| { | |
| "architectures": [ | |
| "Glm4vMoeForConditionalGeneration" | |
| ], | |
| "model_type": "glm4v_moe", | |
| "text_config": { | |
| "pad_token_id": 151329, | |
| "vocab_size": 151552, | |
| "eos_token_id": [ | |
| 151329, | |
| 151336, | |
| 151338 | |
| ], | |
| "image_end_token_id": 151340, | |
| "image_start_token_id": 151339, | |
| "image_token_id": 151363, | |
| "head_dim": 128, | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "first_k_dense_replace": 1, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10944, | |
| "max_position_embeddings": 65536, | |
| "model_type": "glm4v_moe_text", | |
| "moe_intermediate_size": 1408, | |
| "n_group": 1, | |
| "n_routed_experts": 128, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 96, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 46, | |
| "num_key_value_heads": 8, | |
| "partial_rotary_factor": 0.5, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "model.language_model.layers.0.self_attn.q_proj", | |
| "model.language_model.layers.0.self_attn.k_proj", | |
| "model.language_model.layers.0.self_attn.v_proj", | |
| "model.language_model.layers.0.self_attn.o_proj", | |
| "model.language_model.layers.0.mlp.gate_proj", | |
| "model.language_model.layers.0.mlp.up_proj", | |
| "model.language_model.layers.0.mlp.down_proj", | |
| "model.language_model.layers.1.self_attn.q_proj", | |
| "model.language_model.layers.1.self_attn.k_proj", | |
| "model.language_model.layers.1.self_attn.v_proj", | |
| "model.language_model.layers.1.self_attn.o_proj", | |
| "model.language_model.layers.1.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.1.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.1.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.2.self_attn.q_proj", | |
| "model.language_model.layers.2.self_attn.k_proj", | |
| "model.language_model.layers.2.self_attn.v_proj", | |
| "model.language_model.layers.2.self_attn.o_proj", | |
| "model.language_model.layers.2.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.2.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.2.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.3.self_attn.q_proj", | |
| "model.language_model.layers.3.self_attn.k_proj", | |
| "model.language_model.layers.3.self_attn.v_proj", | |
| "model.language_model.layers.3.self_attn.o_proj", | |
| "model.language_model.layers.3.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.3.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.3.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.4.self_attn.q_proj", | |
| "model.language_model.layers.4.self_attn.k_proj", | |
| "model.language_model.layers.4.self_attn.v_proj", | |
| "model.language_model.layers.4.self_attn.o_proj", | |
| "model.language_model.layers.4.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.4.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.4.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.5.self_attn.q_proj", | |
| "model.language_model.layers.5.self_attn.k_proj", | |
| "model.language_model.layers.5.self_attn.v_proj", | |
| "model.language_model.layers.5.self_attn.o_proj", | |
| "model.language_model.layers.5.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.5.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.5.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.6.self_attn.q_proj", | |
| "model.language_model.layers.6.self_attn.k_proj", | |
| "model.language_model.layers.6.self_attn.v_proj", | |
| "model.language_model.layers.6.self_attn.o_proj", | |
| "model.language_model.layers.6.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.6.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.6.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.7.self_attn.q_proj", | |
| "model.language_model.layers.7.self_attn.k_proj", | |
| "model.language_model.layers.7.self_attn.v_proj", | |
| "model.language_model.layers.7.self_attn.o_proj", | |
| "model.language_model.layers.7.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.7.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.7.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.8.self_attn.q_proj", | |
| "model.language_model.layers.8.self_attn.k_proj", | |
| "model.language_model.layers.8.self_attn.v_proj", | |
| "model.language_model.layers.8.self_attn.o_proj", | |
| "model.language_model.layers.8.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.8.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.8.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.9.self_attn.q_proj", | |
| "model.language_model.layers.9.self_attn.k_proj", | |
| "model.language_model.layers.9.self_attn.v_proj", | |
| "model.language_model.layers.9.self_attn.o_proj", | |
| "model.language_model.layers.9.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.9.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.9.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.10.self_attn.q_proj", | |
| "model.language_model.layers.10.self_attn.k_proj", | |
| "model.language_model.layers.10.self_attn.v_proj", | |
| "model.language_model.layers.10.self_attn.o_proj", | |
| "model.language_model.layers.10.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.10.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.10.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.11.self_attn.q_proj", | |
| "model.language_model.layers.11.self_attn.k_proj", | |
| "model.language_model.layers.11.self_attn.v_proj", | |
| "model.language_model.layers.11.self_attn.o_proj", | |
| "model.language_model.layers.11.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.11.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.11.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.12.self_attn.q_proj", | |
| "model.language_model.layers.12.self_attn.k_proj", | |
| "model.language_model.layers.12.self_attn.v_proj", | |
| "model.language_model.layers.12.self_attn.o_proj", | |
| "model.language_model.layers.12.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.12.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.12.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.13.self_attn.q_proj", | |
| "model.language_model.layers.13.self_attn.k_proj", | |
| "model.language_model.layers.13.self_attn.v_proj", | |
| "model.language_model.layers.13.self_attn.o_proj", | |
| "model.language_model.layers.13.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.13.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.13.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.14.self_attn.q_proj", | |
| "model.language_model.layers.14.self_attn.k_proj", | |
| "model.language_model.layers.14.self_attn.v_proj", | |
| "model.language_model.layers.14.self_attn.o_proj", | |
| "model.language_model.layers.14.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.14.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.14.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.15.self_attn.q_proj", | |
| "model.language_model.layers.15.self_attn.k_proj", | |
| "model.language_model.layers.15.self_attn.v_proj", | |
| "model.language_model.layers.15.self_attn.o_proj", | |
| "model.language_model.layers.15.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.15.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.15.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.16.self_attn.q_proj", | |
| "model.language_model.layers.16.self_attn.k_proj", | |
| "model.language_model.layers.16.self_attn.v_proj", | |
| "model.language_model.layers.16.self_attn.o_proj", | |
| "model.language_model.layers.16.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.16.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.16.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.17.self_attn.q_proj", | |
| "model.language_model.layers.17.self_attn.k_proj", | |
| "model.language_model.layers.17.self_attn.v_proj", | |
| "model.language_model.layers.17.self_attn.o_proj", | |
| "model.language_model.layers.17.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.17.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.17.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.18.self_attn.q_proj", | |
| "model.language_model.layers.18.self_attn.k_proj", | |
| "model.language_model.layers.18.self_attn.v_proj", | |
| "model.language_model.layers.18.self_attn.o_proj", | |
| "model.language_model.layers.18.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.18.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.18.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.19.self_attn.q_proj", | |
| "model.language_model.layers.19.self_attn.k_proj", | |
| "model.language_model.layers.19.self_attn.v_proj", | |
| "model.language_model.layers.19.self_attn.o_proj", | |
| "model.language_model.layers.19.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.19.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.19.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.20.self_attn.q_proj", | |
| "model.language_model.layers.20.self_attn.k_proj", | |
| "model.language_model.layers.20.self_attn.v_proj", | |
| "model.language_model.layers.20.self_attn.o_proj", | |
| "model.language_model.layers.20.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.20.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.20.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.21.self_attn.q_proj", | |
| "model.language_model.layers.21.self_attn.k_proj", | |
| "model.language_model.layers.21.self_attn.v_proj", | |
| "model.language_model.layers.21.self_attn.o_proj", | |
| "model.language_model.layers.21.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.21.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.21.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.22.self_attn.q_proj", | |
| "model.language_model.layers.22.self_attn.k_proj", | |
| "model.language_model.layers.22.self_attn.v_proj", | |
| "model.language_model.layers.22.self_attn.o_proj", | |
| "model.language_model.layers.22.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.22.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.22.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.23.self_attn.q_proj", | |
| "model.language_model.layers.23.self_attn.k_proj", | |
| "model.language_model.layers.23.self_attn.v_proj", | |
| "model.language_model.layers.23.self_attn.o_proj", | |
| "model.language_model.layers.23.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.23.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.23.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.24.self_attn.q_proj", | |
| "model.language_model.layers.24.self_attn.k_proj", | |
| "model.language_model.layers.24.self_attn.v_proj", | |
| "model.language_model.layers.24.self_attn.o_proj", | |
| "model.language_model.layers.24.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.24.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.24.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.25.self_attn.q_proj", | |
| "model.language_model.layers.25.self_attn.k_proj", | |
| "model.language_model.layers.25.self_attn.v_proj", | |
| "model.language_model.layers.25.self_attn.o_proj", | |
| "model.language_model.layers.25.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.25.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.25.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.26.self_attn.q_proj", | |
| "model.language_model.layers.26.self_attn.k_proj", | |
| "model.language_model.layers.26.self_attn.v_proj", | |
| "model.language_model.layers.26.self_attn.o_proj", | |
| "model.language_model.layers.26.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.26.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.26.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.27.self_attn.q_proj", | |
| "model.language_model.layers.27.self_attn.k_proj", | |
| "model.language_model.layers.27.self_attn.v_proj", | |
| "model.language_model.layers.27.self_attn.o_proj", | |
| "model.language_model.layers.27.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.27.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.27.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.28.self_attn.q_proj", | |
| "model.language_model.layers.28.self_attn.k_proj", | |
| "model.language_model.layers.28.self_attn.v_proj", | |
| "model.language_model.layers.28.self_attn.o_proj", | |
| "model.language_model.layers.28.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.28.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.28.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.29.self_attn.q_proj", | |
| "model.language_model.layers.29.self_attn.k_proj", | |
| "model.language_model.layers.29.self_attn.v_proj", | |
| "model.language_model.layers.29.self_attn.o_proj", | |
| "model.language_model.layers.29.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.29.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.29.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.30.self_attn.q_proj", | |
| "model.language_model.layers.30.self_attn.k_proj", | |
| "model.language_model.layers.30.self_attn.v_proj", | |
| "model.language_model.layers.30.self_attn.o_proj", | |
| "model.language_model.layers.30.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.30.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.30.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.31.self_attn.q_proj", | |
| "model.language_model.layers.31.self_attn.k_proj", | |
| "model.language_model.layers.31.self_attn.v_proj", | |
| "model.language_model.layers.31.self_attn.o_proj", | |
| "model.language_model.layers.31.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.31.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.31.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.32.self_attn.q_proj", | |
| "model.language_model.layers.32.self_attn.k_proj", | |
| "model.language_model.layers.32.self_attn.v_proj", | |
| "model.language_model.layers.32.self_attn.o_proj", | |
| "model.language_model.layers.32.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.32.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.32.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.33.self_attn.q_proj", | |
| "model.language_model.layers.33.self_attn.k_proj", | |
| "model.language_model.layers.33.self_attn.v_proj", | |
| "model.language_model.layers.33.self_attn.o_proj", | |
| "model.language_model.layers.33.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.33.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.33.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.34.self_attn.q_proj", | |
| "model.language_model.layers.34.self_attn.k_proj", | |
| "model.language_model.layers.34.self_attn.v_proj", | |
| "model.language_model.layers.34.self_attn.o_proj", | |
| "model.language_model.layers.34.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.34.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.34.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.35.self_attn.q_proj", | |
| "model.language_model.layers.35.self_attn.k_proj", | |
| "model.language_model.layers.35.self_attn.v_proj", | |
| "model.language_model.layers.35.self_attn.o_proj", | |
| "model.language_model.layers.35.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.35.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.35.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.36.self_attn.q_proj", | |
| "model.language_model.layers.36.self_attn.k_proj", | |
| "model.language_model.layers.36.self_attn.v_proj", | |
| "model.language_model.layers.36.self_attn.o_proj", | |
| "model.language_model.layers.36.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.36.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.36.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.37.self_attn.q_proj", | |
| "model.language_model.layers.37.self_attn.k_proj", | |
| "model.language_model.layers.37.self_attn.v_proj", | |
| "model.language_model.layers.37.self_attn.o_proj", | |
| "model.language_model.layers.37.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.37.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.37.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.38.self_attn.q_proj", | |
| "model.language_model.layers.38.self_attn.k_proj", | |
| "model.language_model.layers.38.self_attn.v_proj", | |
| "model.language_model.layers.38.self_attn.o_proj", | |
| "model.language_model.layers.38.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.38.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.38.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.39.self_attn.q_proj", | |
| "model.language_model.layers.39.self_attn.k_proj", | |
| "model.language_model.layers.39.self_attn.v_proj", | |
| "model.language_model.layers.39.self_attn.o_proj", | |
| "model.language_model.layers.39.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.39.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.39.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.40.self_attn.q_proj", | |
| "model.language_model.layers.40.self_attn.k_proj", | |
| "model.language_model.layers.40.self_attn.v_proj", | |
| "model.language_model.layers.40.self_attn.o_proj", | |
| "model.language_model.layers.40.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.40.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.40.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.41.self_attn.q_proj", | |
| "model.language_model.layers.41.self_attn.k_proj", | |
| "model.language_model.layers.41.self_attn.v_proj", | |
| "model.language_model.layers.41.self_attn.o_proj", | |
| "model.language_model.layers.41.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.41.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.41.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.42.self_attn.q_proj", | |
| "model.language_model.layers.42.self_attn.k_proj", | |
| "model.language_model.layers.42.self_attn.v_proj", | |
| "model.language_model.layers.42.self_attn.o_proj", | |
| "model.language_model.layers.42.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.42.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.42.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.43.self_attn.q_proj", | |
| "model.language_model.layers.43.self_attn.k_proj", | |
| "model.language_model.layers.43.self_attn.v_proj", | |
| "model.language_model.layers.43.self_attn.o_proj", | |
| "model.language_model.layers.43.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.43.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.43.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.44.self_attn.q_proj", | |
| "model.language_model.layers.44.self_attn.k_proj", | |
| "model.language_model.layers.44.self_attn.v_proj", | |
| "model.language_model.layers.44.self_attn.o_proj", | |
| "model.language_model.layers.44.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.44.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.44.mlp.shared_experts.down_proj", | |
| "model.language_model.layers.45.self_attn.q_proj", | |
| "model.language_model.layers.45.self_attn.k_proj", | |
| "model.language_model.layers.45.self_attn.v_proj", | |
| "model.language_model.layers.45.self_attn.o_proj", | |
| "model.language_model.layers.45.mlp.shared_experts.gate_proj", | |
| "model.language_model.layers.45.mlp.shared_experts.up_proj", | |
| "model.language_model.layers.45.mlp.shared_experts.down_proj", | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed" | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "torch_dtype": "bfloat16", | |
| "rope_scaling": { | |
| "rope_type": "default", | |
| "mrope_section": [ | |
| 8, | |
| 12, | |
| 12 | |
| ] | |
| }, | |
| "rope_theta": 10000.0, | |
| "routed_scaling_factor": 1.0, | |
| "topk_group": 1, | |
| "use_cache": true, | |
| "use_qk_norm": false | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.0.dev0", | |
| "video_end_token_id": 151342, | |
| "video_start_token_id": 151341, | |
| "video_token_id": 151364, | |
| "vision_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "depth": 24, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "image_size": 336, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10944, | |
| "model_type": "glm4v_moe", | |
| "num_heads": 12, | |
| "out_hidden_size": 4096, | |
| "patch_size": 14, | |
| "rms_norm_eps": 1e-05, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| } | |
| } | |