| { | |
| "model_type": "anka_rmw3", | |
| "architecture": "RMW3", | |
| "architectures": ["RMW3"], | |
| "parameter_count": 48944657, | |
| "vocab_size": 16384, | |
| "d_model": 512, | |
| "n_physical_layers": 13, | |
| "recurrent_passes": 2, | |
| "n_heads": 8, | |
| "n_kv_heads": 2, | |
| "d_ff": 1280, | |
| "reflect_rank": 32, | |
| "morph_rank": 368, | |
| "morph_stages": 4, | |
| "morph_experts": 4, | |
| "max_seq_len": 1024, | |
| "rope_theta": 10000.0, | |
| "norm_eps": 1e-05, | |
| "torch_dtype": "bfloat16", | |
| "tie_word_embeddings": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "pad_token_id": 0, | |
| "unk_token_id": 3 | |
| } | |