m1-130M-mamba-CEFR-EN / config.json
fjmgAI's picture
Upload folder using huggingface_hub
b3b17b3 verified
Raw
History Blame Contribute Delete
298 Bytes
{
"d_model": 768,
"n_layer": 24,
"vocab_size": 50277,
"d_intermediate": 0,
"tie_embeddings": true,
"attn_cfg": {},
"attn_layer_idx": [],
"ssm_cfg": {},
"rms_norm": true,
"residual_in_fp32": true,
"fused_add_norm": true,
"pad_vocab_size_multiple": 8
}