| { |
| "architectures": [ |
| "K2HorizonForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_gate_func": "softplus", |
| "auto_map": { |
| "AutoConfig": "configuration_k2_horizon.K2HorizonConfig", |
| "AutoModel": "modeling_k2_horizon.K2HorizonModel", |
| "AutoModelForCausalLM": "modeling_k2_horizon.K2HorizonForCausalLM" |
| }, |
| "bos_token_id": 0, |
| "decoder_sparse_step": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 1, |
| 250019 |
| ], |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 6144, |
| "layernorm_num_groups": 2, |
| "max_position_embeddings": 524288, |
| "mlp_only_layers": [ |
| 0, |
| 1, |
| 2 |
| ], |
| "model_type": "k2_horizon", |
| "moe_gate_bias": true, |
| "moe_intermediate_size": 768, |
| "mova_num_experts": 64, |
| "mova_num_experts_per_tok": 4, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_experts": 100, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 8, |
| "num_shared_experts": 1, |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "quantization": { |
| "group_size": 64, |
| "bits": 6, |
| "mode": "affine", |
| "model.layers.3.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 6, |
| "mode": "affine", |
| "model.layers.3.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.38.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.39.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.40.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.41.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.42.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.43.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.44.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.45.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.46.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.self_attn.v_router": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.47.mlp.gate": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "query_key_norm": false, |
| "rms_norm_eps": 1e-06, |
| "rope_head_dim": 128, |
| "rope_parameters": { |
| "rope_theta": 10000000.0, |
| "rope_type": "default" |
| }, |
| "router_aux_loss_coef": 0.001, |
| "router_scaling_factor": 2.5, |
| "router_score_func": "sigmoid", |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.13.0", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 250624 |
| } |
