{
  "architectures": ["TransformerLM"],
  "model_type": "transformer_lm",
  "vocab_size": 40,
  "hidden_size": 256,
  "num_hidden_layers": 4,
  "num_attention_heads": 8,
  "intermediate_size": 1024,
  "max_position_embeddings": 64,
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "torch_dtype": "float32"
}