config.json

{
  "architectures": [
    "NemotronHForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
    "AutoModel": "modeling_nemotron_h.NemotronHForCausalLM",
    "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
  },
  "bos_token_id": 1,
  "chunk_size": 128,
  "conv_kernel": 4,
  "eos_token_id": 2,
  "expand": 2,
  "head_dim": 128,
  "hidden_dropout": 0.0,
  "hidden_size": 2688,
  "hybrid_override_pattern": "MEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEM*EMEMEMEM*EMEMEMEME",
  "initializer_range": 0.02,
  "intermediate_size": 1856,
  "layer_norm_epsilon": 1e-05,
  "mamba_head_dim": 64,
  "mamba_hidden_act": "silu",
  "mamba_num_heads": 64,
  "mamba_proj_bias": false,
  "mamba_ssm_cache_dtype": "float32",
  "max_position_embeddings": 262144,
  "mlp_bias": false,
  "mlp_hidden_act": "relu2",
  "model_type": "nemotron_h",
  "moe_intermediate_size": 1856,
  "moe_shared_expert_intermediate_size": 3712,
  "n_group": 1,
  "n_groups": 8,
  "n_routed_experts": 128,
  "n_shared_experts": 1,
  "norm_eps": 1e-05,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 52,
  "num_key_value_heads": 2,
  "num_logits_to_keep": 1,
  "pad_token_id": 0,
  "partial_rotary_factor": 1.0,
  "rescale_prenorm_residual": true,
  "residual_in_fp32": false,
  "rope_theta": 10000,
  "routed_scaling_factor": 2.5,
  "sliding_window": null,
  "ssm_state_size": 128,
  "tie_word_embeddings": false,
  "time_step_floor": 0.0001,
  "time_step_limit": [
    0.0,
    Infinity
  ],
  "time_step_max": 0.1,
  "time_step_min": 0.001,
  "topk_group": 1,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.4",
  "use_bias": false,
  "use_cache": true,
  "use_conv_bias": true,
  "use_mamba_kernels": true,
  "vocab_size": 131072
}