{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": 128009,
  "ft_cfg": {
    "bf16": true,
    "continue_final_message": true,
    "dataset_name": "eekay/Llama-3.1-8B-Instruct-dragon-numbers",
    "gradient_accumulation_steps": 1,
    "learning_rate": 0.0002,
    "logging_steps": 100,
    "lora_layers": null,
    "lora_rank": 8,
    "lr_scheduler_type": "constant",
    "max_grad_norm": 1.0,
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "model_save_name": "Llama-3.1-8B-Instruct-dragon-numbers-ft",
    "n_examples": 30000,
    "num_train_epochs": 1,
    "per_device_train_batch_size": 16,
    "train_attn": true
  },
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 128256
}