{
  "architectures": ["GPT"],
  "vocab_size": 8192,
  "n_layer": 6,
  "n_head": 8,
  "n_embd": 256,
  "n_inner": 1024,
  "n_positions": 512,
  "tie_word_embeddings": true,
  "bias": false,
  "norm": "rmsnorm",
  "activation": "gelu",
  "torch_dtype": "bfloat16",
  "model_type": "gpt2",
  "transformers_version": "4.40.0"
}