inference/config.json

{
    "vocab_size": 129280,
    "dim": 4096,
    "moe_inter_dim": 2048,
    "n_layers": 43,
    "n_hash_layers": 3,
    "n_heads": 64,
    "n_routed_experts": 256,
    "n_shared_experts": 1,
    "n_activated_experts": 6,
    "score_func": "sqrtsoftplus",
    "route_scale": 1.5,
    "swiglu_limit": 10.0,
    "q_lora_rank": 1024,
    "head_dim": 512,
    "rope_head_dim": 64,
    "o_groups": 8,
    "o_lora_rank": 1024,
    "window_size": 128,
    "original_seq_len": 65536,
    "rope_theta": 10000,
    "rope_factor": 16,
    "beta_fast": 32,
    "beta_slow": 1,
    "index_n_heads": 64,
    "index_head_dim": 128,
    "index_topk": 512,
    "hc_mult": 4,
    "hc_sinkhorn_iters": 20,
    "dtype": "fp8",
    "scale_fmt": "ue8m0",
    "expert_dtype": "fp4",
    "compress_rope_theta": 160000,
    "compress_ratios": [0, 0, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 128, 4, 0]
}