cfg = GPTNeoXConfig(
    vocab_size = len(tokenizer),
    hidden_size = 768,
    intermediate_size = 768*4,
    num_hidden_layers = 12,
    num_attention_heads = 12,
    tie_word_embeddings = True,
    hidden_act = "gelu_new",
    tokenizer = "NeelNanda/gpt-neox-tokenizer-digits"
)