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

README.md

@@ -0,0 +1,18 @@
+---
+license: mit
+tags:
+- mlx
+---
+
+# mlx-community/GLM-4.5V-8bit
+This model was converted to MLX format from [`ZP2Test/GLM-4.5V`]() using mlx-vlm version **0.3.2**.
+Refer to the [original model card](https://huggingface.co/ZP2Test/GLM-4.5V) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/GLM-4.5V-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

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 +1,83 @@
+{
+    "architectures": [
+        "Glm4vMoeForConditionalGeneration"
+    ],
+    "model_type": "glm4v_moe",
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "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": 10944,
+        "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
+    },
+    "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": 10944,
+        "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
+    }
+}

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-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b78532c549e3d1950277251a3f383b4e9217a216f6b19490c1f16a023a6c87f
+size 5239992342

model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74395e1e030d41faa06bdd4561ff9544b18fd2d4074ffb0ec6cca4688edb50c
+size 4976707832

model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c733b4b3d903ceac158a72500ff9777af784977e3d6827451c6d090524a127
+size 4976707810

model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cb74e17fa0d9622fb8ec3afcb63c48041e04fc3695da2224c93c3061eabc19
+size 4976707794

model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c7ae29fbffd48e35a40935704497d0e8e99b04985faf81b220ef804c355b7c
+size 4976707805

model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4497cd22968ce53255eedf180d89ddd94c511f3a3f9f04ccfeb0db8b727264
+size 4976707848

model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99ddf8adb1f24896bc3ae364494dadfb5185c2e0fde66b792699013f3243d58
+size 4976707890

model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83894199774b6238cd0f2dd6fba023e4431823ff8418e59007d06079ae0cbf80
+size 4976707912

model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba79344689056c68b9ba9b88bb61d642effd56b4ec1efcf6ce9002b8fb92b92
+size 4976707920

model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653455001b9f5cf4f155c41c718ade35f491b39dde459ba3f4a382d5168ac63f
+size 4976707862

model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe29c049d2f0e80ecb5c25887a737d3f1aeb2a0d37619fcfecb134e5d54fe85
+size 4976707918

model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23cb9b3e7b31eed83d5ffd6f0d7f5eb5ed79125384993ea8b316aa2325a903aa
+size 4976707888

model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed12a8be273cdc2b830da0e156836498c2909478ecb30e8788d2901826caa48
+size 4976707896

model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b751a5c8bc091147e1ebf1432a270d63b62c75cb1006313ba88d2eb2dcb2b20e
+size 4976707898

model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6324f8c26bdff205c241fadcabb2ffc9214b26b76e402e66761ee7e3aef9b89a
+size 4976707926

model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a477150932b71ef16bce2fc27cddec67f89c9cfcad00533c80d657f78849db46
+size 4976707890

model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c449ca270452deccb2f4014f58367bc223d8dd4a1d8fe7d128cb55cc6334329
+size 4976707898

model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39e9956e4d4c8a5429154e511fb1ce361628a0789d2e3fba8e7ced8cdda16f2
+size 4976707902

model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f60527c8d50df4a7a5ed614d4c929c04146c58501b78a6dee9521f6b537a9a1
+size 4976707914

model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143ca5dc9e80497edc1b230d33f08abe6cf6b0821ba96da7c3fceb110bbe4e60
+size 4976707898

model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7e6e31dc722b4c3202b8cb942e29a925e48c683d0efaa2badca27b3b687c12
+size 4976707894

model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73c9b27c0fbb3dcd9af09e7dc12aec8ef7c9cd0640da5b0b115d66f7fa55614
+size 4976707868

model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ef95dee92becfdf4063fd65f30c1a2d8434052e3c9b0b6abd36f5cee0772fe
+size 4860817926

model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9879a691aa4def97e562a11e290c43356f67edd72af0d53e0be700ff79e4a91d
+size 659554652

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Glm4vImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "merge_size": 2,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 11760000,
+    "shortest_edge": 12544
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "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"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
+size 19970700

tokenizer_config.json

@@ -0,0 +1,326 @@
+{
+  "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",
+  "processor_class": "Glm4vProcessor",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

video_preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_image_size": {
+    "longest_edge": 47040000
+  },
+  "merge_size": 2,
+  "num_frames": 16,
+  "patch_size": 14,
+  "processor_class": "Glm4vProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 47040000,
+    "shortest_edge": 12544
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Glm4vVideoProcessor"
+}