MERaLiON-2-10B-RotorQuant-MLX-2bit / adaptor_config.json
majentik's picture
Add MLX quantized model with KV cache compression
f87ab8d verified
raw
history blame contribute delete
82 Bytes
{
"speech_hidden_size": 1280,
"text_hidden_size": 3584,
"scale_factor": 15
}