{ "architectures": [ "GlmOcrForConditionalGeneration" ], "dtype": "bfloat16", "image_end_token_id": 59257, "image_start_token_id": 59256, "image_token_id": 59280, "model_type": "glm_ocr", "quantization_config": { "config_groups": { "group_0": { "format": "nvfp4-pack-quantized", "input_activations": null, "output_activations": null, "targets": [ "re:.*mlp.(gate_up_proj|down_proj)*$", "re:.*self_attn.(k_proj|o_proj|q_proj|v_proj)*$" ], "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": "nvfp4-pack-quantized", "global_compression_ratio": null, "ignore": [ "model.visual.blocks.0.attn.qkv", "model.visual.blocks.0.attn.proj", "model.visual.blocks.0.mlp.gate_proj", "model.visual.blocks.0.mlp.up_proj", "model.visual.blocks.1.attn.qkv", "model.visual.blocks.1.attn.proj", "model.visual.blocks.1.mlp.gate_proj", "model.visual.blocks.1.mlp.up_proj", "model.visual.blocks.2.attn.qkv", "model.visual.blocks.2.attn.proj", "model.visual.blocks.2.mlp.gate_proj", "model.visual.blocks.2.mlp.up_proj", "model.visual.blocks.3.attn.qkv", "model.visual.blocks.3.attn.proj", "model.visual.blocks.3.mlp.gate_proj", "model.visual.blocks.3.mlp.up_proj", "model.visual.blocks.4.attn.qkv", "model.visual.blocks.4.attn.proj", "model.visual.blocks.4.mlp.gate_proj", "model.visual.blocks.4.mlp.up_proj", "model.visual.blocks.5.attn.qkv", "model.visual.blocks.5.attn.proj", "model.visual.blocks.5.mlp.gate_proj", "model.visual.blocks.5.mlp.up_proj", "model.visual.blocks.6.attn.qkv", "model.visual.blocks.6.attn.proj", "model.visual.blocks.6.mlp.gate_proj", "model.visual.blocks.6.mlp.up_proj", "model.visual.blocks.7.attn.qkv", "model.visual.blocks.7.attn.proj", "model.visual.blocks.7.mlp.gate_proj", "model.visual.blocks.7.mlp.up_proj", "model.visual.blocks.8.attn.qkv", "model.visual.blocks.8.attn.proj", "model.visual.blocks.8.mlp.gate_proj", "model.visual.blocks.8.mlp.up_proj", "model.visual.blocks.9.attn.qkv", "model.visual.blocks.9.attn.proj", "model.visual.blocks.9.mlp.gate_proj", "model.visual.blocks.9.mlp.up_proj", "model.visual.blocks.10.attn.qkv", "model.visual.blocks.10.attn.proj", "model.visual.blocks.10.mlp.gate_proj", "model.visual.blocks.10.mlp.up_proj", "model.visual.blocks.11.attn.qkv", "model.visual.blocks.11.attn.proj", "model.visual.blocks.11.mlp.gate_proj", "model.visual.blocks.11.mlp.up_proj", "model.visual.blocks.12.attn.qkv", "model.visual.blocks.12.attn.proj", "model.visual.blocks.12.mlp.gate_proj", "model.visual.blocks.12.mlp.up_proj", "model.visual.blocks.13.attn.qkv", "model.visual.blocks.13.attn.proj", "model.visual.blocks.13.mlp.gate_proj", "model.visual.blocks.13.mlp.up_proj", "model.visual.blocks.14.attn.qkv", "model.visual.blocks.14.attn.proj", "model.visual.blocks.14.mlp.gate_proj", "model.visual.blocks.14.mlp.up_proj", "model.visual.blocks.15.attn.qkv", "model.visual.blocks.15.attn.proj", "model.visual.blocks.15.mlp.gate_proj", "model.visual.blocks.15.mlp.up_proj", "model.visual.blocks.16.attn.qkv", "model.visual.blocks.16.attn.proj", "model.visual.blocks.16.mlp.gate_proj", "model.visual.blocks.16.mlp.up_proj", "model.visual.blocks.17.attn.qkv", "model.visual.blocks.17.attn.proj", "model.visual.blocks.17.mlp.gate_proj", "model.visual.blocks.17.mlp.up_proj", "model.visual.blocks.18.attn.qkv", "model.visual.blocks.18.attn.proj", "model.visual.blocks.18.mlp.gate_proj", "model.visual.blocks.18.mlp.up_proj", "model.visual.blocks.19.attn.qkv", "model.visual.blocks.19.attn.proj", "model.visual.blocks.19.mlp.gate_proj", "model.visual.blocks.19.mlp.up_proj", "model.visual.blocks.20.attn.qkv", "model.visual.blocks.20.attn.proj", "model.visual.blocks.20.mlp.gate_proj", "model.visual.blocks.20.mlp.up_proj", "model.visual.blocks.21.attn.qkv", "model.visual.blocks.21.attn.proj", "model.visual.blocks.21.mlp.gate_proj", "model.visual.blocks.21.mlp.up_proj", "model.visual.blocks.22.attn.qkv", "model.visual.blocks.22.attn.proj", "model.visual.blocks.22.mlp.gate_proj", "model.visual.blocks.22.mlp.up_proj", "model.visual.blocks.23.attn.qkv", "model.visual.blocks.23.attn.proj", "model.visual.blocks.23.mlp.gate_proj", "model.visual.blocks.23.mlp.up_proj", "model.visual.merger.proj", "model.visual.merger.gate_proj", "model.visual.merger.up_proj", "model.visual.merger.down_proj", "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.17.1" }, "text_config": { "attention_bias": false, "attention_dropout": 0.0, "dtype": "bfloat16", "eos_token_id": [ 59246, 59253 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 4608, "max_position_embeddings": 131072, "model_type": "glm_ocr_text", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 8, "num_nextn_predict_layers": 1, "pad_token_id": 59246, "rms_norm_eps": 1e-05, "rope_parameters": { "mrope_section": [ 16, 24, 24 ], "partial_rotary_factor": 1.0, "rope_theta": 10000, "rope_type": "default" }, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 59392 }, "tie_word_embeddings": false, "transformers_version": "5.10.1", "video_end_token_id": 59259, "video_start_token_id": 59258, "video_token_id": 59281, "vision_config": { "attention_bias": true, "attention_dropout": 0.0, "depth": 24, "dtype": "bfloat16", "hidden_act": "silu", "hidden_dropout_prob": 0.0, "hidden_size": 1024, "image_size": 336, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 4096, "model_type": "glm_ocr_vision", "num_heads": 16, "out_hidden_size": 1536, "patch_size": 14, "rms_norm_eps": 1e-05, "spatial_merge_size": 2, "temporal_patch_size": 2 } }