{"d_model": 768, "n_layer": 24, "vocab_size": 1035, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 1, "tie_embeddings": true} |
{"d_model": 768, "n_layer": 24, "vocab_size": 1035, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 1, "tie_embeddings": true} |