{
  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "bos_token_id": 31998,
  "eos_token_id": 31999,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 8196,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 12,
  "num_hidden_layers": 16,
  "num_key_value_heads": 6,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "factor": 1.0,
    "type": "linear"
  },
  "rope_theta": 10000.0,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.2",
  "use_cache": true,
  "vocab_size": 128256
}