| {"architectures": ["ScriptableCrammedBERT"], "num_transformer_layers": 16, "intermed_type": "fff", "hidden_size": 768, "intermed_size": 1, "intermed_depth": 11, "hidden_dropout_prob": 0.1, "norm": "LayerNorm", "norm_eps": 1e-12, "norm_scheme": "pre", "nonlin": "GELU", "tie_weights": true, "decoder_bias": false, "sparse_prediction": 0.25, "loss": "cross-entropy", "objective_layout": "MLM", "embedding": {"vocab_size": null, "pos_embedding": "scaled-sinusoidal", "dropout_prob": 0.1, "pad_token_id": 0, "max_seq_length": 128, "embedding_dim": 768, "normalization": true, "stable_low_precision": false}, "attention": {"type": "self-attention", "causal_attention": false, "num_attention_heads": 12, "dropout_prob": 0.1, "skip_output_projection": false, "qkv_bias": false, "rotary_embedding": false, "seq_op_in_fp32": false, "sequence_op": "torch-softmax"}, "init": {"type": "normal", "std": 0.02}, "ffn_layer_frequency": 1, "skip_head_transform": true, "use_bias": false, "final_norm": true, "num_labels": null, "classification_head": {"pooler": "avg", "include_ff_layer": true, "head_dim": 1024, "nonlin": "Tanh", "classifier_dropout": 0.1}} | |