| { | |
| "hidden_size": 2048, | |
| "intermediate_size": 8192, | |
| "hidden_act": "silu", | |
| "n_layer": 16, | |
| "mla_layers": [ | |
| 0, | |
| 5, | |
| 10, | |
| 14 | |
| ], | |
| "rms_norm_eps": 1e-05, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "kv_lora_rank": 128, | |
| "q_lora_rank": 1344, | |
| "use_lora_layer_norm": false, | |
| "use_fixed_rank_for_first_and_last_block": true, | |
| "use_full_kv_head": false, | |
| "layer_rank_list": {}, | |
| "qk_rope_head_dim": 32, | |
| "v_head_dim": 64, | |
| "qk_nope_head_dim": 32, | |
| "q_energy_ratio": null, | |
| "kv_energy_ratio": null, | |
| "qkv_rank_divisor": 8, | |
| "max_position_embeddings": 131072, | |
| "rope_theta": 500000.0, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "rope_type": "yarn", | |
| "d_model": 2048, | |
| "ssm_cfg": { | |
| "expand": 1, | |
| "ngroups": 32, | |
| "d_state": 64, | |
| "repeat_kv_before_conv": false | |
| }, | |
| "d_inner": 2048, | |
| "d_xb": 512 | |
| } | |