{ "architectures": [ "GraniteMoeHybridForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 0.015625, "bos_token_id": 100257, "torch_dtype": "float16", "embedding_multiplier": 12, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.1, "intermediate_size": 8192, "layer_types": [ "mamba", "mamba", "mamba", "mamba", "mamba", "attention", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "attention", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "attention", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "attention", "mamba", "mamba", "mamba", "mamba" ], "logits_scaling": 8, "mamba_chunk_size": 256, "mamba_conv_bias": true, "mamba_d_conv": 4, "mamba_d_head": 64, "mamba_d_state": 128, "mamba_expand": 2, "mamba_n_groups": 1, "mamba_n_heads": 64, "mamba_proj_bias": false, "max_position_embeddings": 131072, "model_type": "granitemoehybrid", "normalization_function": "rmsnorm", "num_attention_heads": 32, "num_experts_per_tok": 0, "num_hidden_layers": 40, "num_key_value_heads": 8, "num_local_experts": 0, "output_router_logits": false, "pad_token_id": 100256, "position_embedding_type": "nope", "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000, "router_aux_loss_coef": 0.01, "shared_intermediate_size": 8192, "tie_word_embeddings": true, "transformers_version": "4.56.2", "unsloth_fixed": true, "unsloth_version": "2025.10.7", "use_cache": true, "vocab_size": 100352 }