Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,85 @@
+{
+  "name_or_path": "tclf90/GLM-4.5V-AWQ",
+  "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": 11264,
+    "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,
+    "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": "float16",
+  "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": 11264,
+    "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
+  },
+  "quantization_config": {
+    "quant_method": "awq_marlin",
+    "bits": 4,
+    "group_size": 128,
+    "version": "gemm",
+    "zero_point": true,
+    "modules_to_not_convert": ["blocks.", "model.embed_tokens", "model.layers.0.mlp.shared_experts.", "model.layers.1.mlp.shared_experts.", "model.layers.2.mlp.shared_experts.", "model.layers.3.mlp.shared_experts.", "model.layers.4.mlp.shared_experts.", "model.layers.5.mlp.shared_experts.", "model.layers.6.mlp.shared_experts.", "model.layers.7.mlp.shared_experts.", "model.layers.8.mlp.shared_experts.", "model.layers.9.mlp.shared_experts.", "model.layers.10.mlp.shared_experts.", "model.layers.11.mlp.shared_experts.", "model.layers.12.mlp.shared_experts.", "model.layers.13.mlp.shared_experts.", "model.layers.14.mlp.shared_experts.", "model.layers.15.mlp.shared_experts.", "model.layers.16.mlp.shared_experts.", "model.layers.17.mlp.shared_experts.", "model.layers.18.mlp.shared_experts.", "model.layers.19.mlp.shared_experts.", "model.layers.20.mlp.shared_experts.", "model.layers.21.mlp.shared_experts.", "model.layers.22.mlp.shared_experts.", "model.layers.23.mlp.shared_experts.", "model.layers.24.mlp.shared_experts.", "model.layers.25.mlp.shared_experts.", "model.layers.26.mlp.shared_experts.", "model.layers.27.mlp.shared_experts.", "model.layers.28.mlp.shared_experts.", "model.layers.29.mlp.shared_experts.", "model.layers.30.mlp.shared_experts.", "model.layers.31.mlp.shared_experts.", "model.layers.32.mlp.shared_experts.", "model.layers.33.mlp.shared_experts.", "model.layers.34.mlp.shared_experts.", "model.layers.35.mlp.shared_experts.", "model.layers.36.mlp.shared_experts.", "model.layers.37.mlp.shared_experts.", "model.layers.38.mlp.shared_experts.", "model.layers.39.mlp.shared_experts.", "model.layers.40.mlp.shared_experts.", "model.layers.41.mlp.shared_experts.", "model.layers.42.mlp.shared_experts.", "model.layers.43.mlp.shared_experts.", "model.layers.44.mlp.shared_experts.", "model.layers.45.mlp.shared_experts.", "lm_head"]
+  }
+}

README.md

@@ -0,0 +1,112 @@
+---
+license: mit
+language:
+- zh
+- en
+base_model:
+- zai-org/GLM-4.5-Air-Base
+pipeline_tag: image-text-to-text
+library_name: transformers
+---
+
+# GLM-4.5V
+
+<div align="center">
+<img src=https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/resources/logo.svg width="40%"/>
+</div>
+<p align="center">
+    👋 Join our <a href="https://discord.com/invite/8cnQKdAprg" target="_blank">Discord</a> communities.
+    <br>
+    📖 Check out the <a href="https://github.com/zai-org/GLM-V/blob/main/resources/GLM-4.5V_technical_report.pdf" target="_blank">paper</a>.
+    <br>
+    📍 Access the GLM-V series models via API on the <a href="https://docs.z.ai/guides/vlm/glm-4.5v">ZhipuAI Open Platform</a>.
+</p>
+
+## Introduction
+
+Vision-language models (VLMs) have become a key cornerstone of intelligent systems. As real-world AI tasks grow increasingly complex, VLMs urgently need to enhance reasoning capabilities beyond basic multimodal perception — improving accuracy, comprehensiveness, and intelligence — to enable complex problem solving, long-context understanding, and multimodal agents.
+
+Through our open-source work, we aim to explore the technological frontier together with the community while empowering more developers to create exciting and innovative applications.
+
+GLM-4.5V is based on ZhipuAI’s next-generation flagship text foundation model GLM-4.5-Air (106B parameters, 12B active).  It continues the technical approach of GLM-4.1V-Thinking, achieving SOTA performance among models of the same scale on 42 public vision-language benchmarks.  It covers common tasks such as image, video, and document understanding, as well as GUI agent operations.
+
+![bench_45](https://raw.githubusercontent.com/zai-org/GLM-V/refs/heads/main/resources/bench_45v.jpeg)
+
+Beyond benchmark performance, GLM-4.5V focuses on real-world usability. Through efficient hybrid training, it can handle diverse types of visual content, enabling full-spectrum vision reasoning, including:
+- **Image reasoning** (scene understanding, complex multi-image analysis, spatial recognition)
+- **Video understanding** (long video segmentation and event recognition)
+- **GUI tasks** (screen reading, icon recognition, desktop operation assistance)
+- **Complex chart & long document parsing** (research report analysis, information extraction)
+- **Grounding** (precise visual element localization)
+
+The model also introduces a **Thinking Mode** switch, allowing users to balance between quick responses and deep reasoning. This switch works the same as in the `GLM-4.5` language model.
+
+## Quick Start 
+
+Using with transformers:
+
+```shell
+pip install transformers-v4.55.0-GLM-4.5V-preview
+```
+
+and then run:
+
+```shell
+from transformers import AutoProcessor, Glm4vMoeForConditionalGeneration
+import torch
+
+MODEL_PATH = "zai-org/GLM-4.5V"
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "url": "https://upload.wikimedia.org/wikipedia/commons/f/fa/Grayscale_8bits_palette_sample_image.png"
+            },
+            {
+                "type": "text",
+                "text": "describe this image"
+            }
+        ],
+    }
+]
+processor = AutoProcessor.from_pretrained(MODEL_PATH)
+model = Glm4vMoeForConditionalGeneration.from_pretrained(
+    pretrained_model_name_or_path=MODEL_PATH,
+    torch_dtype="auto",
+    device_map="auto",
+)
+inputs = processor.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_dict=True,
+    return_tensors="pt"
+).to(model.device)
+inputs.pop("token_type_ids", None)
+generated_ids = model.generate(**inputs, max_new_tokens=8192)
+output_text = processor.decode(generated_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False)
+print(output_text)
+```
+
+The special tokens `<|begin_of_box|>` and `<|end_of_box|>` in the response mark the answer’s bounding box in the image. The bounding box is given as four numbers — for example `[x1, y1, x2, y2]`, where `(x1, y1)` is the top-left corner and `(x2, y2`)` is the bottom-right corner. The bracket style may vary ([], [[]], (), <>, etc.), but the meaning is the same: it encloses the coordinates of the box. These coordinates are relative values between 0 and 1000, normalized to the image size.
+
+For more code information, please visit our [GitHub](https://github.com/zai-org/GLM-V/).
+
+## Citation
+
+If you use this model, please cite the following paper:
+
+```bibtex
+@misc{glmvteam2025glm41vthinkingversatilemultimodalreasoning,
+      title={GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning},
+      author={GLM-V Team and Wenyi Hong and Wenmeng Yu and Xiaotao Gu and Guo Wang and Guobing Gan and Haomiao Tang and Jiale Cheng and Ji Qi and Junhui Ji and Lihang Pan and Shuaiqi Duan and Weihan Wang and Yan Wang and Yean Cheng and Zehai He and Zhe Su and Zhen Yang and Ziyang Pan and Aohan Zeng and Baoxu Wang and Boyan Shi and Changyu Pang and Chenhui Zhang and Da Yin and Fan Yang and Guoqing Chen and Jiazheng Xu and Jiali Chen and Jing Chen and Jinhao Chen and Jinghao Lin and Jinjiang Wang and Junjie Chen and Leqi Lei and Letian Gong and Leyi Pan and Mingzhi Zhang and Qinkai Zheng and Sheng Yang and Shi Zhong and Shiyu Huang and Shuyuan Zhao and Siyan Xue and Shangqin Tu and Shengbiao Meng and Tianshu Zhang and Tianwei Luo and Tianxiang Hao and Wenkai Li and Wei Jia and Xin Lyu and Xuancheng Huang and Yanling Wang and Yadong Xue and Yanfeng Wang and Yifan An and Yifan Du and Yiming Shi and Yiheng Huang and Yilin Niu and Yuan Wang and Yuanchang Yue and Yuchen Li and Yutao Zhang and Yuxuan Zhang and Zhanxiao Du and Zhenyu Hou and Zhao Xue and Zhengxiao Du and Zihan Wang and Peng Zhang and Debing Liu and Bin Xu and Juanzi Li and Minlie Huang and Yuxiao Dong and Jie Tang},
+      year={2025},
+      eprint={2507.01006},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2507.01006},
+}
+```
+

awq_marlin.py

@@ -0,0 +1,526 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from typing import Any, Callable, Optional
+
+import torch
+from torch.nn import Parameter
+
+import vllm.model_executor.layers.fused_moe  # noqa
+from vllm import _custom_ops as ops
+from vllm.logger import init_logger
+from vllm.model_executor.layers.fused_moe.layer import (
+    FusedMoE, FusedMoEMethodBase, FusedMoeWeightScaleSupported, 
+    UnquantizedFusedMoEMethod)
+from vllm.model_executor.layers.linear import (LinearBase, LinearMethodBase,
+                                               UnquantizedLinearMethod,
+                                               set_weight_attrs)
+from vllm.model_executor.layers.quantization import QuantizationMethods
+from vllm.model_executor.layers.quantization.awq import (AWQConfig,
+                                                         is_layer_skipped_awq)
+from vllm.model_executor.layers.quantization.base_config import (
+    QuantizationConfig, QuantizeMethodBase)
+from vllm.model_executor.layers.quantization.utils import replace_parameter
+from vllm.model_executor.layers.quantization.utils.marlin_utils import (
+    apply_awq_marlin_linear, awq_to_marlin_zero_points, check_marlin_supported,
+    check_marlin_supports_layer, check_moe_marlin_supports_layer,
+    marlin_make_empty_g_idx, marlin_make_workspace_new,
+    marlin_moe_permute_scales, marlin_permute_scales,
+    moe_awq_to_marlin_zero_points, verify_marlin_supported,
+    verify_marlin_supports_shape)
+from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
+from vllm.model_executor.parameter import (GroupQuantScaleParameter,
+                                           PackedvLLMParameter)
+from vllm.platforms import current_platform
+from vllm.scalar_type import scalar_types
+
+logger = init_logger(__name__)
+
+
+class AWQMarlinConfig(QuantizationConfig):
+    """Config class for AWQ Marlin"""
+
+    # num_bits -> type
+    TYPE_MAP = {
+        4: scalar_types.uint4,
+        8: scalar_types.uint8,
+    }
+
+    def __init__(self, weight_bits: int, group_size: int, zero_point: bool,
+                 lm_head_quantized: bool,
+                 modules_to_not_convert: Optional[list[str]],
+                 full_config: dict[str, Any]) -> None:
+        super().__init__()
+        self.pack_factor = 32 // weight_bits  # packed into int32
+        self.group_size = group_size
+        self.zero_point = zero_point
+        self.lm_head_quantized = lm_head_quantized
+        self.weight_bits = weight_bits
+        self.modules_to_not_convert = modules_to_not_convert or []
+        self.full_config = full_config
+
+        if self.weight_bits not in self.TYPE_MAP:
+            raise ValueError(f"Unsupported num_bits = {self.weight_bits}. "
+                             f"Supported num_bits = {self.TYPE_MAP.keys()}")
+
+        self.quant_type = self.TYPE_MAP[self.weight_bits]
+
+        verify_marlin_supported(self.quant_type,
+                                group_size=self.group_size,
+                                has_zp=self.zero_point)
+
+    def __repr__(self) -> str:
+        return (f"AWQMarlinConfig(quant_type={self.quant_type}, "
+                f"group_size={self.group_size}, "
+                f"zero_point={self.zero_point}, "
+                f"lm_head_quantized={self.lm_head_quantized}, "
+                f"modules_to_not_convert={self.modules_to_not_convert})")
+
+    @classmethod
+    def get_name(cls) -> QuantizationMethods:
+        return "awq_marlin"
+
+    @classmethod
+    def get_supported_act_dtypes(cls) -> list[torch.dtype]:
+        return [torch.half, torch.bfloat16]
+
+    @classmethod
+    def get_min_capability(cls) -> int:
+        return 80
+
+    @classmethod
+    def get_config_filenames(cls) -> list[str]:
+        return ["quantize_config.json"]
+
+    @classmethod
+    def from_config(cls, config: dict[str, Any]) -> "AWQMarlinConfig":
+        weight_bits = cls.get_from_keys(config, ["bits"])
+        group_size = cls.get_from_keys(config, ["group_size"])
+        zero_point = cls.get_from_keys(config, ["zero_point"])
+        lm_head_quantized = cls.get_from_keys_or(config, ["lm_head"],
+                                                 default=False)
+        modules_to_not_convert = cls.get_from_keys_or(
+            config, ["modules_to_not_convert"], None)
+        return cls(weight_bits, group_size, zero_point, lm_head_quantized,
+                   modules_to_not_convert, config)
+
+    @classmethod
+    def override_quantization_method(
+            cls, hf_quant_cfg, user_quant) -> Optional[QuantizationMethods]:
+        can_convert = cls.is_awq_marlin_compatible(hf_quant_cfg)
+        is_valid_user_quant = (user_quant is None or user_quant == "marlin"
+                               or user_quant == "awq_marlin")
+
+        if can_convert and is_valid_user_quant:
+            msg = ("The model is convertible to {} during runtime."
+                   " Using {} kernel.".format(cls.get_name(), cls.get_name()))
+            logger.info(msg)
+            return cls.get_name()
+
+        if can_convert and user_quant == "awq":
+            logger.info("Detected that the model can run with awq_marlin"
+                        ", however you specified quantization=awq explicitly,"
+                        " so forcing awq. Use quantization=awq_marlin for"
+                        " faster inference")
+        return None
+
+    def get_quant_method(self, layer: torch.nn.Module,
+                         prefix: str) -> Optional["QuantizeMethodBase"]:
+        if (isinstance(layer, LinearBase) or
+            (isinstance(layer, ParallelLMHead) and self.lm_head_quantized)):
+            if is_layer_skipped_awq(prefix, self.modules_to_not_convert):
+                return UnquantizedLinearMethod()
+            # Check if the layer is supported by AWQMarlin.
+            if not check_marlin_supports_layer(layer, self.group_size):
+                logger.warning_once(
+                    "Layer '%s' is not supported by AWQMarlin. Falling back to unoptimized AWQ kernels.",  # noqa: E501
+                    prefix,
+                )
+                return AWQConfig.from_config(
+                    self.full_config).get_quant_method(layer, prefix)
+            return AWQMarlinLinearMethod(self)
+        elif isinstance(layer, FusedMoE):
+            if is_layer_skipped_awq(prefix, getattr(self, "modules_to_not_convert", [])):
+                return UnquantizedFusedMoEMethod(layer.moe_config)
+            from vllm.model_executor.layers.quantization.moe_wna16 import (
+                MoeWNA16Config)
+            if not check_moe_marlin_supports_layer(layer, self.group_size):
+                logger.warning_once(
+                    f"Layer '{prefix}' is not supported by AWQMoeMarlin. "
+                    "Falling back to Moe WNA16 kernels.")
+                return MoeWNA16Config.from_config(
+                    self.full_config).get_quant_method(layer, prefix)
+            return AWQMoEMethod(self)
+        return None
+
+    @classmethod
+    def is_awq_marlin_compatible(cls, quant_config: dict[str, Any]):
+        # Extract data from quant config.
+        quant_method = quant_config.get("quant_method", "").lower()
+        num_bits = quant_config.get("bits")
+        group_size = quant_config.get("group_size")
+        zero_point = quant_config.get("zero_point")
+
+        if not current_platform.is_cuda():
+            return False
+
+        if quant_method != "awq":
+            return False
+
+        # If we cannot find the info needed in the config, cannot convert.
+        if (num_bits is None or group_size is None or zero_point is None):
+            return False
+
+        if num_bits not in cls.TYPE_MAP:
+            return False
+
+        return check_marlin_supported(quant_type=cls.TYPE_MAP[num_bits],
+                                      group_size=group_size,
+                                      has_zp=zero_point)
+
+
+class AWQMarlinLinearMethod(LinearMethodBase):
+    """Linear method for AWQ Marlin.
+
+    Args:
+        quant_config: The AWQ Marlin quantization config.
+    """
+
+    def __init__(self, quant_config: AWQMarlinConfig) -> None:
+        self.quant_config = quant_config
+
+    def create_weights(
+        self,
+        layer: torch.nn.Module,
+        input_size_per_partition: int,
+        output_partition_sizes: list[int],
+        input_size: int,
+        output_size: int,
+        params_dtype: torch.dtype,
+        **extra_weight_attrs,
+    ) -> None:
+        del output_size
+        output_size_per_partition = sum(output_partition_sizes)
+        weight_loader = extra_weight_attrs.get("weight_loader")
+
+        # Normalize group_size
+        if self.quant_config.group_size != -1:
+            group_size = self.quant_config.group_size
+        else:
+            group_size = input_size
+
+        verify_marlin_supports_shape(
+            output_size_per_partition=output_size_per_partition,
+            input_size_per_partition=input_size_per_partition,
+            input_size=input_size,
+            group_size=group_size)
+
+        qweight = PackedvLLMParameter(
+            data=torch.empty(
+                input_size_per_partition,
+                output_size_per_partition // self.quant_config.pack_factor,
+                dtype=torch.int32,
+            ),
+            input_dim=0,
+            output_dim=1,
+            packed_dim=1,
+            packed_factor=self.quant_config.pack_factor,
+            weight_loader=weight_loader)
+
+        num_groups = input_size_per_partition // group_size
+
+        qzeros = PackedvLLMParameter(
+            data=torch.empty(
+                num_groups,
+                output_size_per_partition // self.quant_config.pack_factor,
+                dtype=torch.int32,
+            ),
+            input_dim=0,
+            output_dim=1,
+            packed_dim=1,
+            packed_factor=self.quant_config.pack_factor,
+            weight_loader=weight_loader)
+
+        scales = GroupQuantScaleParameter(data=torch.empty(
+            num_groups,
+            output_size_per_partition,
+            dtype=params_dtype,
+        ),
+                                          input_dim=0,
+                                          output_dim=1,
+                                          weight_loader=weight_loader)
+
+        layer.register_parameter("qweight", qweight)
+        layer.register_parameter("qzeros", qzeros)
+        layer.register_parameter("scales", scales)
+
+        layer.input_size_per_partition = input_size_per_partition
+        layer.output_size_per_partition = output_size_per_partition
+        layer.num_groups = num_groups
+
+    # TODO: Update this docs
+    # Checkpoints are serialized in AutoAWQ format, which is different from the
+    # marlin format. This function is called after the weights are loaded.
+    # Here, we handle the repacking
+    def process_weights_after_loading(self, layer: torch.nn.Module) -> None:
+        device = layer.qweight.device
+        layer.qweight = torch.nn.Parameter(layer.qweight.data,
+                                           requires_grad=False)
+        layer.qzeros = torch.nn.Parameter(layer.qzeros.data,
+                                          requires_grad=False)
+        layer.scales = torch.nn.Parameter(layer.scales.data,
+                                          requires_grad=False)
+
+        # Allocate marlin workspace
+        layer.workspace = marlin_make_workspace_new(device)
+
+        # Repack weights from AWQ format to marlin format.
+        marlin_qweight = ops.awq_marlin_repack(
+            layer.qweight,
+            size_k=layer.input_size_per_partition,
+            size_n=layer.output_size_per_partition,
+            num_bits=self.quant_config.quant_type.size_bits)
+        replace_parameter(layer, "qweight", marlin_qweight)
+
+        # Permute scales from AWQ format to marlin format.
+        marlin_scales = marlin_permute_scales(
+            layer.scales,
+            size_k=layer.input_size_per_partition,
+            size_n=layer.output_size_per_partition,
+            group_size=self.quant_config.group_size)
+        replace_parameter(layer, "scales", marlin_scales)
+
+        # Permute zero-points from AWQ format to marlin format.
+        marlin_zp = awq_to_marlin_zero_points(
+            layer.qzeros,
+            size_k=layer.num_groups,
+            size_n=layer.output_size_per_partition,
+            num_bits=self.quant_config.quant_type.size_bits)
+        replace_parameter(layer, "qzeros", marlin_zp)
+
+        # Not-used
+        layer.g_idx = marlin_make_empty_g_idx(device)
+        layer.g_idx_sort_indices = marlin_make_empty_g_idx(device)
+
+    def apply(
+        self,
+        layer: torch.nn.Module,
+        x: torch.Tensor,
+        bias: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        return apply_awq_marlin_linear(
+            input=x,
+            weight=layer.qweight,
+            weight_scale=layer.scales,
+            weight_zp=layer.qzeros,
+            g_idx=layer.g_idx,
+            g_idx_sort_indices=layer.g_idx_sort_indices,
+            workspace=layer.workspace,
+            quant_type=self.quant_config.quant_type,
+            output_size_per_partition=layer.output_size_per_partition,
+            input_size_per_partition=layer.input_size_per_partition,
+            bias=bias)
+
+
+class AWQMoEMethod(FusedMoEMethodBase):
+
+    def __init__(self, quant_config: AWQMarlinConfig):
+        self.quant_config = quant_config
+        if self.quant_config.weight_bits != 4:
+            raise ValueError("AWQMoEMethod only supports 4bit now.")
+        self.quant_type = scalar_types.uint4
+
+    def create_weights(self, layer: torch.nn.Module, num_experts: int,
+                       hidden_size: int, intermediate_size_per_partition: int,
+                       params_dtype: torch.dtype, **extra_weight_attrs):
+        extra_weight_attrs.update({
+            "is_transposed":
+            True,
+            "quant_method":
+            FusedMoeWeightScaleSupported.GROUP.value,
+        })
+
+        w13_qweight = Parameter(
+            torch.empty(num_experts,
+                        hidden_size,
+                        2 * intermediate_size_per_partition //
+                        self.quant_config.pack_factor,
+                        dtype=torch.int32),
+            requires_grad=False)
+        layer.register_parameter("w13_qweight", w13_qweight)
+        set_weight_attrs(w13_qweight, extra_weight_attrs)
+
+        w2_qweight = Parameter(torch.empty(num_experts,
+                                           intermediate_size_per_partition,
+                                           hidden_size //
+                                           self.quant_config.pack_factor,
+                                           dtype=torch.int32),
+                               requires_grad=False)
+        layer.register_parameter("w2_qweight", w2_qweight)
+        set_weight_attrs(w2_qweight, extra_weight_attrs)
+
+        num_groups_w13 = hidden_size // self.quant_config.group_size
+        num_groups_w2 = (intermediate_size_per_partition //
+                         self.quant_config.group_size)
+
+        # WEIGHT_SCALES
+        # Allocate 2 scales for w1 and w3 respectively.
+        w13_scales = Parameter(torch.empty(num_experts,
+                                           num_groups_w13,
+                                           intermediate_size_per_partition * 2,
+                                           dtype=params_dtype),
+                               requires_grad=False)
+        layer.register_parameter("w13_scales", w13_scales)
+        set_weight_attrs(w13_scales, extra_weight_attrs)
+
+        w2_scales = Parameter(torch.empty(num_experts,
+                                          num_groups_w2,
+                                          hidden_size,
+                                          dtype=params_dtype),
+                              requires_grad=False)
+        layer.register_parameter("w2_scales", w2_scales)
+        set_weight_attrs(w2_scales, extra_weight_attrs)
+
+        # WEIGHT_ZERO_POINT
+        # Allocate 2 zero points for w1 and w3 respectively.
+        w13_qzeros = Parameter(
+            torch.empty(num_experts,
+                        num_groups_w13,
+                        2 * intermediate_size_per_partition //
+                        self.quant_config.pack_factor,
+                        dtype=torch.int32),
+            requires_grad=False)
+        layer.register_parameter("w13_qzeros", w13_qzeros)
+        set_weight_attrs(w13_qzeros, extra_weight_attrs)
+
+        w2_qzeros = Parameter(torch.empty(num_experts,
+                                          num_groups_w2,
+                                          hidden_size //
+                                          self.quant_config.pack_factor,
+                                          dtype=torch.int32),
+                              requires_grad=False)
+        layer.register_parameter("w2_qzeros", w2_qzeros)
+        set_weight_attrs(w2_qzeros, extra_weight_attrs)
+
+        device = layer.w13_qweight.device
+        layer.workspace = marlin_make_workspace_new(device, 4)
+
+    def process_weights_after_loading(self, layer: torch.nn.Module) -> None:
+        num_experts = layer.w13_qweight.shape[0]
+        device = layer.w13_qweight.device
+
+        layer.w13_g_idx_sort_indices = torch.nn.Parameter(
+            torch.empty((num_experts, 0), dtype=torch.int32, device=device),
+            requires_grad=False,
+        )
+        layer.w2_g_idx_sort_indices = torch.nn.Parameter(
+            torch.empty((num_experts, 0), dtype=torch.int32, device=device),
+            requires_grad=False,
+        )
+
+        marlin_w13_qweight = ops.awq_marlin_moe_repack(
+            layer.w13_qweight,
+            layer.w13_g_idx_sort_indices,
+            size_k=layer.w13_qweight.shape[1],
+            size_n=layer.w13_qweight.shape[2] * self.quant_config.pack_factor,
+            num_bits=self.quant_config.weight_bits,
+        )
+        replace_parameter(layer, "w13_qweight", marlin_w13_qweight)
+
+        marlin_w2_qweight = ops.awq_marlin_moe_repack(
+            layer.w2_qweight,
+            layer.w2_g_idx_sort_indices,
+            size_k=layer.w2_qweight.shape[1],
+            size_n=layer.w2_qweight.shape[2] * self.quant_config.pack_factor,
+            num_bits=self.quant_config.weight_bits,
+        )
+        replace_parameter(layer, "w2_qweight", marlin_w2_qweight)
+
+        # Why does this take the intermediate size for size_k?
+        marlin_w13_scales = marlin_moe_permute_scales(
+            s=layer.w13_scales,
+            size_k=layer.intermediate_size_per_partition,
+            size_n=layer.w13_scales.shape[2],
+            group_size=self.quant_config.group_size,
+        )
+
+        replace_parameter(layer, "w13_scales", marlin_w13_scales)
+
+        marlin_w2_scales = marlin_moe_permute_scales(
+            s=layer.w2_scales,
+            size_k=layer.intermediate_size_per_partition,
+            size_n=layer.w2_scales.shape[2],
+            group_size=self.quant_config.group_size,
+        )
+        replace_parameter(layer, "w2_scales", marlin_w2_scales)
+
+        marlin_w13_zp = moe_awq_to_marlin_zero_points(
+            layer.w13_qzeros,
+            size_k=layer.w13_qzeros.shape[1],
+            size_n=layer.w13_qzeros.shape[2] * self.quant_config.pack_factor,
+            num_bits=self.quant_config.weight_bits)
+        replace_parameter(layer, "w13_qzeros", marlin_w13_zp)
+
+        marlin_w2_zp = moe_awq_to_marlin_zero_points(
+            layer.w2_qzeros,
+            size_k=layer.w2_qzeros.shape[1],
+            size_n=layer.w2_qzeros.shape[2] * self.quant_config.pack_factor,
+            num_bits=self.quant_config.weight_bits)
+        replace_parameter(layer, "w2_qzeros", marlin_w2_zp)
+
+    def apply(
+        self,
+        layer: torch.nn.Module,
+        x: torch.Tensor,
+        router_logits: torch.Tensor,
+        top_k: int,
+        renormalize: bool,
+        use_grouped_topk: bool = False,
+        topk_group: Optional[int] = None,
+        num_expert_group: Optional[int] = None,
+        global_num_experts: int = -1,
+        expert_map: Optional[torch.Tensor] = None,
+        custom_routing_function: Optional[Callable] = None,
+        scoring_func: str = "softmax",
+        e_score_correction_bias: Optional[torch.Tensor] = None,
+        apply_router_weight_on_input: bool = False,
+        activation: str = "silu",
+        enable_eplb: bool = False,
+        expert_load_view: Optional[torch.Tensor] = None,
+        logical_to_physical_map: Optional[torch.Tensor] = None,
+        logical_replica_count: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        if enable_eplb:
+            raise NotImplementedError(
+                "EPLB not supported for `AWQMoEMethod` yet.")
+
+        assert activation == "silu", "Only SiLU activation is supported."
+
+        topk_weights, topk_ids = FusedMoE.select_experts(
+            hidden_states=x,
+            router_logits=router_logits,
+            use_grouped_topk=use_grouped_topk,
+            top_k=top_k,
+            renormalize=renormalize,
+            topk_group=topk_group,
+            num_expert_group=num_expert_group,
+            custom_routing_function=custom_routing_function,
+            scoring_func=scoring_func,
+            e_score_correction_bias=e_score_correction_bias)
+
+        return torch.ops.vllm.fused_marlin_moe(
+            x,
+            layer.w13_qweight,
+            layer.w2_qweight,
+            layer.w13_scales,
+            layer.w2_scales,
+            router_logits,
+            topk_weights,
+            topk_ids,
+            quant_type_id=self.quant_type.id,
+            apply_router_weight_on_input=apply_router_weight_on_input,
+            global_num_experts=global_num_experts,
+            expert_map=expert_map,
+            w1_zeros=layer.w13_qzeros,
+            w2_zeros=layer.w2_qzeros,
+            workspace=layer.workspace)

chat_template.jinja

@@ -0,0 +1,118 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
+                <|begin_of_image|><|image|><|end_of_image|>
+            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
+                <|begin_of_video|><|video|><|end_of_video|>
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{% if m.content is string %}
+{{ m.content }}
+{%- else %}
+{%- for item in m.content %}
+{% if item.type == 'video' or 'video' in item %}
+<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
+<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
+{{ item.text }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|assistant|>
+{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
+{%- endif -%}

config.json

@@ -0,0 +1,85 @@
+{
+  "name_or_path": "tclf90/GLM-4.5V-AWQ",
+  "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": 11264,
+    "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,
+    "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": "float16",
+  "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": 11264,
+    "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
+  },
+  "quantization_config": {
+    "quant_method": "awq_marlin",
+    "bits": 4,
+    "group_size": 128,
+    "version": "gemm",
+    "zero_point": true,
+    "modules_to_not_convert": ["blocks.", "model.embed_tokens", "model.layers.0.mlp.shared_experts.", "model.layers.1.mlp.shared_experts.", "model.layers.2.mlp.shared_experts.", "model.layers.3.mlp.shared_experts.", "model.layers.4.mlp.shared_experts.", "model.layers.5.mlp.shared_experts.", "model.layers.6.mlp.shared_experts.", "model.layers.7.mlp.shared_experts.", "model.layers.8.mlp.shared_experts.", "model.layers.9.mlp.shared_experts.", "model.layers.10.mlp.shared_experts.", "model.layers.11.mlp.shared_experts.", "model.layers.12.mlp.shared_experts.", "model.layers.13.mlp.shared_experts.", "model.layers.14.mlp.shared_experts.", "model.layers.15.mlp.shared_experts.", "model.layers.16.mlp.shared_experts.", "model.layers.17.mlp.shared_experts.", "model.layers.18.mlp.shared_experts.", "model.layers.19.mlp.shared_experts.", "model.layers.20.mlp.shared_experts.", "model.layers.21.mlp.shared_experts.", "model.layers.22.mlp.shared_experts.", "model.layers.23.mlp.shared_experts.", "model.layers.24.mlp.shared_experts.", "model.layers.25.mlp.shared_experts.", "model.layers.26.mlp.shared_experts.", "model.layers.27.mlp.shared_experts.", "model.layers.28.mlp.shared_experts.", "model.layers.29.mlp.shared_experts.", "model.layers.30.mlp.shared_experts.", "model.layers.31.mlp.shared_experts.", "model.layers.32.mlp.shared_experts.", "model.layers.33.mlp.shared_experts.", "model.layers.34.mlp.shared_experts.", "model.layers.35.mlp.shared_experts.", "model.layers.36.mlp.shared_experts.", "model.layers.37.mlp.shared_experts.", "model.layers.38.mlp.shared_experts.", "model.layers.39.mlp.shared_experts.", "model.layers.40.mlp.shared_experts.", "model.layers.41.mlp.shared_experts.", "model.layers.42.mlp.shared_experts.", "model.layers.43.mlp.shared_experts.", "model.layers.44.mlp.shared_experts.", "model.layers.45.mlp.shared_experts.", "lm_head"]
+  }
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"image-text-to-text"}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "temperature": 1.0,
+  "top_k": 1,
+  "top_p": 0.0001,
+  "transformers_version": "4.55.0.dev"
+}

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4c85fbb499a58ffd06ce52729a7f0be18f8089b5c04532d4b2ea4e3d64db1a
+size 2998317112

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69960b4e8403009cf6563dd56e94d466772dfda49b4957781b927ecd62d3bd40
+size 2998549936

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a522fe22ae1930a3f5add3f4d99ff854ff7b1936f70db759d35f8e250d08833e
+size 2998010304

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb2355675d38d695fe01755c938dcbe4c443f4bd56d9db05232b14e5ceec0e1
+size 2998550688

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1732bb579bd643b9c18fd7c69750e03a3d20fb9b2ea44390a70fae3c0e5a2c4c
+size 2997439264

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e38a7349a6ba5093010091947537ca81da523dcddc00ff1c78ab2aee67534be
+size 2999126848

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba3f758896d4180c9ded0f69790c5149af043f7544bd58ec96e21d31152f396
+size 2998552792

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3433599f8939e6bf74625c50d010f10d61d5860f4b51448cb99b797a8e64a794
+size 2998013176

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b56a1fa3e14ed35bcda0381039353d7906b3da0ab823a3a47e0ffa0b29bd583
+size 2998552864

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e4e32b56aa910fe758c9477039eff1c32a3661b7aa85bd348df48322582e42
+size 2998012944

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3f6f0c69833df2ea44922af76007aa00f825019573692a7110e24ba5cea979
+size 2998553016

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2039acb9a345e71e808b02810b842bd99a10653c63124adf783317ecfd5056b
+size 2998552800

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c2a1eed091394e4f07141874aca42fa4827e591760d249d243cab0f6f1a5c4
+size 2998013224

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6cdd344bcdb2d0317bde77f32be4e0a69f339edd61e9e1316880f8108f9976f
+size 2998552800

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1da929b5e622a26f2481fc6a57dab58b81f2a01d6b81222bfe0e261be1c2ab0
+size 2998013032

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155fa8798ea6b4b93fc67c372609c11f7030dcca8f3fb8f809a90fa3959259d1
+size 2998552944

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4237ea97c14fafd482da3f04b3ed7d35dcb0277c1e5dd6bdaf8a3f44f1235b
+size 2998552800

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17d30f0a5348c18bfcb9fe8f10c6197affb04781683a2d6a7222cbf8b064ec3
+size 2998013288

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386a445a7ff7bc9e89512fb81d5f857bffbac409446c8b6ff1cb7e9be2b94cc4
+size 2776117192

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75882d3df123c824ae9d61c4e13e647b4930e7053562f57d37f9e36ef10fde99
+size 2997425744

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d94cd20831a9380e80ec17b587c4040461127752ebffbdfdad27560d927a6e13
+size 531298968

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "size": {"shortest_edge": 12544, "longest_edge": 9633792},
+    "do_rescale": true,
+    "patch_size": 14,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [0.48145466, 0.4578275, 0.40821073],
+    "image_std": [0.26862954, 0.26130258, 0.27577711],
+    "image_processor_type": "Glm4vImageProcessor",
+    "processor_class": "Glm4vProcessor"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9340665016419c825c4bdabbcc9acc43b7ca2c68ce142724afa829abb1be5efd
+size 19970699

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|begin_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|end_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151345": {
+      "content": "<|begin_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151346": {
+      "content": "<|end_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151347": {
+      "content": "<|code_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151348": {
+      "content": "<|code_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151349": {
+      "content": "<|code_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151350": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151352": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151353": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151354": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151355": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151356": {
+      "content": "<arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151357": {
+      "content": "</arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151358": {
+      "content": "<arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151359": {
+      "content": "</arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151360": {
+      "content": "/nothink",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151361": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151362": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151363": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151364": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}

video_preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+    "size": {"shortest_edge": 12544, "longest_edge": 47040000},
+    "do_rescale": true,
+    "patch_size": 14,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [0.48145466, 0.4578275, 0.40821073],
+    "image_std": [0.26862954, 0.26130258, 0.27577711],
+    "video_processor_type": "Glm4vVideoProcessor",
+    "processor_class": "Glm4vProcessor"
+}