{
  "architectures": [
    "Lfm2MoeForCausalLM"
  ],
  "bos_token_id": 1,
  "conv_L_cache": 3,
  "conv_bias": false,
  "dtype": "bfloat16",
  "eos_token_id": 7,
  "hidden_size": 2048,
  "intermediate_size": 7168,
  "layer_types": [
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv",
    "full_attention",
    "conv",
    "conv"
  ],
  "max_position_embeddings": 128000,
  "model_type": "lfm2_moe",
  "moe_intermediate_size": 1792,
  "norm_eps": 1e-05,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_dense_layers": 2,
  "num_experts": 32,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 24,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 32,
          "num_bits": 8,
          "observer": "mse",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.conv.in_proj",
      "model.layers.0.conv.out_proj",
      "model.layers.0.feed_forward.w1",
      "model.layers.0.feed_forward.w3",
      "model.layers.0.feed_forward.w2",
      "model.layers.1.conv.in_proj",
      "model.layers.1.conv.out_proj",
      "model.layers.1.feed_forward.w1",
      "model.layers.1.feed_forward.w3",
      "model.layers.1.feed_forward.w2",
      "model.layers.2.self_attn.q_proj",
      "model.layers.2.self_attn.k_proj",
      "model.layers.2.self_attn.v_proj",
      "model.layers.2.self_attn.out_proj",
      "model.layers.2.feed_forward.gate",
      "model.layers.3.conv.in_proj",
      "model.layers.3.conv.out_proj",
      "model.layers.3.feed_forward.gate",
      "model.layers.4.conv.in_proj",
      "model.layers.4.conv.out_proj",
      "model.layers.4.feed_forward.gate",
      "model.layers.5.conv.in_proj",
      "model.layers.5.conv.out_proj",
      "model.layers.5.feed_forward.gate",
      "model.layers.6.self_attn.q_proj",
      "model.layers.6.self_attn.k_proj",
      "model.layers.6.self_attn.v_proj",
      "model.layers.6.self_attn.out_proj",
      "model.layers.6.feed_forward.gate",
      "model.layers.7.conv.in_proj",
      "model.layers.7.conv.out_proj",
      "model.layers.7.feed_forward.gate",
      "model.layers.8.conv.in_proj",
      "model.layers.8.conv.out_proj",
      "model.layers.8.feed_forward.gate",
      "model.layers.9.conv.in_proj",
      "model.layers.9.conv.out_proj",
      "model.layers.9.feed_forward.gate",
      "model.layers.10.self_attn.q_proj",
      "model.layers.10.self_attn.k_proj",
      "model.layers.10.self_attn.v_proj",
      "model.layers.10.self_attn.out_proj",
      "model.layers.10.feed_forward.gate",
      "model.layers.11.conv.in_proj",
      "model.layers.11.conv.out_proj",
      "model.layers.11.feed_forward.gate",
      "model.layers.12.conv.in_proj",
      "model.layers.12.conv.out_proj",
      "model.layers.12.feed_forward.gate",
      "model.layers.13.conv.in_proj",
      "model.layers.13.conv.out_proj",
      "model.layers.13.feed_forward.gate",
      "model.layers.14.self_attn.q_proj",
      "model.layers.14.self_attn.k_proj",
      "model.layers.14.self_attn.v_proj",
      "model.layers.14.self_attn.out_proj",
      "model.layers.14.feed_forward.gate",
      "model.layers.15.conv.in_proj",
      "model.layers.15.conv.out_proj",
      "model.layers.15.feed_forward.gate",
      "model.layers.16.conv.in_proj",
      "model.layers.16.conv.out_proj",
      "model.layers.16.feed_forward.gate",
      "model.layers.17.conv.in_proj",
      "model.layers.17.conv.out_proj",
      "model.layers.17.feed_forward.gate",
      "model.layers.18.self_attn.q_proj",
      "model.layers.18.self_attn.k_proj",
      "model.layers.18.self_attn.v_proj",
      "model.layers.18.self_attn.out_proj",
      "model.layers.18.feed_forward.gate",
      "model.layers.19.conv.in_proj",
      "model.layers.19.conv.out_proj",
      "model.layers.19.feed_forward.gate",
      "model.layers.20.conv.in_proj",
      "model.layers.20.conv.out_proj",
      "model.layers.20.feed_forward.gate",
      "model.layers.21.self_attn.q_proj",
      "model.layers.21.self_attn.k_proj",
      "model.layers.21.self_attn.v_proj",
      "model.layers.21.self_attn.out_proj",
      "model.layers.21.feed_forward.gate",
      "model.layers.22.conv.in_proj",
      "model.layers.22.conv.out_proj",
      "model.layers.22.feed_forward.gate",
      "model.layers.23.conv.in_proj",
      "model.layers.23.conv.out_proj",
      "model.layers.23.feed_forward.gate",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.1.dev0"
  },
  "rope_theta": 1000000.0,
  "routed_scaling_factor": 1.0,
  "tie_word_embeddings": false,
  "transformers_version": "5.0.0.dev0",
  "use_cache": true,
  "use_expert_bias": true,
  "vocab_size": 65536
}