{ | |
"bos_token_id": 1, | |
"conv_size": 4, | |
"eos_token_id": 2, | |
"expand_k": 1, | |
"expand_v": 1, | |
"elementwise_affine": false, | |
"feature_map": "swish", | |
"fuse_cross_entropy": true, | |
"fuse_norm": true, | |
"gate_logit_normalizer": 4, | |
"hidden_act": "swish", | |
"hidden_ratio": 4, | |
"hidden_size": 1024, | |
"initializer_range": 0.006, | |
"intermediate_size": null, | |
"model_type": "gsa", | |
"num_heads": 4, | |
"num_hidden_layers": 24, | |
"num_slots": 64, | |
"norm_eps": 1e-06, | |
"share_conv_kernel": true, | |
"tie_word_embeddings": false, | |
"use_cache": true, | |
"use_norm": true, | |
"use_output_gate": true, | |
"use_rope": false, | |
"use_short_conv": false | |
} |