{ "architectures": [ "GlmMoeDsaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "bfloat16", "eos_token_id": 2, "first_k_dense_replace": 1, "head_dim": 8, "hidden_act": "silu", "hidden_size": 64, "index_head_dim": 16, "index_n_heads": 4, "index_topk": 8, "indexer_types": [ "full", "shared", "full", "shared" ], "initializer_range": 0.02, "intermediate_size": 128, "kv_lora_rank": 16, "layer_types": [ "deepseek_sparse_attention", "deepseek_sparse_attention", "deepseek_sparse_attention", "deepseek_sparse_attention" ], "max_position_embeddings": 256, "mlp_bias": false, "mlp_layer_types": [ "dense", "sparse", "sparse", "sparse" ], "model_type": "glm_moe_dsa", "moe_intermediate_size": 32, "n_group": 1, "n_routed_experts": 8, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 4, "num_experts_per_tok": 2, "num_hidden_layers": 4, "num_key_value_heads": 4, "num_nextn_predict_layers": 0, "pad_token_id": 0, "q_lora_rank": 32, "qk_head_dim": 16, "qk_nope_head_dim": 8, "qk_rope_head_dim": 8, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "routed_scaling_factor": 2.5, "tie_word_embeddings": false, "topk_group": 1, "transformers_version": "5.16.1", "use_cache": true, "v_head_dim": 16, "vocab_size": 260 }