configs/nano.json

{
  "model": {
    "vocab_size": 16384,
    "n_layers": 8,
    "n_heads": 8,
    "n_kv_heads": 2,
    "d_model": 512,
    "d_ffn": 2304,
    "max_seq_len": 1024,
    "rope_theta": 10000.0,
    "rms_eps": 1e-6,
    "init_std": 0.02,
    "dropout": 0.0,
    "tie_embeddings": true,
    "qk_norm": true,
    "z_loss_coef": 1e-4
  },
  "tokenizer": {
    "vocab_size": 16384,
    "model_type": "bpe",
    "character_coverage": 1.0,
    "byte_fallback": true,
    "normalization": "nmt_nfkc",
    "split_digits": true,
    "split_by_unicode_script": true,
    "add_dummy_prefix": true,
    "user_defined_symbols": [
      "<|pad|>", "<|bos|>", "<|eos|>", "<|unk|>", "<|sep|>",
      "<|system|>", "<|user|>", "<|assistant|>", "<|end|>",
      "<|tool_call|>", "<|/tool_call|>", "<|tool_result|>", "<|/tool_result|>",
      "<|cve|>", "<|cvss|>", "<|ioc|>", "<|ttp|>", "<|mitre|>", "<|kev|>",
      "<|exploit|>", "<|patch|>", "<|alert|>",
      "<|critical|>", "<|high|>", "<|medium|>", "<|low|>", "<|info|>"
    ],
    "balance": {
      "conversational_ratio": 0.5,
      "technical_ratio": 0.5
    }
  }
}