| { |
| "architectures": [ |
| "LongcatCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_method": "MLA", |
| "bos_token_id": 1, |
| "cli_factor": 2, |
| "dsa_mtp_cli": true, |
| "eos_token_id": 2, |
| "expert_ffn_hidden_size": 2048, |
| "ffn_hidden_size": 12288, |
| "hidden_size": 8192, |
| "index_head_dim": 128, |
| "index_init_tokens": 16, |
| "index_k_norm_type": "rms", |
| "index_local_tokens": 1024, |
| "index_n_heads": 32, |
| "index_topk": 2048, |
| "kv_lora_rank": 512, |
| "max_position_embeddings": 262144, |
| "mla_scale_kv_lora": true, |
| "mla_scale_q_lora": true, |
| "model_type": "longcat2", |
| "moe_impl": "mix", |
| "moe_switch_token_num": 1024, |
| "moe_topk": 12, |
| "mtp_disable_over_tokenizer": true, |
| "mtp_num_layers": 3, |
| "mtp_replicate_modules": true, |
| "n_routed_experts": 768, |
| "num_attention_heads": 64, |
| "num_layers": 38, |
| "oe_neighbor_num": 5, |
| "oe_split_num": 4, |
| "oe_vocab_size_ratio": 100.567, |
| "q_lora_rank": 1536, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "quantization": { |
| "group_size": 64, |
| "bits": 3, |
| "mode": "affine", |
| "model.layers.0.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 3, |
| "mode": "affine", |
| "model.layers.0.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.1.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.2.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.3.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.4.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.5.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.6.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.7.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.8.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.9.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.10.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.11.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.12.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.13.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.14.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.15.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.16.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.17.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.18.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.19.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.20.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.21.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.22.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.23.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.24.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.25.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.26.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.27.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.28.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.29.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.30.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.31.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.32.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.33.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.34.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.35.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.36.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| }, |
| "model.layers.37.mlp.router.classifier": { |
| "group_size": 64, |
| "bits": 8 |
| } |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "original_max_position_embeddings": 8192, |
| "rope_type": "deepseek_yarn", |
| "factor": 120, |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "mscale": 1, |
| "mscale_all_dim": 1 |
| }, |
| "rope_theta": 1000000.0, |
| "routed_scaling_factor": 9, |
| "use_cache": true, |
| "use_mla": 1, |
| "v_head_dim": 128, |
| "vocab_size": 163840, |
| "zero_expert_num": 128, |
| "zero_expert_type": "identity" |
| } |
