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 +1,646 @@
+{
+  "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": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "ignore": [
+      "model.layers.4.input_layernorm",
+      "model.layers.3.input_layernorm",
+      "model.layers.2.input_layernorm",
+      "model.layers.0.input_layernorm",
+      "model.layers.1.input_layernorm",
+      "model.layers.8.input_layernorm",
+      "model.layers.6.input_layernorm",
+      "model.layers.7.input_layernorm",
+      "model.layers.5.input_layernorm",
+      "model.layers.9.input_layernorm",
+      "visual.blocks.6.norm1",
+      "visual.blocks.7.norm1",
+      "visual.blocks.8.norm1",
+      "visual.blocks.9.norm1",
+      "visual.patch_embed.proj.bias",
+      "visual.downsample.bias",
+      "model.layers.38.mlp.gate",
+      "model.layers.39.mlp.gate",
+      "model.layers.40.mlp.gate",
+      "model.layers.41.mlp.gate",
+      "model.layers.42.mlp.gate",
+      "model.layers.28.mlp.gate",
+      "model.layers.29.mlp.gate",
+      "model.layers.30.mlp.gate",
+      "model.layers.31.mlp.gate",
+      "model.layers.32.mlp.gate",
+      "model.layers.31.self_attn.q_proj.bias",
+      "model.layers.32.self_attn.q_proj.bias",
+      "model.layers.33.self_attn.q_proj.bias",
+      "model.layers.43.self_attn.q_proj.bias",
+      "model.layers.44.self_attn.q_proj.bias",
+      "model.layers.45.self_attn.q_proj.bias",
+      "model.layers.20.self_attn.q_proj.bias",
+      "model.layers.22.self_attn.q_proj.bias",
+      "model.layers.21.self_attn.q_proj.bias",
+      "model.layers.23.self_attn.q_proj.bias",
+      "model.layers.10.self_attn.q_proj.bias",
+      "model.layers.11.self_attn.q_proj.bias",
+      "model.layers.12.self_attn.q_proj.bias",
+      "model.layers.14.self_attn.q_proj.bias",
+      "model.layers.38.self_attn.q_proj.bias",
+      "model.layers.39.self_attn.q_proj.bias",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.43.self_attn.k_proj.bias",
+      "model.layers.44.self_attn.k_proj.bias",
+      "model.layers.45.self_attn.k_proj.bias",
+      "model.layers.5.self_attn.v_proj.bias",
+      "model.layers.9.self_attn.v_proj.bias",
+      "model.layers.33.mlp.gate",
+      "model.layers.34.mlp.gate",
+      "model.layers.35.mlp.gate",
+      "model.layers.36.mlp.gate",
+      "model.layers.37.mlp.gate",
+      "model.layers.10.mlp.gate",
+      "model.layers.11.mlp.gate",
+      "model.layers.12.mlp.gate",
+      "model.layers.14.mlp.gate",
+      "model.layers.13.mlp.gate",
+      "model.layers.6.mlp.gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.5.mlp.gate",
+      "model.layers.3.mlp.gate",
+      "model.layers.2.mlp.gate",
+      "model.layers.4.mlp.gate",
+      "model.layers.1.mlp.gate",
+      "model.layers.8.mlp.gate",
+      "model.layers.9.mlp.gate",
+      "visual.blocks.15.mlp.gate_up_proj",
+      "visual.blocks.15.mlp.gate_proj",
+      "visual.blocks.15.mlp.up_proj",
+      "visual.blocks.16.mlp.down_proj",
+      "visual.blocks.16.mlp.gate_up_proj",
+      "visual.blocks.16.mlp.gate_proj",
+      "visual.blocks.16.mlp.up_proj",
+      "visual.blocks.17.mlp.down_proj",
+      "visual.blocks.17.mlp.gate_up_proj",
+      "visual.blocks.17.mlp.gate_proj",
+      "visual.blocks.17.mlp.up_proj",
+      "visual.blocks.18.mlp.down_proj",
+      "visual.blocks.18.mlp.gate_up_proj",
+      "visual.blocks.18.mlp.gate_proj",
+      "visual.blocks.18.mlp.up_proj",
+      "visual.blocks.19.mlp.down_proj",
+      "visual.blocks.19.mlp.gate_up_proj",
+      "visual.blocks.19.mlp.gate_proj",
+      "visual.blocks.19.mlp.up_proj",
+      "visual.blocks.20.mlp.down_proj",
+      "visual.post_layernorm",
+      "model.layers.40.mlp.gate.e_score_correction_bias",
+      "model.layers.41.mlp.gate.e_score_correction_bias",
+      "model.layers.42.mlp.gate.e_score_correction_bias",
+      "model.layers.29.mlp.gate.e_score_correction_bias",
+      "model.layers.30.mlp.gate.e_score_correction_bias",
+      "model.layers.31.mlp.gate.e_score_correction_bias",
+      "model.layers.32.mlp.gate.e_score_correction_bias",
+      "model.layers.33.mlp.gate.e_score_correction_bias",
+      "model.layers.34.mlp.gate.e_score_correction_bias",
+      "model.layers.35.mlp.gate.e_score_correction_bias",
+      "visual.blocks.12.norm1",
+      "visual.blocks.12.norm2",
+      "visual.blocks.13.norm1",
+      "visual.blocks.13.norm2",
+      "visual.blocks.14.norm1",
+      "visual.blocks.14.norm2",
+      "visual.blocks.15.norm1",
+      "visual.blocks.15.norm2",
+      "visual.blocks.16.norm2",
+      "visual.blocks.17.norm2",
+      "model.layers.45.mlp.gate.e_score_correction_bias",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.20.self_attn.v_proj.bias",
+      "model.layers.22.self_attn.v_proj.bias",
+      "model.layers.21.self_attn.v_proj.bias",
+      "model.layers.23.self_attn.v_proj.bias",
+      "model.layers.24.self_attn.v_proj.bias",
+      "model.layers.25.self_attn.v_proj.bias",
+      "model.layers.26.self_attn.v_proj.bias",
+      "model.layers.27.self_attn.v_proj.bias",
+      "model.layers.28.self_attn.v_proj.bias",
+      "model.layers.29.self_attn.v_proj.bias",
+      "visual.blocks.11.mlp.gate_up_proj",
+      "visual.blocks.11.mlp.gate_proj",
+      "visual.blocks.11.mlp.up_proj",
+      "visual.blocks.5.mlp.gate_up_proj",
+      "visual.blocks.5.mlp.gate_proj",
+      "visual.blocks.5.mlp.up_proj",
+      "visual.blocks.5.norm1",
+      "visual.blocks.6.mlp.gate_up_proj",
+      "visual.blocks.6.mlp.gate_proj",
+      "visual.blocks.6.mlp.up_proj",
+      "visual.blocks.7.mlp.gate_up_proj",
+      "visual.blocks.7.mlp.gate_proj",
+      "visual.blocks.7.mlp.up_proj",
+      "visual.blocks.8.mlp.gate_up_proj",
+      "visual.blocks.8.mlp.gate_proj",
+      "visual.blocks.8.mlp.up_proj",
+      "visual.blocks.9.mlp.gate_up_proj",
+      "visual.blocks.9.mlp.gate_proj",
+      "visual.blocks.9.mlp.up_proj",
+      "model.layers.22.mlp.gate.e_score_correction_bias",
+      "model.layers.10.mlp.gate.e_score_correction_bias",
+      "model.layers.11.mlp.gate.e_score_correction_bias",
+      "model.layers.12.mlp.gate.e_score_correction_bias",
+      "visual.blocks.12.mlp.down_proj",
+      "visual.blocks.12.mlp.gate_up_proj",
+      "visual.blocks.12.mlp.gate_proj",
+      "visual.blocks.12.mlp.up_proj",
+      "model.layers.14.mlp.gate.e_score_correction_bias",
+      "model.layers.13.mlp.gate.e_score_correction_bias",
+      "model.layers.15.mlp.gate.e_score_correction_bias",
+      "visual.blocks.13.mlp.down_proj",
+      "visual.blocks.13.mlp.gate_up_proj",
+      "visual.blocks.13.mlp.gate_proj",
+      "visual.blocks.13.mlp.up_proj",
+      "visual.blocks.14.mlp.down_proj",
+      "visual.blocks.14.mlp.gate_up_proj",
+      "visual.blocks.14.mlp.gate_proj",
+      "visual.blocks.14.mlp.up_proj",
+      "visual.blocks.15.mlp.down_proj",
+      "model.embed_tokens",
+      "model.layers.10.input_layernorm",
+      "model.layers.11.input_layernorm",
+      "model.layers.12.input_layernorm",
+      "model.layers.14.input_layernorm",
+      "model.layers.39.input_layernorm",
+      "model.layers.13.input_layernorm",
+      "model.layers.15.input_layernorm",
+      "model.layers.16.input_layernorm",
+      "model.layers.17.input_layernorm",
+      "model.layers.18.input_layernorm",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.16.post_attention_layernorm",
+      "visual.blocks.19.norm2",
+      "visual.blocks.20.norm2",
+      "visual.blocks.21.norm2",
+      "visual.blocks.22.norm2",
+      "visual.blocks.23.norm2",
+      "visual.blocks.10.norm2",
+      "visual.blocks.11.norm2",
+      "model.layers.2.mlp.gate.e_score_correction_bias",
+      "model.layers.4.mlp.gate.e_score_correction_bias",
+      "model.layers.3.mlp.gate.e_score_correction_bias",
+      "model.layers.1.mlp.gate.e_score_correction_bias",
+      "model.layers.8.mlp.gate.e_score_correction_bias",
+      "model.layers.6.mlp.gate.e_score_correction_bias",
+      "model.layers.7.mlp.gate.e_score_correction_bias",
+      "model.layers.5.mlp.gate.e_score_correction_bias",
+      "model.layers.9.mlp.gate.e_score_correction_bias",
+      "model.layers.2.self_attn.k_proj.bias",
+      "model.layers.4.self_attn.k_proj.bias",
+      "model.layers.3.self_attn.k_proj.bias",
+      "model.layers.0.self_attn.k_proj.bias",
+      "model.layers.1.self_attn.k_proj.bias",
+      "model.layers.8.self_attn.k_proj.bias",
+      "model.layers.6.self_attn.k_proj.bias",
+      "model.layers.7.self_attn.k_proj.bias",
+      "model.layers.5.self_attn.k_proj.bias",
+      "model.layers.9.self_attn.k_proj.bias",
+      "model.layers.34.self_attn.q_proj.bias",
+      "model.layers.35.self_attn.q_proj.bias",
+      "model.layers.36.self_attn.q_proj.bias",
+      "model.layers.37.self_attn.q_proj.bias",
+      "model.layers.13.self_attn.q_proj.bias",
+      "model.layers.15.self_attn.q_proj.bias",
+      "model.layers.16.self_attn.q_proj.bias",
+      "model.layers.17.self_attn.q_proj.bias",
+      "model.layers.18.self_attn.q_proj.bias",
+      "model.layers.19.self_attn.q_proj.bias",
+      "model.layers.40.self_attn.q_proj.bias",
+      "model.layers.41.self_attn.q_proj.bias",
+      "model.layers.42.self_attn.q_proj.bias",
+      "model.layers.24.self_attn.q_proj.bias",
+      "model.layers.25.self_attn.q_proj.bias",
+      "model.layers.26.self_attn.q_proj.bias",
+      "model.layers.27.self_attn.q_proj.bias",
+      "model.layers.28.self_attn.q_proj.bias",
+      "model.layers.29.self_attn.q_proj.bias",
+      "model.layers.30.self_attn.q_proj.bias",
+      "model.layers.25.mlp.gate.e_score_correction_bias",
+      "model.layers.26.mlp.gate.e_score_correction_bias",
+      "model.layers.27.mlp.gate.e_score_correction_bias",
+      "model.layers.28.mlp.gate.e_score_correction_bias",
+      "model.layers.39.mlp.gate.e_score_correction_bias",
+      "model.layers.16.mlp.gate.e_score_correction_bias",
+      "model.layers.17.mlp.gate.e_score_correction_bias",
+      "model.layers.18.mlp.gate.e_score_correction_bias",
+      "model.layers.19.mlp.gate.e_score_correction_bias",
+      "model.layers.20.mlp.gate.e_score_correction_bias",
+      "model.layers.36.mlp.gate.e_score_correction_bias",
+      "model.layers.37.mlp.gate.e_score_correction_bias",
+      "model.layers.38.mlp.gate.e_score_correction_bias",
+      "model.layers.21.mlp.gate.e_score_correction_bias",
+      "model.layers.23.mlp.gate.e_score_correction_bias",
+      "model.layers.24.mlp.gate.e_score_correction_bias",
+      "model.layers.22.self_attn.k_proj.bias",
+      "model.layers.21.self_attn.k_proj.bias",
+      "model.layers.23.self_attn.k_proj.bias",
+      "model.layers.24.self_attn.k_proj.bias",
+      "model.layers.25.self_attn.k_proj.bias",
+      "model.layers.26.self_attn.k_proj.bias",
+      "model.layers.27.self_attn.k_proj.bias",
+      "model.layers.28.self_attn.k_proj.bias",
+      "model.layers.38.self_attn.k_proj.bias",
+      "model.layers.39.self_attn.k_proj.bias",
+      "visual.blocks.0.norm1",
+      "visual.blocks.1.norm1",
+      "visual.blocks.2.norm1",
+      "visual.blocks.0.norm2",
+      "visual.blocks.1.norm2",
+      "visual.blocks.2.norm2",
+      "visual.blocks.3.norm1",
+      "visual.blocks.3.norm2",
+      "visual.blocks.4.norm1",
+      "visual.blocks.19.attn.qkv_proj",
+      "visual.blocks.20.attn.qkv_proj",
+      "visual.blocks.21.attn.qkv_proj",
+      "visual.blocks.22.attn.qkv_proj",
+      "visual.blocks.23.attn.qkv_proj",
+      "visual.blocks.10.attn.qkv_proj",
+      "visual.blocks.11.attn.qkv_proj",
+      "visual.blocks.4.norm2",
+      "visual.blocks.5.norm2",
+      "visual.blocks.6.norm2",
+      "visual.blocks.7.norm2",
+      "visual.blocks.8.norm2",
+      "visual.blocks.9.norm2",
+      "visual.blocks.20.mlp.gate_up_proj",
+      "visual.blocks.20.mlp.gate_proj",
+      "visual.blocks.20.mlp.up_proj",
+      "visual.blocks.21.mlp.down_proj",
+      "visual.blocks.21.mlp.gate_up_proj",
+      "visual.blocks.21.mlp.gate_proj",
+      "visual.blocks.21.mlp.up_proj",
+      "visual.blocks.22.mlp.down_proj",
+      "visual.blocks.22.mlp.gate_up_proj",
+      "visual.blocks.22.mlp.gate_proj",
+      "visual.blocks.22.mlp.up_proj",
+      "visual.blocks.23.mlp.down_proj",
+      "visual.blocks.23.mlp.gate_up_proj",
+      "visual.blocks.23.mlp.gate_proj",
+      "visual.blocks.23.mlp.up_proj",
+      "visual.blocks.10.mlp.down_proj",
+      "visual.blocks.10.mlp.gate_up_proj",
+      "visual.blocks.10.mlp.gate_proj",
+      "visual.blocks.10.mlp.up_proj",
+      "visual.blocks.11.mlp.down_proj",
+      "visual.embeddings.position_embedding",
+      "model.layers.15.mlp.gate",
+      "model.layers.16.mlp.gate",
+      "model.layers.17.mlp.gate",
+      "visual.merger.proj",
+      "model.layers.43.mlp.gate",
+      "model.layers.44.mlp.gate",
+      "model.layers.45.mlp.gate",
+      "model.layers.32.input_layernorm",
+      "model.layers.33.input_layernorm",
+      "model.layers.34.input_layernorm",
+      "model.layers.35.input_layernorm",
+      "model.layers.36.input_layernorm",
+      "model.layers.37.input_layernorm",
+      "model.layers.38.input_layernorm",
+      "model.layers.40.input_layernorm",
+      "model.layers.41.input_layernorm",
+      "model.layers.42.input_layernorm",
+      "model.layers.10.self_attn.k_proj.bias",
+      "model.layers.11.self_attn.k_proj.bias",
+      "model.layers.12.self_attn.k_proj.bias",
+      "model.layers.14.self_attn.k_proj.bias",
+      "model.layers.13.self_attn.k_proj.bias",
+      "model.layers.15.self_attn.k_proj.bias",
+      "model.layers.16.self_attn.k_proj.bias",
+      "model.layers.17.self_attn.k_proj.bias",
+      "model.layers.18.self_attn.k_proj.bias",
+      "model.layers.19.self_attn.k_proj.bias",
+      "visual.patch_embed.proj",
+      "model.layers.32.self_attn.k_proj.bias",
+      "model.layers.33.self_attn.k_proj.bias",
+      "model.layers.34.self_attn.k_proj.bias",
+      "model.layers.35.self_attn.k_proj.bias",
+      "model.layers.36.self_attn.k_proj.bias",
+      "model.layers.37.self_attn.k_proj.bias",
+      "model.layers.40.self_attn.k_proj.bias",
+      "model.layers.41.self_attn.k_proj.bias",
+      "model.layers.42.self_attn.k_proj.bias",
+      "model.layers.29.self_attn.k_proj.bias",
+      "lm_head",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.30.self_attn.k_proj.bias",
+      "model.layers.31.self_attn.k_proj.bias",
+      "model.layers.20.self_attn.k_proj.bias",
+      "model.layers.21.input_layernorm",
+      "model.layers.23.input_layernorm",
+      "model.layers.24.input_layernorm",
+      "model.layers.25.input_layernorm",
+      "model.layers.26.input_layernorm",
+      "model.layers.27.input_layernorm",
+      "model.layers.28.input_layernorm",
+      "model.layers.29.input_layernorm",
+      "model.layers.30.input_layernorm",
+      "model.layers.31.input_layernorm",
+      "visual.blocks.22.attn.proj",
+      "visual.blocks.23.attn.proj",
+      "visual.blocks.10.attn.proj",
+      "visual.blocks.11.attn.proj",
+      "visual.merger.down_proj",
+      "visual.merger.gate_up_proj",
+      "visual.merger.post_projection_norm.bias",
+      "model.norm",
+      "visual.blocks.16.norm1",
+      "visual.blocks.17.norm1",
+      "visual.blocks.18.norm1",
+      "visual.blocks.19.norm1",
+      "visual.blocks.20.norm1",
+      "visual.blocks.21.norm1",
+      "visual.blocks.22.norm1",
+      "visual.blocks.23.norm1",
+      "visual.blocks.10.norm1",
+      "visual.blocks.11.norm1",
+      "visual.blocks.18.norm2",
+      "model.layers.10.self_attn.v_proj.bias",
+      "model.layers.11.self_attn.v_proj.bias",
+      "model.layers.12.self_attn.v_proj.bias",
+      "model.layers.14.self_attn.v_proj.bias",
+      "model.layers.13.self_attn.v_proj.bias",
+      "model.layers.15.self_attn.v_proj.bias",
+      "model.layers.16.self_attn.v_proj.bias",
+      "model.layers.17.self_attn.v_proj.bias",
+      "model.layers.18.self_attn.v_proj.bias",
+      "model.layers.19.self_attn.v_proj.bias",
+      "visual.blocks.0.attn.qkv_proj",
+      "visual.blocks.1.attn.qkv_proj",
+      "visual.blocks.2.attn.qkv_proj",
+      "visual.blocks.3.attn.qkv_proj",
+      "visual.blocks.4.attn.qkv_proj",
+      "visual.blocks.5.attn.qkv_proj",
+      "visual.blocks.6.attn.qkv_proj",
+      "visual.blocks.7.attn.qkv_proj",
+      "visual.blocks.8.attn.qkv_proj",
+      "visual.blocks.9.attn.qkv_proj",
+      "model.layers.31.self_attn.v_proj.bias",
+      "model.layers.32.self_attn.v_proj.bias",
+      "model.layers.33.self_attn.v_proj.bias",
+      "model.layers.43.self_attn.v_proj.bias",
+      "model.layers.44.self_attn.v_proj.bias",
+      "model.layers.45.self_attn.v_proj.bias",
+      "visual.post_conv_layernorm",
+      "visual.blocks.0.mlp.down_proj",
+      "visual.blocks.0.mlp.gate_up_proj",
+      "visual.blocks.0.mlp.gate_proj",
+      "visual.blocks.0.mlp.up_proj",
+      "visual.blocks.1.mlp.down_proj",
+      "visual.blocks.1.mlp.gate_up_proj",
+      "visual.blocks.1.mlp.gate_proj",
+      "visual.blocks.1.mlp.up_proj",
+      "visual.blocks.2.mlp.down_proj",
+      "visual.blocks.2.mlp.gate_up_proj",
+      "visual.blocks.2.mlp.gate_proj",
+      "visual.blocks.2.mlp.up_proj",
+      "visual.blocks.3.mlp.down_proj",
+      "visual.blocks.3.mlp.gate_up_proj",
+      "visual.blocks.3.mlp.gate_proj",
+      "visual.blocks.3.mlp.up_proj",
+      "visual.blocks.4.mlp.down_proj",
+      "visual.blocks.4.mlp.gate_up_proj",
+      "visual.blocks.4.mlp.gate_proj",
+      "visual.blocks.4.mlp.up_proj",
+      "visual.merger.post_projection_norm",
+      "visual.blocks.12.attn.proj",
+      "visual.blocks.13.attn.proj",
+      "visual.blocks.14.attn.proj",
+      "visual.blocks.15.attn.proj",
+      "visual.blocks.16.attn.proj",
+      "visual.blocks.17.attn.proj",
+      "visual.blocks.18.attn.proj",
+      "visual.blocks.19.attn.proj",
+      "visual.blocks.20.attn.proj",
+      "visual.blocks.21.attn.proj",
+      "visual.blocks.5.mlp.down_proj",
+      "visual.blocks.6.mlp.down_proj",
+      "visual.blocks.7.mlp.down_proj",
+      "visual.blocks.8.mlp.down_proj",
+      "visual.blocks.9.mlp.down_proj",
+      "visual.blocks.0.attn.proj",
+      "visual.blocks.1.attn.proj",
+      "visual.blocks.2.attn.proj",
+      "visual.blocks.3.attn.proj",
+      "visual.blocks.4.attn.proj",
+      "visual.blocks.5.attn.proj",
+      "visual.blocks.6.attn.proj",
+      "visual.blocks.7.attn.proj",
+      "visual.blocks.8.attn.proj",
+      "visual.blocks.9.attn.proj",
+      "visual.blocks.12.attn.qkv_proj",
+      "visual.blocks.13.attn.qkv_proj",
+      "visual.blocks.14.attn.qkv_proj",
+      "visual.blocks.15.attn.qkv_proj",
+      "visual.blocks.16.attn.qkv_proj",
+      "visual.blocks.17.attn.qkv_proj",
+      "visual.blocks.18.attn.qkv_proj",
+      "model.layers.34.self_attn.v_proj.bias",
+      "model.layers.35.self_attn.v_proj.bias",
+      "model.layers.36.self_attn.v_proj.bias",
+      "model.layers.37.self_attn.v_proj.bias",
+      "model.layers.38.self_attn.v_proj.bias",
+      "model.layers.39.self_attn.v_proj.bias",
+      "model.layers.40.self_attn.v_proj.bias",
+      "model.layers.41.self_attn.v_proj.bias",
+      "model.layers.42.self_attn.v_proj.bias",
+      "model.layers.30.self_attn.v_proj.bias",
+      "model.layers.2.self_attn.q_proj.bias",
+      "model.layers.4.self_attn.q_proj.bias",
+      "model.layers.3.self_attn.q_proj.bias",
+      "model.layers.0.self_attn.q_proj.bias",
+      "model.layers.1.self_attn.q_proj.bias",
+      "model.layers.8.self_attn.q_proj.bias",
+      "model.layers.6.self_attn.q_proj.bias",
+      "model.layers.7.self_attn.q_proj.bias",
+      "model.layers.5.self_attn.q_proj.bias",
+      "model.layers.9.self_attn.q_proj.bias",
+      "model.layers.2.self_attn.v_proj.bias",
+      "model.layers.4.self_attn.v_proj.bias",
+      "model.layers.3.self_attn.v_proj.bias",
+      "model.layers.0.self_attn.v_proj.bias",
+      "model.layers.1.self_attn.v_proj.bias",
+      "model.layers.8.self_attn.v_proj.bias",
+      "model.layers.6.self_attn.v_proj.bias",
+      "model.layers.7.self_attn.v_proj.bias",
+      "model.layers.18.mlp.gate",
+      "model.layers.19.mlp.gate",
+      "model.layers.20.mlp.gate",
+      "model.layers.22.mlp.gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.23.mlp.gate",
+      "model.layers.24.mlp.gate",
+      "model.layers.25.mlp.gate",
+      "model.layers.26.mlp.gate",
+      "model.layers.27.mlp.gate",
+      "model.layers.43.mlp.gate.e_score_correction_bias",
+      "model.layers.44.mlp.gate.e_score_correction_bias",
+      "model.layers.19.input_layernorm",
+      "model.layers.20.input_layernorm",
+      "model.layers.22.input_layernorm",
+      "model.layers.43.input_layernorm",
+      "model.layers.44.input_layernorm",
+      "model.layers.45.input_layernorm",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.9.post_attention_layernorm",
+      "visual.downsample"
+    ],
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  }
+}

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"
+}

model-00001-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a735720a1b90aeaca4b33bf1ea7342c1d3f6d23d215d80e6b8f8e02efc25e482
+size 3304424656

model-00002-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f578bfc767ddae89d729baa42a0d5e77641248b2a9f26bf623a3b0d435ba6b51
+size 2687035496

model-00003-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2970b3ae9ceb82cff7afdc288f32651c06f985fd89046580dd3b218b51a04b55
+size 2687052432

model-00004-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c83edf82be40dc7335489c6aaba1bb6a2c8eda48e5384ee4cfcae70ba3d0e96
+size 2686400856

model-00005-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e071413ad3a162833bc471555e518eb5773b06b6bb4d575d5c6d0c0cdb6e5a
+size 2686400872

model-00006-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935c7d3d4fef073b79fd9779bde4f75654805f409c4aa3f3e703a994fe59036c
+size 2686400880

model-00007-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4c5c738ae0bdf0cd4d9f9ac08edf29832d4918d980c4ae7a6ccd1a23e74cb1
+size 2686476248

model-00008-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abd854f1975ad0635978c269c54c25dc0938c30e1d3694fb71ce1fbb3ec941d
+size 2687035456

model-00009-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82db6d4d4469cd1b841e0daa6464146d600ebcca164fda961f3f32adf535ac2
+size 2687036136

model-00010-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39027617db086d4e98f9ce926fe23a15ae987c5d716ac36e95c2b1452bece8d5
+size 2686978016

model-00011-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02e508321b9d91b1730c28b1b1d43cd218c41f6aa5c1337817b9e570ad5b2ab
+size 2686401776

model-00012-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349a80bc32084ba324bba6a304b1c8ddd2644acdaff8219375551b9193cbcda4
+size 2686401776

model-00013-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766be835b959e93ca43764a8304b5d2e33b35bbc925600e3471a7d9b8c007cda
+size 2686401800

model-00014-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae49b78b5ea4bea7d8b4c7785b5b3b5cf7bb5ed7f7e5d8c1daf2126ddeef2bd4
+size 2686552424

model-00015-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5210fc19b9ad17fffafedea389c9c74625f0e99255036d3f7886de5dd7a106
+size 2687036368

model-00016-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ecdc681a9b2b76fcdef074684dc8a6ac6050855c5800db4b71fdbfd9c82114c
+size 2664949784

model-00017-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4386cd6413c3b4d9dea337ffb1c08c0596eed49ca23633a8e59e7e89601caff4
+size 2685897056

model-00018-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74b849f83908e7372189a51dc1a59fb532228285b0d7d30912a1d285e09bf82
+size 2686401776

model-00019-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6da165c6adde01063adc4d82789e4bab77b698a772decd0f659fd1003cf5422
+size 2686401784

model-00020-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42dae1f28f88216ae20e5a717fa82b5d2b84730edb6cbc928f4caeb460384b86
+size 2686401808

model-00021-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194b29e243de8319be9474c4efed458c5f7a3720f78d5b7295469faaa8c5fa99
+size 2686584680

model-00022-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f6dea5e03e0884a091223b212bb6ebe3cca6df38a31be4814854e3a3f7426d
+size 2687036368

model-00023-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e0bd22e39caa2be184c7bc3b904a0933f85801aeffc48bfa10bb0a5cff08fd5
+size 2664936624

model-00024-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d248cb423d94d45e081ce77d2f1badd667f1bf2e74bd37f386fcd7ea30b2c2
+size 2685877960

model-00025-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093600ec5c0c7188d38be5e03282fd100d3897a7e12f4c79a8e80570ae9c7e46
+size 2686401784

model-00026-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856e5e4238d50c5f4be12c8e4b7014f009aecf30a9a2e339d916e5c4f2ce4b88
+size 2686401776

model-00027-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7614db65f32c19b851fbe0b04c64220c5d88d42d909b7eab6da5db751aaeb97
+size 2686401816

model-00028-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8527d3d926edddd1bfe85d8d996c0093840b7ac531bef48bd21f687900b1047
+size 2686616944

model-00029-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1409f521d390f3c6e5ba199e08e5469ffa3de8dc9db9635eacc14ac84afee3
+size 2687036368

model-00030-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefc0e54e5fa9b2e1bb0fc32f5575c65740700390a2663b6004867121a3ae6d8
+size 2685319472

model-00031-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ced8a7119c34cbb7365176e0b1212a1dd89f91c1f0982be603c30076902c0c7
+size 2688555128

model-00032-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb61eaa4bebaaf6fd51d09b4cc78e1eac15a45f7753b25b8e3a0d1171965ed5c
+size 2686401776

model-00033-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3db64148c46cb30c81d595b73fad9494f32b0c91ef04213608302a6dd9880cf
+size 2686401784

model-00034-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e04a703217d50d6a72ee65fe5aa902d8e87ce50e35573b47583de36d6b8879
+size 2686401824

model-00035-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0c180ddbcb5154926644a2153bd5ea074b26bbc03fd4e57953604d359e94ba
+size 2686692232

model-00036-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4156a4d8121f49c7f5a8e621c0e012994ccfcf0f6fd2870936bd0b957e9ddb64
+size 2687036368

model-00037-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c685268ed6c2d0e2c0adc2dcc11b0524fcaf875311ab4a36d33624edc57cb66
+size 2665868992

model-00038-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1998e39fc474136ad7dbde1df0c8edbc3461097b04fdb319c9e8535a90e7fedb
+size 2684838000

model-00039-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a7bbdc89eeed68d3a5a44d0dfae7459922c0fa431ac166a1003314dac8c0ec
+size 2686401784

model-00040-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c204ba63bab0740f9215cb6bb632f45b37edab2e662728c4b8d35e3c07da6934
+size 3646968248

model-00041-of-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1786b6e7ccba887db5ebfb7b2ebff06eb40f637acc9a33768b0a31a001e694b1
+size 1028463576

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"
+}