def gpt_params(seq_len, vocab_size, d_model, num_heads, num_layers):
    """ Given GPT config calculate total number of parameters """
    ffw_size = 4*d_model # in GPT the number of intermediate features is always 4*d_model
    # token and position embeddings
    embeddings = d_model * vocab_size + d_model * seq_len
    # transformer blocks
    attention = 3*d_model**2 + 3*d_model # weights and biases
    attproj = d_model**2 + d_model
    ffw = d_model*(ffw_size) + ffw_size
    ffwproj = ffw_size*d_model + d_model
    layernorms = 2*2*d_model
    # dense
    ln_f = 2*d_model
    dense = d_model*vocab_size # note: no bias here
    # note: embeddings are not included in the param count!
    total_params = num_layers*(attention + attproj + ffw + ffwproj + layernorms) + ln_f + dense
    return total_params

#gpt2 = dict(seq_len = 1024, vocab_size = 50257, d_model = 768, num_heads = 12, num_layers = 12)
gpt2 = dict(seq_len = 256, vocab_size = 50259, d_model = 128, num_heads = 16, num_layers = 8)
result = gpt_params(**gpt2)/1e6
print(result) #Prints 8.019584