Hugging Face's logo

Intel
/
GLM-4.5V-int4-AutoRound

Safetensors
glm4v_moe
4-bit precision
auto-round
Model card Files
xet
Community
n1ck-guo commited on
Commit
522ba09
·
verified ·
1 Parent(s): c763fd9

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +118 -0
  3. config.json +90 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00012.safetensors +3 -0
  6. model-00002-of-00012.safetensors +3 -0
  7. model-00003-of-00012.safetensors +3 -0
  8. model-00004-of-00012.safetensors +3 -0
  9. model-00005-of-00012.safetensors +3 -0
  10. model-00006-of-00012.safetensors +3 -0
  11. model-00007-of-00012.safetensors +3 -0
  12. model-00008-of-00012.safetensors +3 -0
  13. model-00009-of-00012.safetensors +3 -0
  14. model-00010-of-00012.safetensors +3 -0
  15. model-00011-of-00012.safetensors +3 -0
  16. model-00012-of-00012.safetensors +3 -0
  17. model.safetensors.index.json +0 -0
  18. preprocessor_config.json +27 -0
  19. quantization_config.json +11 -0
  20. special_tokens_map.json +40 -0
  21. tokenizer.json +3 -0
  22. tokenizer_config.json +326 -0
  23. video_preprocessor_config.json +42 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- if tools -%}
3
+ <|system|>
4
+ # Tools
5
+
6
+ You may call one or more functions to assist with the user query.
7
+
8
+ You are provided with function signatures within <tools></tools> XML tags:
9
+ <tools>
10
+ {% for tool in tools %}
11
+ {{ tool | tojson(ensure_ascii=False) }}
12
+ {% endfor %}
13
+ </tools>
14
+
15
+ For each function call, output the function name and arguments within the following XML format:
16
+ <tool_call>{function-name}
17
+ <arg_key>{arg-key-1}</arg_key>
18
+ <arg_value>{arg-value-1}</arg_value>
19
+ <arg_key>{arg-key-2}</arg_key>
20
+ <arg_value>{arg-value-2}</arg_value>
21
+ ...
22
+ </tool_call>{%- endif -%}
23
+ {%- macro visible_text(content) -%}
24
+ {%- if content is string -%}
25
+ {{- content }}
26
+ {%- elif content is iterable and content is not mapping -%}
27
+ {%- for item in content -%}
28
+ {%- if item is mapping and item.type == 'text' -%}
29
+ {{- item.text }}
30
+ {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
31
+ <|begin_of_image|><|image|><|end_of_image|>
32
+ {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
33
+ <|begin_of_video|><|video|><|end_of_video|>
34
+ {%- elif item is string -%}
35
+ {{- item }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{- content }}
40
+ {%- endif -%}
41
+ {%- endmacro -%}
42
+ {%- set ns = namespace(last_user_index=-1) %}
43
+ {%- for m in messages %}
44
+ {%- if m.role == 'user' %}
45
+ {% set ns.last_user_index = loop.index0 -%}
46
+ {%- endif %}
47
+ {%- endfor %}
48
+ {% for m in messages %}
49
+ {%- if m.role == 'user' -%}<|user|>
50
+ {% if m.content is string %}
51
+ {{ m.content }}
52
+ {%- else %}
53
+ {%- for item in m.content %}
54
+ {% if item.type == 'video' or 'video' in item %}
55
+ <|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
56
+ <|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
57
+ {{ item.text }}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {%- endif %}
61
+ {{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
62
+ {%- elif m.role == 'assistant' -%}
63
+ <|assistant|>
64
+ {%- set reasoning_content = '' %}
65
+ {%- set content = visible_text(m.content) %}
66
+ {%- if m.reasoning_content is string %}
67
+ {%- set reasoning_content = m.reasoning_content %}
68
+ {%- else %}
69
+ {%- if '</think>' in content %}
70
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
71
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
72
+ {%- endif %}
73
+ {%- endif %}
74
+ {%- if loop.index0 > ns.last_user_index and reasoning_content -%}
75
+ {{ '\n<think>' + reasoning_content.strip() + '</think>'}}
76
+ {%- else -%}
77
+ {{ '\n<think></think>' }}
78
+ {%- endif -%}
79
+ {%- if content.strip() -%}
80
+ {{ '\n' + content.strip() }}
81
+ {%- endif -%}
82
+ {% if m.tool_calls %}
83
+ {% for tc in m.tool_calls %}
84
+ {%- if tc.function %}
85
+ {%- set tc = tc.function %}
86
+ {%- endif %}
87
+ {{ '\n<tool_call>' + tc.name }}
88
+ {% set _args = tc.arguments %}
89
+ {% for k, v in _args.items() %}
90
+ <arg_key>{{ k }}</arg_key>
91
+ <arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
92
+ {% endfor %}
93
+ </tool_call>{% endfor %}
94
+ {% endif %}
95
+ {%- elif m.role == 'tool' -%}
96
+ {%- if m.content is string -%}
97
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
98
+ {{- '<|observation|>' }}
99
+ {%- endif %}
100
+ {{- '\n<tool_response>\n' }}
101
+ {{- m.content }}
102
+ {{- '\n</tool_response>' }}
103
+ {%- else -%}
104
+ <|observation|>{% for tr in m.content %}
105
+
106
+ <tool_response>
107
+ {{ tr.output if tr.output is defined else tr }}
108
+ </tool_response>{% endfor -%}
109
+ {% endif -%}
110
+ {%- elif m.role == 'system' -%}
111
+ <|system|>
112
+ {{ visible_text(m.content) }}
113
+ {%- endif -%}
114
+ {%- endfor -%}
115
+ {%- if add_generation_prompt -%}
116
+ <|assistant|>
117
+ {{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
118
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4vMoeForConditionalGeneration"
4
+ ],
5
+ "image_end_token_id": 151340,
6
+ "image_start_token_id": 151339,
7
+ "image_token_id": 151363,
8
+ "model_type": "glm4v_moe",
9
+ "quantization_config": {
10
+ "autoround_version": "0.6.1.dev",
11
+ "bits": 4,
12
+ "block_name_to_quantize": "model.language_model.layers",
13
+ "data_type": "int",
14
+ "group_size": 128,
15
+ "low_gpu_mem_usage": true,
16
+ "packing_format": "auto_round:auto_gptq",
17
+ "quant_method": "auto-round",
18
+ "sym": true
19
+ },
20
+ "text_config": {
21
+ "attention_bias": true,
22
+ "attention_dropout": 0.0,
23
+ "eos_token_id": [
24
+ 151329,
25
+ 151336,
26
+ 151338
27
+ ],
28
+ "first_k_dense_replace": 1,
29
+ "head_dim": 128,
30
+ "hidden_act": "silu",
31
+ "hidden_size": 4096,
32
+ "image_end_token_id": 151340,
33
+ "image_start_token_id": 151339,
34
+ "image_token_id": 151363,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 10944,
37
+ "max_position_embeddings": 65536,
38
+ "model_type": "Glm4vMoe_text",
39
+ "moe_intermediate_size": 1408,
40
+ "n_group": 1,
41
+ "n_routed_experts": 128,
42
+ "n_shared_experts": 1,
43
+ "norm_topk_prob": true,
44
+ "num_attention_heads": 96,
45
+ "num_experts_per_tok": 8,
46
+ "num_hidden_layers": 46,
47
+ "num_key_value_heads": 8,
48
+ "pad_token_id": 151329,
49
+ "partial_rotary_factor": 0.5,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "mrope_section": [
53
+ 8,
54
+ 12,
55
+ 12
56
+ ],
57
+ "rope_type": "default"
58
+ },
59
+ "rope_theta": 10000.0,
60
+ "routed_scaling_factor": 1.0,
61
+ "topk_group": 1,
62
+ "torch_dtype": "bfloat16",
63
+ "use_cache": true,
64
+ "use_qk_norm": false,
65
+ "vocab_size": 151552
66
+ },
67
+ "torch_dtype": "bfloat16",
68
+ "transformers_version": "4.56.0.dev0",
69
+ "video_end_token_id": 151342,
70
+ "video_start_token_id": 151341,
71
+ "video_token_id": 151364,
72
+ "vision_config": {
73
+ "attention_bias": false,
74
+ "attention_dropout": 0.0,
75
+ "depth": 24,
76
+ "hidden_act": "silu",
77
+ "hidden_size": 1536,
78
+ "image_size": 336,
79
+ "in_channels": 3,
80
+ "initializer_range": 0.02,
81
+ "intermediate_size": 10944,
82
+ "model_type": "glm4v_moe",
83
+ "num_heads": 12,
84
+ "out_hidden_size": 4096,
85
+ "patch_size": 14,
86
+ "rms_norm_eps": 1e-05,
87
+ "spatial_merge_size": 2,
88
+ "temporal_patch_size": 2
89
+ }
90
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151329,
6
+ 151336,
7
+ 151338
8
+ ],
9
+ "pad_token_id": 151329,
10
+ "top_k": 1,
11
+ "top_p": 0.0001,
12
+ "transformers_version": "4.56.0.dev0"
13
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c16d692b21739bb74af86f3c86ebe060c391b6ef94a218137b172c30283292
3
+ size 4997892688
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ecad74bc7eb77b600ca77de299f30cac78b7ba3c15efd41f295d8364ba037e
3
+ size 4998652832
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3701c9f652c87f36f1bfbd2ada39ff0f4c602bbb092665a092a2fe52d120be
3
+ size 4998653800
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22d3a9f25964a03fb8505c734ae0c07d81270b48a992e65208db350d73ebc77
3
+ size 4998657808
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1fabda9345d6501ff340556f2c6c41ba9b81eef361968cf4e9d64be67de56f
3
+ size 4999706912
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9597d04646f44946ee9fe1cb7f8aef987c592510705d1ce3d5e86f0193ceacc3
3
+ size 4998424664
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ffdf29bce1aab3b9810bdd52cd392fb4450f8682c52f3b8bbefef1199472cd8
3
+ size 4998657648
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd8be469b861dded3b08249c5139da2923f9d525b526468a607667eb2b32c55
3
+ size 4998657680
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9f4acc7fb584c1a3c7e872413f05e6ccb02ec26031c19c1dc9b7b994f3f8ce2
3
+ size 4998657680
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81133942bb011b40eb9a18aa5c7e2c23f29d7db61ee8342a8a28a08580d17a2e
3
+ size 4998657672
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0281740a2776d2cc898e3f3ef60dd1d9261e64803f3be4c4438ebf26e998e6
3
+ size 4998657680
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656c54514263e39910f490251c16c3a18db670d0d397b409e0831ed8ed03e43a
3
+ size 4126984352
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Glm4vImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "merge_size": 2,
18
+ "patch_size": 14,
19
+ "processor_class": "Glm4vProcessor",
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 9633792,
24
+ "shortest_edge": 12544
25
+ },
26
+ "temporal_patch_size": 2
27
+ }
quantization_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "sym": true,
5
+ "data_type": "int",
6
+ "low_gpu_mem_usage": true,
7
+ "autoround_version": "0.6.1.dev",
8
+ "block_name_to_quantize": "model.language_model.layers",
9
+ "quant_method": "auto-round",
10
+ "packing_format": "auto_round:auto_gptq"
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>",
17
+ "<|begin_of_audio|>",
18
+ "<|end_of_audio|>",
19
+ "<|begin_of_transcription|>",
20
+ "<|end_of_transcription|>",
21
+ "<|code_prefix|>",
22
+ "<|code_middle|>",
23
+ "<|code_suffix|>",
24
+ "/nothink"
25
+ ],
26
+ "eos_token": {
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
3
+ size 19970700
tokenizer_config.json ADDED
@@ -0,0 +1,326 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151343": {
116
+ "content": "<|begin_of_audio|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "151344": {
124
+ "content": "<|end_of_audio|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "151345": {
132
+ "content": "<|begin_of_transcription|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "151346": {
140
+ "content": "<|end_of_transcription|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "151347": {
148
+ "content": "<|code_prefix|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "151348": {
156
+ "content": "<|code_middle|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "151349": {
164
+ "content": "<|code_suffix|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "151350": {
172
+ "content": "<think>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151351": {
180
+ "content": "</think>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "151352": {
188
+ "content": "<tool_call>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "151353": {
196
+ "content": "</tool_call>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "151354": {
204
+ "content": "<tool_response>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "151355": {
212
+ "content": "</tool_response>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "151356": {
220
+ "content": "<arg_key>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "151357": {
228
+ "content": "</arg_key>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "151358": {
236
+ "content": "<arg_value>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "151359": {
244
+ "content": "</arg_value>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "151360": {
252
+ "content": "/nothink",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "151361": {
260
+ "content": "<|begin_of_box|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "151362": {
268
+ "content": "<|end_of_box|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "151363": {
276
+ "content": "<|image|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "151364": {
284
+ "content": "<|video|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ }
291
+ },
292
+ "additional_special_tokens": [
293
+ "<|endoftext|>",
294
+ "[MASK]",
295
+ "[gMASK]",
296
+ "[sMASK]",
297
+ "<sop>",
298
+ "<eop>",
299
+ "<|system|>",
300
+ "<|user|>",
301
+ "<|assistant|>",
302
+ "<|observation|>",
303
+ "<|begin_of_image|>",
304
+ "<|end_of_image|>",
305
+ "<|begin_of_video|>",
306
+ "<|end_of_video|>",
307
+ "<|begin_of_audio|>",
308
+ "<|end_of_audio|>",
309
+ "<|begin_of_transcription|>",
310
+ "<|end_of_transcription|>",
311
+ "<|code_prefix|>",
312
+ "<|code_middle|>",
313
+ "<|code_suffix|>",
314
+ "/nothink"
315
+ ],
316
+ "clean_up_tokenization_spaces": false,
317
+ "do_lower_case": false,
318
+ "eos_token": "<|endoftext|>",
319
+ "extra_special_tokens": {},
320
+ "model_max_length": 128000,
321
+ "pad_token": "<|endoftext|>",
322
+ "padding_side": "left",
323
+ "processor_class": "Glm4vProcessor",
324
+ "remove_space": false,
325
+ "tokenizer_class": "PreTrainedTokenizerFast"
326
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": true,
13
+ "fps": 2,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_image_size": {
26
+ "longest_edge": 47040000
27
+ },
28
+ "merge_size": 2,
29
+ "num_frames": 16,
30
+ "patch_size": 14,
31
+ "processor_class": "Glm4vProcessor",
32
+ "resample": 3,
33
+ "rescale_factor": 0.00392156862745098,
34
+ "size": {
35
+ "longest_edge": 47040000,
36
+ "shortest_edge": 12544
37
+ },
38
+ "size_divisor": null,
39
+ "temporal_patch_size": 2,
40
+ "video_metadata": null,
41
+ "video_processor_type": "Glm4vVideoProcessor"
42
+ }