hrm-labs's picture patrickvonplaten's picture
Duplicate from mistralai/Mistral-Nemo-Instruct-2407
6ed57ea
Raw History Blame Contribute Delete
243 Bytes
{
"dim": 5120,
"n_layers": 40,
"head_dim": 128,
"hidden_dim": 14336,
"n_heads": 32,
"n_kv_heads": 8,
"norm_eps": 1e-05,
"vocab_size": 131072,
"rope_theta": 1000000.0,
"max_position_embeddings": 131072
}