| { |
| "architectures": [ |
| "Glm4MoeForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "pad_token_id": 151329, |
| "eos_token_id": [ |
| 151329, |
| 151336, |
| 151338 |
| ], |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "partial_rotary_factor": 0.5, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "max_position_embeddings": 202752, |
| "model_type": "glm4_moe", |
| "moe_intermediate_size": 1536, |
| "norm_topk_prob": true, |
| "num_attention_heads": 96, |
| "n_group": 1, |
| "topk_group": 1, |
| "n_routed_experts": 160, |
| "n_shared_experts": 1, |
| "routed_scaling_factor": 2.5, |
| "num_experts_per_tok": 8, |
| "first_k_dense_replace": 3, |
| "num_hidden_layers": 92, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 1000000, |
| "num_nextn_predict_layers": 1, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.54.0", |
| "use_cache": true, |
| "use_qk_norm": true, |
| "vocab_size": 151552 |
| } |
