language_head": false, "enable_lm_head": false, "eos_token_id": 50256, "initializer_range": 0.02, "intermediate_size": 1536, "layer_norm_epsilon": 1e-05, "model_type": "wayrappl", "n_embd": 384, "n_head": 12, "n_inner": 1536, "n_layer": 3, "n_positions": 2048, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "torch_dtype": "float32", "transformers_version": "4.53.2", "use_cache": true, "vocab_size": 128256 }