{
  "architectures": [
    "AfmoeForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_afmoe.AfmoeConfig",
    "AutoModel": "modeling_afmoe.AfmoeModel",
    "AutoModelForCausalLM": "modeling_afmoe.AfmoeForCausalLM"
  },
  "dtype": "bfloat16",
  "global_attn_every_n_layers": 4,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "load_balance_coeff": 0.001,
  "max_position_embeddings": 131072,
  "model_type": "afmoe",
  "moe_intermediate_size": 256,
  "mup_enabled": true,
  "n_group": 1,
  "num_attention_heads": 8,
  "num_dense_layers": 2,
  "num_expert_groups": 1,
  "num_experts": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 56,
  "num_key_value_heads": 2,
  "num_limited_groups": 1,
  "num_shared_experts": 1,
  "quantization_config": {
    "config_groups": {
      "config_group_0": {
        "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": [
          "Linear"
        ],
        "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
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head",
      "model.embed_tokens",
      "re:model\\.layers\\.[0-9]+\\.mlp\\.router\\.gate"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "transform_config": {},
    "version": "0.15.1.a20260526"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000,
  "route_norm": true,
  "route_scale": 2.826,
  "score_func": "sigmoid",
  "sliding_window": 2048,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "use_grouped_mm": true,
  "vocab_size": 200192
}