{ "architectures": [ "Glm4vForConditionalGeneration" ], "dtype": "bfloat16", "image_end_token_id": 151340, "image_start_token_id": 151339, "image_token_id": 151363, "model_type": "glm4v", "quantization_config": { "config_groups": { "group_0": { "format": "nvfp4-pack-quantized", "input_activations": { "actorder": null, "block_structure": null, "dynamic": "local", "group_size": 16, "num_bits": 4, "observer": "static_minmax", "observer_kwargs": {}, "strategy": "tensor_group", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 16, "num_bits": 4, "observer": "static_minmax", "observer_kwargs": {}, "strategy": "tensor_group", "symmetric": true, "type": "float" } } }, "format": "nvfp4-pack-quantized", "global_compression_ratio": null, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.13.1.a20251215" }, "text_config": { "attention_bias": true, "attention_dropout": 0.0, "dtype": "bfloat16", "eos_token_id": [ 151329, 151336, 151338 ], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 13696, "max_position_embeddings": 131072, "model_type": "glm4v_text", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 2, "pad_token_id": 151329, "rms_norm_eps": 1e-05, "rope_parameters": { "mrope_section": [ 8, 12, 12 ], "partial_rotary_factor": 0.5, "rope_theta": 500000, "rope_type": "default" }, "use_cache": true, "vocab_size": 151552 }, "tie_word_embeddings": false, "transformers_version": "5.0.0rc1", "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_dropout_prob": 0.0, "hidden_size": 1536, "image_size": 336, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 13696, "model_type": "glm4v_vision", "num_heads": 12, "out_hidden_size": 4096, "patch_size": 14, "rms_norm_eps": 1e-05, "spatial_merge_size": 2, "temporal_patch_size": 2 } }