{ "attention_type": "gqa", "dropout": 0.1, "hidden_dim": 768, "intermediate_dim": 2048, "kv_latent_dim": null, "max_seq_len": 128, "n_head": 12, "n_kv_head": 6, "n_layer": 12, "q_latent_dim": null, "rope_base": 10000.0, "use_rope": true, "vocab_size": 1024 }