{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "model_type": "llama",
  "vocab_size": 32000,
  "max_position_embeddings": 512,
  "hidden_size": 768,
  "intermediate_size": 2048,
  "num_hidden_layers": 11,
  "num_attention_heads": 12,
  "head_dim": 64,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "tie_word_embeddings": true,
  "hidden_act": "silu",
  "initializer_range": 0.02,
  "bos_token_id": 2,
  "eos_token_id": 3,
  "pad_token_id": 0,
  "torch_dtype": "bfloat16",
  "learnllm": {
    "vocab_size": 32000,
    "context_length": 512,
    "d_model": 768,
    "n_layers": 11,
    "n_heads": 12,
    "head_dim": null,
    "ffn_dim": 2048,
    "dropout": 0.0,
    "bias": false,
    "tie_embeddings": true,
    "norm_type": "rmsnorm",
    "norm_eps": 1e-05,
    "activation": "swiglu",
    "position_encoding": "rope",
    "rope_theta": 10000.0,
    "rope_scaling": null,
    "initializer_range": 0.02,
    "model_type": "llama",
    "architecture_note": "Learned from scratch; parameter names follow the Llama convention so transformers/PEFT/GGUF tools can consume it."
  }
}