MambaSan-370m-instruct / config.json
loiccabannes's picture
model and tokenizer first upload
3ec46e9 verified
raw
history blame contribute delete
166 Bytes
{"d_model": 1024, "n_layer": 48, "vocab_size": 32000, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8}