Add files using upload-large-folder tool

.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

chat_template.jinja

@@ -0,0 +1,141 @@
+[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>' }}
+{% elif m.content is iterable and m.content is not mapping %}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+{{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{%- for tr in m.content -%}
+  {%- if tr is mapping and tr.type is defined -%}
+    {%- set t = tr.type | lower -%}
+    {%- if t == 'text' and tr.text is defined -%}
+{{ tr.text }}
+    {%- elif t in ['image', 'image_url'] -%}
+<|begin_of_image|><|image|><|end_of_image|>
+    {%- elif t in ['video', 'video_url'] -%}
+<|begin_of_video|><|video|><|end_of_video|>
+    {%- else -%}
+{{ tr | tojson(ensure_ascii=False) }}
+    {%- endif -%}
+  {%- else -%}
+{{ tr.output if tr.output is defined else tr }}
+  {%- endif -%}
+{%- endfor -%}
+{{- '\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 -%}
+{# ====== 逻辑结束 ====== #}
+{%- 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 +1,112 @@
+{
+  "architectures": [
+    "Glm4vMoeForConditionalGeneration"
+  ],
+  "model_type": "glm4v_moe",
+  "text_config": {
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+      151329,
+      151336,
+      151338
+    ],
+    "first_k_dense_replace": 1,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 10944,
+    "max_position_embeddings": 131072,
+    "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,
+    "num_nextn_predict_layers": 0,
+    "pad_token_id": 151329,
+    "partial_rotary_factor": 0.5,
+    "qk_layernorm": false,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "mrope_section": [
+        8,
+        12,
+        12
+      ],
+      "partial_rotary_factor": 0.5,
+      "rope_theta": 500000,
+      "rope_type": "default"
+    },
+    "routed_scaling_factor": 1.0,
+    "topk_group": 1,
+    "use_cache": true,
+    "use_qk_norm": false,
+    "vocab_size": 151552
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0rc0",
+  "image_start_token_id": 151339,
+  "image_end_token_id": 151340,
+  "video_start_token_id": 151341,
+  "video_end_token_id": 151342,
+  "image_token_id": 151363,
+  "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": 10944,
+    "model_type": "glm4v_moe_vision",
+    "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": "compressed-tensors",
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "num_bits": 4,
+          "type": "float",
+          "strategy": "tensor_group",
+          "group_size": 16,
+          "symmetric": true,
+          "dynamic": false
+        },
+        "weights": {
+          "num_bits": 4,
+          "type": "float",
+          "strategy": "tensor_group",
+          "group_size": 16,
+          "symmetric": true
+        },
+        "targets": [
+          "Linear"
+        ]
+      }
+    },
+    "format": "nvfp4-pack-quantized",
+    "ignore": [
+      "lm_head",
+      "re:visual.*",
+      "re:model.visual.*"
+    ],
+    "dynamic": true
+  }
+}

eval_results/mmlu_results_20260112_072142.json

@@ -0,0 +1,373 @@
+{
+  "timestamp": "20260112_072142",
+  "model": "glm-4.6v",
+  "overall_accuracy": 0.7355789773536533,
+  "total_correct": 10329,
+  "total_questions": 14042,
+  "category_results": {
+    "STEM": {
+      "accuracy": 0.7025055502695845,
+      "correct": 2215,
+      "total": 3153
+    },
+    "Other": {
+      "accuracy": 0.7837141937560348,
+      "correct": 2435,
+      "total": 3107
+    },
+    "Social Sciences": {
+      "accuracy": 0.8189795255118621,
+      "correct": 2520,
+      "total": 3077
+    },
+    "Humanities": {
+      "accuracy": 0.6714133900106269,
+      "correct": 3159,
+      "total": 4705
+    }
+  },
+  "subject_results": [
+    {
+      "subject": "abstract_algebra",
+      "correct": 54,
+      "total": 100,
+      "accuracy": 0.54
+    },
+    {
+      "subject": "anatomy",
+      "correct": 104,
+      "total": 135,
+      "accuracy": 0.7703703703703704
+    },
+    {
+      "subject": "astronomy",
+      "correct": 131,
+      "total": 152,
+      "accuracy": 0.8618421052631579
+    },
+    {
+      "subject": "business_ethics",
+      "correct": 83,
+      "total": 100,
+      "accuracy": 0.83
+    },
+    {
+      "subject": "clinical_knowledge",
+      "correct": 201,
+      "total": 265,
+      "accuracy": 0.7584905660377359
+    },
+    {
+      "subject": "college_biology",
+      "correct": 123,
+      "total": 144,
+      "accuracy": 0.8541666666666666
+    },
+    {
+      "subject": "college_chemistry",
+      "correct": 55,
+      "total": 100,
+      "accuracy": 0.55
+    },
+    {
+      "subject": "college_computer_science",
+      "correct": 76,
+      "total": 100,
+      "accuracy": 0.76
+    },
+    {
+      "subject": "college_mathematics",
+      "correct": 56,
+      "total": 100,
+      "accuracy": 0.56
+    },
+    {
+      "subject": "college_medicine",
+      "correct": 130,
+      "total": 173,
+      "accuracy": 0.7514450867052023
+    },
+    {
+      "subject": "college_physics",
+      "correct": 66,
+      "total": 102,
+      "accuracy": 0.6470588235294118
+    },
+    {
+      "subject": "computer_security",
+      "correct": 72,
+      "total": 100,
+      "accuracy": 0.72
+    },
+    {
+      "subject": "conceptual_physics",
+      "correct": 191,
+      "total": 235,
+      "accuracy": 0.8127659574468085
+    },
+    {
+      "subject": "econometrics",
+      "correct": 72,
+      "total": 114,
+      "accuracy": 0.631578947368421
+    },
+    {
+      "subject": "electrical_engineering",
+      "correct": 104,
+      "total": 145,
+      "accuracy": 0.7172413793103448
+    },
+    {
+      "subject": "elementary_mathematics",
+      "correct": 250,
+      "total": 378,
+      "accuracy": 0.6613756613756614
+    },
+    {
+      "subject": "formal_logic",
+      "correct": 82,
+      "total": 126,
+      "accuracy": 0.6507936507936508
+    },
+    {
+      "subject": "global_facts",
+      "correct": 58,
+      "total": 100,
+      "accuracy": 0.58
+    },
+    {
+      "subject": "high_school_biology",
+      "correct": 273,
+      "total": 310,
+      "accuracy": 0.8806451612903226
+    },
+    {
+      "subject": "high_school_chemistry",
+      "correct": 140,
+      "total": 203,
+      "accuracy": 0.6896551724137931
+    },
+    {
+      "subject": "high_school_computer_science",
+      "correct": 68,
+      "total": 100,
+      "accuracy": 0.68
+    },
+    {
+      "subject": "high_school_european_history",
+      "correct": 141,
+      "total": 165,
+      "accuracy": 0.8545454545454545
+    },
+    {
+      "subject": "high_school_geography",
+      "correct": 171,
+      "total": 198,
+      "accuracy": 0.8636363636363636
+    },
+    {
+      "subject": "high_school_government_and_politics",
+      "correct": 175,
+      "total": 193,
+      "accuracy": 0.9067357512953368
+    },
+    {
+      "subject": "high_school_macroeconomics",
+      "correct": 314,
+      "total": 390,
+      "accuracy": 0.8051282051282052
+    },
+    {
+      "subject": "high_school_mathematics",
+      "correct": 128,
+      "total": 270,
+      "accuracy": 0.4740740740740741
+    },
+    {
+      "subject": "high_school_microeconomics",
+      "correct": 198,
+      "total": 238,
+      "accuracy": 0.8319327731092437
+    },
+    {
+      "subject": "high_school_physics",
+      "correct": 108,
+      "total": 151,
+      "accuracy": 0.7152317880794702
+    },
+    {
+      "subject": "high_school_psychology",
+      "correct": 488,
+      "total": 545,
+      "accuracy": 0.8954128440366973
+    },
+    {
+      "subject": "high_school_statistics",
+      "correct": 149,
+      "total": 216,
+      "accuracy": 0.6898148148148148
+    },
+    {
+      "subject": "high_school_us_history",
+      "correct": 180,
+      "total": 204,
+      "accuracy": 0.8823529411764706
+    },
+    {
+      "subject": "high_school_world_history",
+      "correct": 210,
+      "total": 237,
+      "accuracy": 0.8860759493670886
+    },
+    {
+      "subject": "human_aging",
+      "correct": 172,
+      "total": 223,
+      "accuracy": 0.7713004484304933
+    },
+    {
+      "subject": "human_sexuality",
+      "correct": 104,
+      "total": 131,
+      "accuracy": 0.7938931297709924
+    },
+    {
+      "subject": "international_law",
+      "correct": 96,
+      "total": 121,
+      "accuracy": 0.7933884297520661
+    },
+    {
+      "subject": "jurisprudence",
+      "correct": 89,
+      "total": 108,
+      "accuracy": 0.8240740740740741
+    },
+    {
+      "subject": "logical_fallacies",
+      "correct": 131,
+      "total": 163,
+      "accuracy": 0.803680981595092
+    },
+    {
+      "subject": "machine_learning",
+      "correct": 67,
+      "total": 112,
+      "accuracy": 0.5982142857142857
+    },
+    {
+      "subject": "management",
+      "correct": 87,
+      "total": 103,
+      "accuracy": 0.8446601941747572
+    },
+    {
+      "subject": "marketing",
+      "correct": 191,
+      "total": 234,
+      "accuracy": 0.8162393162393162
+    },
+    {
+      "subject": "medical_genetics",
+      "correct": 83,
+      "total": 100,
+      "accuracy": 0.83
+    },
+    {
+      "subject": "miscellaneous",
+      "correct": 686,
+      "total": 783,
+      "accuracy": 0.876117496807152
+    },
+    {
+      "subject": "moral_disputes",
+      "correct": 252,
+      "total": 346,
+      "accuracy": 0.7283236994219653
+    },
+    {
+      "subject": "moral_scenarios",
+      "correct": 409,
+      "total": 895,
+      "accuracy": 0.4569832402234637
+    },
+    {
+      "subject": "nutrition",
+      "correct": 246,
+      "total": 306,
+      "accuracy": 0.803921568627451
+    },
+    {
+      "subject": "philosophy",
+      "correct": 237,
+      "total": 311,
+      "accuracy": 0.7620578778135049
+    },
+    {
+      "subject": "prehistory",
+      "correct": 268,
+      "total": 324,
+      "accuracy": 0.8271604938271605
+    },
+    {
+      "subject": "professional_accounting",
+      "correct": 173,
+      "total": 282,
+      "accuracy": 0.6134751773049646
+    },
+    {
+      "subject": "professional_law",
+      "correct": 926,
+      "total": 1534,
+      "accuracy": 0.6036505867014341
+    },
+    {
+      "subject": "professional_medicine",
+      "correct": 240,
+      "total": 272,
+      "accuracy": 0.8823529411764706
+    },
+    {
+      "subject": "professional_psychology",
+      "correct": 495,
+      "total": 612,
+      "accuracy": 0.8088235294117647
+    },
+    {
+      "subject": "public_relations",
+      "correct": 74,
+      "total": 110,
+      "accuracy": 0.6727272727272727
+    },
+    {
+      "subject": "security_studies",
+      "correct": 185,
+      "total": 245,
+      "accuracy": 0.7551020408163265
+    },
+    {
+      "subject": "sociology",
+      "correct": 154,
+      "total": 201,
+      "accuracy": 0.7661691542288557
+    },
+    {
+      "subject": "us_foreign_policy",
+      "correct": 90,
+      "total": 100,
+      "accuracy": 0.9
+    },
+    {
+      "subject": "virology",
+      "correct": 85,
+      "total": 166,
+      "accuracy": 0.5120481927710844
+    },
+    {
+      "subject": "world_religions",
+      "correct": 138,
+      "total": 171,
+      "accuracy": 0.8070175438596491
+    }
+  ]
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "top_p": 0.6,
+  "temperature": 0.8,
+  "top_k": 2,
+  "transformers_version": "5.0.0rc0"
+}

hf_quant_config.json

@@ -0,0 +1,11 @@
+{
+  "producer": {
+    "name": "glm4v-nvfp4-layer-by-layer",
+    "version": "1.0.0"
+  },
+  "quantization": {
+    "quant_algo": "NVFP4",
+    "kv_cache_quant_algo": null,
+    "group_size": 16
+  }
+}

model-00000-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c226f163bfa5dd3ff157003ebbc82d7d5b450e909c0e6c9520835063ae65594
+size 5368529744

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05db2e38a8211f9b3f6e2de358c30c195b194e684d7050a51a34a72f9391361c
+size 5369359944

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29649ab31148f1ca7694a9ea75345f16c421444ca4e400595b7bca8745298d67
+size 5366840544

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2a63f302651db9ca473d4e9c7bab156d26542d973ec066af9b97efd129ed0c
+size 5369366488

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2ba213afbe7f9b982074683b3b4df4f48de7e9a5b61c3a891e9482cb085ab5
+size 5366843744

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6e4a9c32e4ef6c8a6fa6bb3e6ce539c03ed6e02437cbaff0720a34ca6abb25
+size 5369366648

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88be4823bcda218061f81e8528003dde65e6a185af085c300d09f65345de650e
+size 5366843808

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2548081d41090e456124d07e66391fd34d5fe2e9f922eb083fbe2af35df2c32f
+size 5369366736

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7862961f1285df37c4fe9ca0d7c246cdca5ef31bfac0ab53c0cca01e47374d8a
+size 5366843928

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1704d31f562aeaff92abd1e23319e8639cd10b683914064f59320e40b2681a84
+size 5369366696

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d57bba9b7f4e473ef863081d7c743d2381e2a666f68c2d08ea978f6d9b8f67
+size 5366843960

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f714c97e96028748a2fd095af5a291ffd3dc24d4e11670770fc758abe3b877f2
+size 4602256272

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": "Glm46VImageProcessor",
+    "processor_class": "Glm46VProcessor"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,327 @@
+{
+  "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|>",
+    "<|image|>",
+    "<|video|>",
+    "<|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": "Glm46VVideoProcessor",
+    "processor_class": "Glm46VProcessor"
+}