{ "architectures": [ "SolarOpenForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "dtype": "bfloat16", "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "max_position_embeddings": 4096, "model_type": "solar_open", "moe_intermediate_size": 512, "n_group": 1, "n_routed_experts": 16, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 16, "num_experts_per_tok": 4, "num_hidden_layers": 24, "num_key_value_heads": 4, "partial_rotary_factor": 1.0, "rms_norm_eps": 1e-05, "rope_parameters": { "factor": 2.0, "original_max_position_embeddings": 2048, "partial_rotary_factor": 1.0, "rope_theta": 1000000.0, "rope_type": "yarn" }, "routed_scaling_factor": 1.0, "tie_word_embeddings": false, "topk_group": 1, "transformers_version": "5.0.0.dev0", "use_cache": true, "use_qk_norm": false, "vocab_size": 196608 }