type: llamathree | |
context_length: 2048 | |
emb_dim: 256 | |
n_heads: 4 | |
n_layers: 6 | |
hidden_dim: 128 | |
hidden_activation: silu | |
n_kv_groups: 1 | |
rope_base: 50000 | |
rope_freq: null | |
dtype: float32 | |
vocab_size: 269 | |
type: llamathree | |
context_length: 2048 | |
emb_dim: 256 | |
n_heads: 4 | |
n_layers: 6 | |
hidden_dim: 128 | |
hidden_activation: silu | |
n_kv_groups: 1 | |
rope_base: 50000 | |
rope_freq: null | |
dtype: float32 | |
vocab_size: 269 | |