| { |
| "architectures": [ |
| "MetisMoRLMHeadModel" |
| ], |
| "model_type": "metis_mor_transformer", |
| "name": "Metis-1.4", |
| "architecture": "metis_mor_decoder", |
| "vocab_size": 16384, |
| "block_size": 1024, |
| "d_model": 1536, |
| "n_layer": 19, |
| "n_heads": 24, |
| "n_kv_heads": 8, |
| "head_dim": 64, |
| "intermediate_size": 4096, |
| "hidden_act": "swiglu", |
| "attn_cfg": {}, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "pad_token_id": 0, |
| "unk_token_id": 3, |
| "rms_norm": true, |
| "residual_in_fp32": false, |
| "fused_add_norm": false, |
| "pad_vocab_size_multiple": 16, |
| "tie_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "estimated_params": 503772163, |
| "attention_bias": false, |
| "mlp_bias": false, |
| "attention_dropout": 0.0, |
| "rope_theta": 10000.0, |
| "attention_backend": "flash_attention_3", |
| "fp8_pad_multiple": 16, |
| "mor_max_depth": 3, |
| "mor_router_hidden_dim": 256, |
| "mor_router_temperature": 1.0, |
| "mor_router_aux_loss_coef": 0.01, |
| "mor_target_avg_depth": 1.4, |
| "effective_layer_count": 57, |
| "target_effective_layer_count": 28.5, |
| "training_mode": "static_sequence_mor", |
| "mor_runtime_mode": "static_sequence", |
| "mor_enabled": true, |
| "mor_train_router": false, |
| "mor_depth2_capacity_sequences": 10, |
| "mor_depth3_capacity_sequences": 6, |
| "attention_mask_mode": "causal_none", |
| "disable_token_packing": true, |
| "disable_token_scatter": true, |
| "lm_loss_impl": "standard", |
| "te_fused_mlp": false |
| } |
|
|