| { | |
| "n_q": 4, | |
| "card": 2048, | |
| "dim": 1536, | |
| "num_heads": 24, | |
| "num_layers": 48, | |
| "ffn_dim": 6144, | |
| "segment_duration": 30, | |
| "frame_rate": 50, | |
| "subcodes_context": 5, | |
| "span_len": 3, | |
| "sample_rate": 32000, | |
| "t5_name": "t5-base", | |
| "t5_dim": 768, | |
| "encodec_name": "encodec-32khz", | |
| "quantization": { | |
| "mode": "mlx_affine", | |
| "bits": 4, | |
| "group_size": 64, | |
| "targets": [ | |
| "self_attn.q_proj.weight", | |
| "self_attn.k_proj.weight", | |
| "self_attn.v_proj.weight", | |
| "self_attn.out_proj.weight", | |
| "cross_attn.q_proj.weight", | |
| "cross_attn.k_proj.weight", | |
| "cross_attn.v_proj.weight", | |
| "cross_attn.out_proj.weight", | |
| "linear1.weight", | |
| "linear2.weight" | |
| ] | |
| }, | |
| "format": "int4" | |
| } |