config.json

{
  "architectures": ["TinyStoriesGPT"],
  "d_model": 512,
  "n_layers": 16,
  "n_heads": 8,
  "ffn_dim": 2048,
  "vocab_size": 12288,
  "max_seq_len": 512,
  "tie_word_embeddings": true,
  "norm": "rmsnorm",
  "activation": "gelu",
  "attn": "causal",
  "dtype": "float32",
  "n_params": 56902144
}