{
  "architectures": [
    "GlmOcrForConditionalGeneration"
  ],
  "image_end_token_id": 59257,
  "image_start_token_id": 59256,
  "image_token_id": 59280,
  "model_type": "glm_ocr",
  "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": "5.17.0",
  "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,
    "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,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "axial"
    },
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "quantization_config": {
    "config_groups": {
      "FP8_DYNAMIC": {
        "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": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head",
      "re:.*embed_tokens.*",
      "re:model\\.visual\\..*",
      "re:.*\\.eh_proj.*",
      "re:.*shared_head.*",
      "re:.*norm.*",
      "re:.*language_model\\.layers\\.16\\..*"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "transform_config": {},
    "version": "0.19.0"
  }
}