{ "vocab_size": 32832, "n_layer": 24, "d_model": 1024, "arch": "hybrid", "attn_every": 4, "n_head": 16, "n_kv_head": 4, "head_dim": 128, "gdn_heads": 16, "gdn_head_dim": 128, "ffn_dim": 3584, "attnres_blocks": 8, "rope_theta": 10000.0, "max_seq_len": 4096, "softcap": 15.0, "grad_ckpt": false }