{
  "_name_or_path": "vietphuon/Llama-3.2-1B-Instruct-alpaca-then-quizgen-16bit",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "neuron": {
    "auto_cast_type": "fp16",
    "batch_size": 1,
    "checkpoint_id": "vietphuon/Llama-3.2-1B-Instruct-alpaca-then-quizgen-16bit",
    "checkpoint_revision": "a01e6bf5efa30f940147bf0f1d038e32af8d46d6",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.15.128.0+56dc5a86",
    "num_cores": 2,
    "sequence_length": 4096,
    "task": "text-generation"
  },
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pad_token_id": 128004,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "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": true,
  "torch_dtype": "float16",
  "transformers_version": "4.43.2",
  "unsloth_version": "2024.10.3",
  "use_cache": true,
  "vocab_size": 128256
}