config.json

{
  "model_type": "llama",
  "vocab_size": 33244,
  "hidden_size": 1024,
  "num_hidden_layers": 16,
  "num_attention_heads": 16,
  "num_key_value_heads": 4,
  "intermediate_size": 2816,
  "max_position_embeddings": 2048,
  "rms_norm_eps": 1e-6,
  "initializer_range": 0.02,
  "use_cache": true,
  "pad_token_id": 0,
  "bos_token_id": 2,
  "eos_token_id": 3,
  "tie_word_embeddings": false
}