{ "architectures": [ "Glm4MoeLiteForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "dtype": "bfloat16", "eos_token_id": [ 154820, 154827, 154829 ], "first_k_dense_replace": 1, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 10240, "kv_lora_rank": 512, "max_position_embeddings": 202752, "mlp_layer_types": [ "dense", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse" ], "model_type": "glm4_moe_lite", "moe_intermediate_size": 1536, "n_group": 1, "n_routed_experts": 64, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 20, "num_experts_per_tok": 4, "num_hidden_layers": 47, "num_key_value_heads": 20, "num_nextn_predict_layers": 1, "pad_token_id": 154821, "partial_rotary_factor": 1.0, "pretraining_tp": 1, "q_lora_rank": 768, "qk_head_dim": 256, "qk_nope_head_dim": 192, "qk_rope_head_dim": 64, "quantization_config": { "config_groups": { "group_0": { "format": "float-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "scale_dtype": null, "strategy": "token", "symmetric": true, "type": "float", "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*self_attn\\.(q_a_proj|q_b_proj|kv_a_proj_with_mqa|kv_b_proj|o_proj)$", "re:.*lm_head", "re:.*layers\\.(1|39|46)\\.mlp\\.experts\\.\\d+\\.(gate|up|down)_proj$", "re:.*layers\\.(1|39|46)\\.mlp\\.shared_experts\\.(gate|up|down)_proj$", "re:.*layers\\.(1|39|46)\\.mlp\\.(gate|up|down)_proj$" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "channel", "symmetric": true, "type": "float", "zp_dtype": null } }, "group_1": { "format": "nvfp4-pack-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": "local", "group_size": 16, "num_bits": 4, "observer": "static_minmax", "observer_kwargs": {}, "scale_dtype": "torch.float8_e4m3fn", "strategy": "tensor_group", "symmetric": true, "type": "float", "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*mlp\\.experts\\.\\d+\\.(gate|up|down)_proj$", "re:.*mlp\\.shared_experts\\.(gate|up|down)_proj$", "re:.*mlp\\.(gate|up|down)_proj$" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 16, "num_bits": 4, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": "torch.float8_e4m3fn", "strategy": "tensor_group", "symmetric": true, "type": "float", "zp_dtype": null } } }, "format": "mixed-precision", "global_compression_ratio": null, "ignore": [ "model.layers.1.mlp.gate", "model.layers.2.mlp.gate", "model.layers.3.mlp.gate", "model.layers.4.mlp.gate", "model.layers.5.mlp.gate", "model.layers.6.mlp.gate", "model.layers.7.mlp.gate", "model.layers.8.mlp.gate", "model.layers.9.mlp.gate", "model.layers.10.mlp.gate", "model.layers.11.mlp.gate", "model.layers.12.mlp.gate", "model.layers.13.mlp.gate", "model.layers.14.mlp.gate", "model.layers.15.mlp.gate", "model.layers.16.mlp.gate", "model.layers.17.mlp.gate", "model.layers.18.mlp.gate", "model.layers.19.mlp.gate", "model.layers.20.mlp.gate", "model.layers.21.mlp.gate", "model.layers.22.mlp.gate", "model.layers.23.mlp.gate", "model.layers.24.mlp.gate", "model.layers.25.mlp.gate", "model.layers.26.mlp.gate", "model.layers.27.mlp.gate", "model.layers.28.mlp.gate", "model.layers.29.mlp.gate", "model.layers.30.mlp.gate", "model.layers.31.mlp.gate", "model.layers.32.mlp.gate", "model.layers.33.mlp.gate", "model.layers.34.mlp.gate", "model.layers.35.mlp.gate", "model.layers.36.mlp.gate", "model.layers.37.mlp.gate", "model.layers.38.mlp.gate", "model.layers.39.mlp.gate", "model.layers.40.mlp.gate", "model.layers.41.mlp.gate", "model.layers.42.mlp.gate", "model.layers.43.mlp.gate", "model.layers.44.mlp.gate", "model.layers.45.mlp.gate", "model.layers.46.mlp.gate", "re:^model.layers.47..*" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.17.2.a20260707" }, "rms_norm_eps": 1e-05, "rope_interleave": true, "rope_parameters": { "partial_rotary_factor": 1.0, "rope_theta": 1000000, "rope_type": "default" }, "routed_scaling_factor": 1.8, "scoring_func": "sigmoid", "tie_word_embeddings": false, "topk_group": 1, "topk_method": "noaux_tc", "transformers_version": "5.13.0", "unsloth_fixed": true, "use_cache": true, "v_head_dim": 256, "vocab_size": 154880 }