{ "architectures": [ "SolonMoEForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_k_eq_v": true, "auto_map": { "AutoConfig": "modeling_solon_moe.SolonMoEConfig", "AutoModelForCausalLM": "modeling_solon_moe.SolonMoEForCausalLM" }, "bos_token_id": 2, "dtype": "bfloat16", "enable_moe_block": true, "eos_token_id": 1, "final_logit_softcapping": 30.0, "global_head_dim": 512, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 3840, "hidden_size_per_layer_input": 0, "initializer_range": 0.02, "intermediate_size": 15360, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 262144, "model_type": "solon_moe", "moe_intermediate_size": 15360, "moe_layers": [ 18, 19, 20, 21, 22, 24, 25, 26, 27, 28, 30, 31, 32, 33, 34 ], "num_attention_heads": 16, "num_experts": 4, "num_global_key_value_heads": 1, "num_hidden_layers": 48, "num_key_value_heads": 8, "num_kv_shared_layers": 0, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_parameters": { "full_attention": { "partial_rotary_factor": 0.25, "rope_theta": 1000000.0, "rope_type": "proportional" }, "sliding_attention": { "rope_theta": 10000.0, "rope_type": "default" } }, "sliding_window": 1024, "tie_word_embeddings": true, "top_k_experts": 2, "transformers_version": "5.12.1", "use_bidirectional_attention": null, "use_cache": true, "use_double_wide_mlp": false, "vocab_size": 262144, "vocab_size_per_layer_input": 262144 }