
GPT-2 released configurations resolved through hmdctr (hmgpt2)
Source:R/geron_w4a_native.R
morie_geron_gpt2.RdGPT-2 released configurations resolved through hmdctr (hmgpt2)
Examples
V <- c(1, 2, 3, 4, 5, 6, 7, 8)
morie_geron_gpt2(V)
#> $total_params
#> [1] 124439808
#>
#> $non_embedding_params
#> [1] 85056000
#>
#> $embedding_params
#> [1] 39383808
#>
#> $block_params
#> [1] 7087872
#>
#> $config
#> $config$vocab_size
#> [1] 50257
#>
#> $config$max_len
#> [1] 1024
#>
#> $config$n_layers
#> [1] 12
#>
#> $config$n_heads
#> [1] 12
#>
#> $config$d_model
#> [1] 768
#>
#>
#> $size
#> [1] "small"
#>
#> $d_head
#> [1] 64
#>
#> $params_vs_small
#> [1] 1
#>
#> $all_sizes
#> $all_sizes$small
#> [1] 124439808
#>
#> $all_sizes$medium
#> [1] 354823168
#>
#> $all_sizes$large
#> [1] 774030080
#>
#> $all_sizes$xl
#> [1] 1557611200
#>
#>
#> $mask
#> [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
#> [1,] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
#> [2,] FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
#> [3,] FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE
#> [4,] FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE
#> [5,] FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE
#> [6,] FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE
#> [7,] FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE
#> [8,] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
#>
#> $estimate
#> [1] 124439808
#>
#> $n
#> [1] 12
#>
#> $method
#> [1] "GPT-2 released configurations resolved through hmdctr, with scaling comparisons"
#>