| { |
| "model_type": "nested_byte_mamba2", |
| "architectures": ["ForwardBackwardRepairModel"], |
| "architecture": "byte_latent_mamba_nested_jsonl", |
| "vocab_size": 260, |
| "byte_offset": 4, |
| "special_token_ids": { |
| "pad": 0, |
| "bos": 1, |
| "eos": 2, |
| "unk": 3 |
| }, |
| "dim": 2000, |
| "layers": 26, |
| "fine_layers": 6, |
| "nested_layers": 20, |
| "tertiary_layers": 30, |
| "decoder_dim": 8000, |
| "position_bins": 8192, |
| "mamba_version": 2, |
| "mamba_d_state": 64, |
| "mamba2_headdim": 100, |
| "no_mamba": false, |
| "blt_min_patch_bytes": 1, |
| "blt_max_patch_bytes": 96, |
| "blt_patch_change_threshold": 48, |
| "blt_close_threshold": 0.98, |
| "blt_mid_close_bonus": 0.05, |
| "blt_short_pool_budget": 3000, |
| "blt_short_pool_window": 6000, |
| "blt_secondary_min_patch_bytes": 6, |
| "nested_pool_factor": 16, |
| "nested_min_pool_factor": 4, |
| "nested_close_threshold": 0.98, |
| "tertiary_pool_factor": 16, |
| "tertiary_min_pool_factor": 2, |
| "tertiary_close_threshold": 0.98, |
| "detach_inactive_coarse_gradients": true, |
| "decoder_pool_controller": true, |
| "pool_controller_alpha": 1.0, |
| "pool_controller_beta": 0.5, |
| "pool_controller_gamma": 1.0, |
| "recommended_precision": "bf16", |
| "recommended_placement": { |
| "fine_device": "cuda:0", |
| "nested_devices": ["cuda:1"], |
| "tertiary_device": "cuda:2" |
| } |
| } |
|
|
