workshoplps / params.json
mkur0021
addmodel
05736eb
raw
history blame contribute delete
220 Bytes
{
"dim": 2048,
"ffn_dim_multiplier": 1.5,
"multiple_of": 256,
"n_heads": 32,
"n_kv_heads": 8,
"n_layers": 16,
"norm_eps": 1e-05,
"rope_theta": 500000.0,
"use_scaled_rope": true,
"vocab_size": 128256
}