{ "architectures": [ "RaptorForCausalLM" ], "auto_map": { "AutoConfig": "configuration_raptor.RaptorConfig", "AutoModelForCausalLM": "modeling_raptor.RaptorForCausalLM" }, "bos_token_id": 2, "dim": 1024, "dtype": "bfloat16", "eos_token_id": 3, "expert_hidden_dim": 2816, "gradient_checkpointing": false, "hidden_size": 1024, "latent_dim": 256, "load_balance_weight": 0.01, "max_position_embeddings": 2048, "max_seq_len": 2048, "model_type": "raptor", "moe_top_k": 2, "num_attention_heads": 16, "num_experts": 6, "num_heads": 16, "num_hidden_layers": 18, "num_layers": 18, "pad_token_id": 0, "rope_theta": 10000.0, "router_z_weight": 0.001, "transformers_version": "4.57.6", "vocab_size": 35000 }