{
  "architectures": [
    "Lfm2MoeForCausalLM"
  ],
  "bos_token_id": 1,
  "conv_L_cache": 3,
  "conv_bias": false,
  "dtype": "bfloat16",
  "eos_token_id": 7,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "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_name": "augment-multi-ft2/checkpoint-1000",
  "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": {
      "NVFP4A16": {
        "format": "nvfp4-pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 16,
          "num_bits": 4,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": "torch.float8_e4m3fn",
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "nvfp4-pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.embed_tokens",
      "lm_head",
      "re:.*norm.*",
      "re:.*gate$",
      "re:.*\\.conv\\..*",
      "re:^model\\.layers\\.0\\..*",
      "re:^model\\.layers\\.1\\..*",
      "re:^model\\.layers\\.23\\..*"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.14.0.1"
  },
  "rope_parameters": {
    "rope_theta": 1000000.0,
    "rope_type": "default"
  },
  "routed_scaling_factor": 1.0,
  "tie_word_embeddings": true,
  "transformers_version": "5.3.0",
  "unsloth_version": "2026.3.4",
  "use_cache": false,
  "use_expert_bias": true,
  "vocab_size": 65536
}