| { | |
| "name": "nirca-mini", | |
| "step": 123009, | |
| "tokens": 4612237558, | |
| "quant": "ternary", | |
| "quant_scope": "all", | |
| "n_experts": 32, | |
| "chat_format": "chatml", | |
| "bytes": 32638048, | |
| "parameters": 108815393, | |
| "cfg": { | |
| "vocab_size": 265, | |
| "d_model": 512, | |
| "n_head": 8, | |
| "d_ff": 1408, | |
| "block": 2048, | |
| "rope_theta": 10000.0, | |
| "tie_embeddings": true, | |
| "n_prelude": 2, | |
| "n_recur": 1, | |
| "n_coda": 0, | |
| "max_steps": 24, | |
| "pool_experts": 32, | |
| "pool_d_ff": 2048, | |
| "pool_top_k": 8, | |
| "pool_resident": 32, | |
| "pool_capacity_factor": 2.25, | |
| "pool_aux": 0.01, | |
| "pool_balance": 0.001, | |
| "min_steps": 1, | |
| "train_steps_mean": 8.0, | |
| "train_depth": "halt:8/2/1", | |
| "bptt_window": 24, | |
| "ponder_beta": 0.01, | |
| "halt_prior": 0.072, | |
| "halt_thresh": 0.9, | |
| "halt_freeze": true, | |
| "adam_moments": "bf16", | |
| "adam_beta2": 0.95, | |
| "use_pool": true, | |
| "pool_depth": 1, | |
| "pool_max": 32 | |
| } | |
| } | |