config.json

{
  "architectures": [
    "GraniteMoeHybridForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_multiplier": 0.015625,
  "bos_token_id": 100257,
  "calibrate_all_experts": true,
  "dtype": "float16",
  "embedding_multiplier": 12,
  "eos_token_id": 100257,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.1,
  "intermediate_size": 8192,
  "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": 8,
  "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": 64,
  "mamba_proj_bias": false,
  "max_position_embeddings": 131072,
  "model_type": "granitemoehybrid",
  "normalization_function": "rmsnorm",
  "num_attention_heads": 32,
  "num_experts_per_tok": 0,
  "num_hidden_layers": 40,
  "num_key_value_heads": 8,
  "num_local_experts": 0,
  "output_router_logits": false,
  "pad_token_id": 100256,
  "position_embedding_type": "nope",
  "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": 4,
          "observer": "mse",
          "observer_kwargs": {},
          "strategy": "group",
          "symmetric": true,
          "type": "int"
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.12.1.dev0"
  },
  "residual_multiplier": 0.22,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000,
  "router_aux_loss_coef": 0.01,
  "shared_intermediate_size": 8192,
  "tie_word_embeddings": false,
  "transformers_version": "4.56.0",
  "use_cache": true,
  "vocab_size": 100352
}