| { | |
| "vocab_size": 32000, | |
| "hidden_size": 768, | |
| "n_heads": 12, | |
| "n_kv_heads": 4, | |
| "n_kv_groups": 3, | |
| "head_dim": 64, | |
| "n_layers": 12, | |
| "attention_bias": false, | |
| "intermediate_size": 3072, | |
| "mlp_bias": false, | |
| "eps": 1e-5, | |
| "dropout": 0.0, | |
| "max_position_embeddings": 2048, | |
| "pre_norm": true, | |
| "tie_weights": true, | |
| "max_seq_len": 2048 | |
| } |