{ "architectures": [ "GraniteMoeForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "dtype": "float32", "embedding_multiplier": 1.0, "eos_token_id": 0, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 40, "is_decoder": true, "logits_scaling": 1.0, "max_position_embeddings": 512, "model_type": "granitemoe", "num_attention_heads": 4, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 4, "num_local_experts": 8, "output_router_logits": false, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "router_aux_loss_coef": 0.001, "tie_word_embeddings": false, "transformers_version": "5.16.0.dev0", "type_vocab_size": 16, "use_cache": true, "vocab_size": 49156 }