{ "max_batch_size": 4, "max_seq_len": 65536, "dtype": "fp8", "scale_fmt": "ue8m0", "expert_dtype": "fp4", "scale_dtype": "fp8", "vocab_size": 129280, "dim": 128, "moe_inter_dim": 256, "n_layers": 7, "n_hash_layers": 3, "n_mtp_layers": 1, "n_heads": 8, "n_routed_experts": 32, "n_shared_experts": 1, "n_activated_experts": 6, "score_func": "sqrtsoftplus", "route_scale": 1.5, "swiglu_limit": 10.0, "q_lora_rank": 128, "head_dim": 128, "rope_head_dim": 64, "norm_eps": 1e-06, "o_groups": 8, "o_lora_rank": 128, "window_size": 128, "compress_ratios": [ 0, 0, 4, 128, 4, 128, 4, 0 ], "compress_rope_theta": 160000.0, "original_seq_len": 65536, "rope_theta": 10000.0, "rope_factor": 16.0, "beta_fast": 32, "beta_slow": 1, "index_n_heads": 4, "index_head_dim": 128, "index_topk": 512, "hc_mult": 4, "hc_sinkhorn_iters": 20, "hc_eps": 1e-06 }