draft_config.json

{
  "transformer_layer_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11264,
    "layer_types": [
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention",
      "sliding_attention"
    ],
    "max_position_embeddings": 262144,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 5,
    "num_key_value_heads": 2,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 1000000,
      "rope_type": "default"
    },
    "sliding_window": 2048,
    "tie_word_embeddings": false,
    "use_cache": true
  },
  "transformers_version": "5.9.0"
}