| { | |
| "architectures": [ | |
| "MetisMoRLMHeadModel" | |
| ], | |
| "model_type": "metis_multihead_latent_moe", | |
| "name": "Metis-1.5", | |
| "architecture": "metis_multihead_latent_moe_decoder", | |
| "vocab_size": 32768, | |
| "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": 950973312, | |
| "attention_bias": false, | |
| "mlp_bias": false, | |
| "attention_dropout": 0.0, | |
| "rope_theta": 10000.0, | |
| "attention_backend": "sdpa", | |
| "fp8_pad_multiple": 16, | |
| "mor_max_depth": 3, | |
| "mor_router_hidden_dim": 384, | |
| "mor_router_aux_loss_coef": 0.0, | |
| "mor_target_avg_depth": 1.0 | |
| } | |