{
  "architectures": [
    "GlmMoeDsaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "dtype": "bfloat16",
  "eos_token_id": [
    154820,
    154827,
    154829
  ],
  "ep_size": 1,
  "first_k_dense_replace": 3,
  "head_dim": 192,
  "hidden_act": "silu",
  "hidden_size": 6144,
  "index_head_dim": 128,
  "index_n_heads": 32,
  "index_share_for_mtp_iteration": true,
  "index_skip_topk_offset": 3,
  "index_topk": 2048,
  "index_topk_freq": 4,
  "index_topk_pattern": null,
  "indexer_rope_interleave": true,
  "indexer_types": [
    "full",
    "full",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared",
    "full",
    "shared",
    "shared",
    "shared"
  ],
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "kv_lora_rank": 512,
  "max_position_embeddings": 1048576,
  "mlp_layer_types": [
    "dense",
    "dense",
    "dense",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse"
  ],
  "model_type": "glm_moe_dsa",
  "moe_intermediate_size": 2048,
  "moe_layer_freq": 1,
  "moe_router_dtype": "float32",
  "n_group": 1,
  "n_routed_experts": 256,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 64,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 78,
  "num_key_value_heads": 64,
  "num_nextn_predict_layers": 1,
  "pad_token_id": 154820,
  "pretraining_tp": 1,
  "q_lora_rank": 2048,
  "qk_head_dim": 256,
  "qk_nope_head_dim": 192,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "config_groups": {
      "linears": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": 128,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "re:^model\\.layers\\.[0-2]\\..*",
          "re:.*self_attn.*"
        ],
        "weights": {
          "actorder": null,
          "block_structure": [
            128,
            128
          ],
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "block",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      },
      "moe": {
        "format": "mxfp4-pack-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": 128,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "re:^model\\.layers\\.(?:[3-9]|[1-6][0-9]|7[0-8])\\..*mlp.*"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 4,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": "torch.uint8",
          "strategy": "group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "mixed-precision",
    "global_compression_ratio": null,
    "ignore": [
      "model.embed_tokens",
      "re:.*weights_proj.*",
      "re:.*mlp\\.gate$",
      "re:.*eh_proj.*",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "transform_config": {},
    "version": "0.17.2.dev32+g46196ce"
  },
  "rms_norm_eps": 1e-05,
  "rope_interleave": true,
  "rope_parameters": {
    "rope_theta": 8000000,
    "rope_type": "default"
  },
  "routed_scaling_factor": 2.5,
  "scoring_func": "sigmoid",
  "tie_word_embeddings": false,
  "topk_group": 1,
  "topk_method": "noaux_tc",
  "transformers_version": "5.12.0",
  "use_cache": true,
  "v_head_dim": 256,
  "vocab_size": 154880
}