config.json

{
  "architectures": [
    "GraniteMoeHybridForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_multiplier": 0.0078125,
  "bos_token_id": 100257,
  "dtype": "bfloat16",
  "embedding_multiplier": 12,
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.1,
  "intermediate_size": 512,
  "layer_types": [
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "mamba",
    "attention",
    "mamba",
    "mamba",
    "mamba",
    "mamba"
  ],
  "logits_scaling": 6,
  "mamba_chunk_size": 256,
  "mamba_conv_bias": true,
  "mamba_d_conv": 4,
  "mamba_d_head": 64,
  "mamba_d_state": 128,
  "mamba_expand": 2,
  "mamba_n_groups": 1,
  "mamba_n_heads": 48,
  "mamba_proj_bias": false,
  "max_position_embeddings": 131072,
  "model_type": "granitemoehybrid",
  "normalization_function": "rmsnorm",
  "num_attention_heads": 12,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 40,
  "num_key_value_heads": 4,
  "num_local_experts": 64,
  "output_router_logits": false,
  "pad_token_id": 100256,
  "position_embedding_type": "nope",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "strategy": "token",
          "symmetric": true,
          "type": "float"
        },
        "output_activations": null,
        "targets": [
          "Linear",
          "GraniteMoeHybridParallelExpertsLinear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "minmax",
          "observer_kwargs": {},
          "strategy": "channel",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.block_sparse_moe.router.layer",
      "model.layers.1.block_sparse_moe.router.layer",
      "model.layers.2.block_sparse_moe.router.layer",
      "model.layers.3.block_sparse_moe.router.layer",
      "model.layers.4.block_sparse_moe.router.layer",
      "model.layers.5.block_sparse_moe.router.layer",
      "model.layers.6.block_sparse_moe.router.layer",
      "model.layers.7.block_sparse_moe.router.layer",
      "model.layers.8.block_sparse_moe.router.layer",
      "model.layers.9.block_sparse_moe.router.layer",
      "model.layers.10.block_sparse_moe.router.layer",
      "model.layers.11.block_sparse_moe.router.layer",
      "model.layers.12.block_sparse_moe.router.layer",
      "model.layers.13.block_sparse_moe.router.layer",
      "model.layers.14.block_sparse_moe.router.layer",
      "model.layers.15.block_sparse_moe.router.layer",
      "model.layers.16.block_sparse_moe.router.layer",
      "model.layers.17.block_sparse_moe.router.layer",
      "model.layers.18.block_sparse_moe.router.layer",
      "model.layers.19.block_sparse_moe.router.layer",
      "model.layers.20.block_sparse_moe.router.layer",
      "model.layers.21.block_sparse_moe.router.layer",
      "model.layers.22.block_sparse_moe.router.layer",
      "model.layers.23.block_sparse_moe.router.layer",
      "model.layers.24.block_sparse_moe.router.layer",
      "model.layers.25.block_sparse_moe.router.layer",
      "model.layers.26.block_sparse_moe.router.layer",
      "model.layers.27.block_sparse_moe.router.layer",
      "model.layers.28.block_sparse_moe.router.layer",
      "model.layers.29.block_sparse_moe.router.layer",
      "model.layers.30.block_sparse_moe.router.layer",
      "model.layers.31.block_sparse_moe.router.layer",
      "model.layers.32.block_sparse_moe.router.layer",
      "model.layers.33.block_sparse_moe.router.layer",
      "model.layers.34.block_sparse_moe.router.layer",
      "model.layers.35.block_sparse_moe.router.layer",
      "model.layers.36.block_sparse_moe.router.layer",
      "model.layers.37.block_sparse_moe.router.layer",
      "model.layers.38.block_sparse_moe.router.layer",
      "model.layers.39.block_sparse_moe.router.layer",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.2.a20251002"
  },
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000,
  "router_aux_loss_coef": 0.0,
  "shared_intermediate_size": 1024,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0",
  "unsloth_fixed": true,
  "use_cache": true,
  "vocab_size": 100352
}