| { | |
| "architectures": [ | |
| "GlmMoeDsaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 154820, | |
| 154827, | |
| 154829 | |
| ], | |
| "ep_size": 1, | |
| "first_k_dense_replace": 3, | |
| "hidden_act": "silu", | |
| "head_dim": 64, | |
| "hidden_size": 6144, | |
| "index_head_dim": 128, | |
| "index_n_heads": 32, | |
| "index_topk": 2048, | |
| "indexer_rope_interleave": true, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "kv_lora_rank": 512, | |
| "max_position_embeddings": 202752, | |
| "moe_intermediate_size": 2048, | |
| "moe_layer_freq": 1, | |
| "model_type": "glm_moe_dsa", | |
| "n_group": 1, | |
| "n_routed_experts": 256, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 64, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 78, | |
| "num_key_value_heads": 64, | |
| "num_nextn_predict_layers": 1, | |
| "pad_token_id": 154820, | |
| "pretraining_tp": 1, | |
| "q_lora_rank": 2048, | |
| "qk_head_dim": 256, | |
| "qk_nope_head_dim": 192, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-05, | |
| "rope_interleave": true, | |
| "rope_parameters": { | |
| "rope_theta": 1000000, | |
| "rope_type": "default" | |
| }, | |
| "routed_scaling_factor": 2.5, | |
| "scoring_func": "sigmoid", | |
| "tie_word_embeddings": false, | |
| "topk_group": 1, | |
| "topk_method": "noaux_tc", | |
| "transformers_version": "5.0.2.dev0", | |
| "use_cache": true, | |
| "v_head_dim": 256, | |
| "vocab_size": 154880 | |
| } | |