config.json

{
  "architectures": [
    "NeoLLMForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_neollm.NeoLLMConfig",
    "AutoModel": "modeling_neollm.NeoLLMModel",
    "AutoModelForCausalLM": "modeling_neollm.NeoLLMForCausalLM"
  },
  "bos_token_id": 200004,
  "dropout_rate": 0.1,
  "dtype": "bfloat16",
  "eos_token_id": 200004,
  "fan_ratio": 0.125,
  "fan_ratio_ffn": 0.0625,
  "head_dim": 64,
  "hidden_act": "xielu",
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 32,
  "linear_num_key_heads": 8,
  "linear_num_value_heads": 16,
  "linear_value_head_dim": 32,
  "max_position_embeddings": 512,
  "model_type": "neollm",
  "num_attention_heads": 8,
  "num_hidden_layers": 12,
  "num_key_value_heads": 2,
  "pad_token_id": 200001,
  "partial_rotary_factor": 0.25,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "transformers_version": "4.57.3",
  "vocab_size": 200005
}