config.json

{
  "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128009,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "model_type": "llama",
  "neuron": {
    "auto_cast_type": "fp16",
    "batch_size": 1,
    "checkpoint_id": "NousResearch/Meta-Llama-3-8B-Instruct",
    "checkpoint_revision": "cc55ce42f28d5264927b011938a45c71016ebbd0",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.13.72.0+78a426937",
    "num_cores": 2,
    "sequence_length": 1024,
    "task": "text-generation"
  },
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 128256
}