LibraMindMini / config.json
alby13's picture
Upload LibraMind Mini weights, tokenizer, and inference code
bcda938 verified
Raw History Blame Contribute Delete
343 Bytes
{
"vocab_size": 32832,
"n_layer": 24,
"d_model": 1024,
"arch": "hybrid",
"attn_every": 4,
"n_head": 16,
"n_kv_head": 4,
"head_dim": 128,
"gdn_heads": 16,
"gdn_head_dim": 128,
"ffn_dim": 3584,
"attnres_blocks": 8,
"rope_theta": 10000.0,
"max_seq_len": 4096,
"softcap": 15.0,
"grad_ckpt": false
}