Hugging Face's logo

mlx-community
/
GLM-4.6V-mxfp4

Image-Text-to-Text
Transformers
Safetensors
MLX
Chinese
English
glm4v_moe
conversational
4-bit precision
Model card Files
xet
 Community
foobar2333 commited on
Commit
7c87163
·
verified ·
1 Parent(s): 1b322cf

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. README.md +23 -0
  3. chat_template.jinja +141 -0
  4. config.json +266 -0
  5. generation_config.json +14 -0
  6. model-00001-of-00012.safetensors +3 -0
  7. model-00002-of-00012.safetensors +3 -0
  8. model-00003-of-00012.safetensors +3 -0
  9. model-00004-of-00012.safetensors +3 -0
  10. model-00005-of-00012.safetensors +3 -0
  11. model-00006-of-00012.safetensors +3 -0
  12. model-00007-of-00012.safetensors +3 -0
  13. model-00008-of-00012.safetensors +3 -0
  14. model-00009-of-00012.safetensors +3 -0
  15. model-00010-of-00012.safetensors +3 -0
  16. model-00011-of-00012.safetensors +3 -0
  17. model-00012-of-00012.safetensors +3 -0
  18. model.safetensors.index.json +0 -0
  19. preprocessor_config.json +11 -0
  20. special_tokens_map.json +42 -0
  21. tokenizer.json +3 -0
  22. tokenizer_config.json +327 -0
  23. video_preprocessor_config.json +11 -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
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - zh
4
+ - en
5
+ library_name: transformers
6
+ license: mit
7
+ pipeline_tag: image-text-to-text
8
+ tags:
9
+ - mlx
10
+ ---
11
+
12
+ # mlx-community/GLM-4.6V-mxfp4
13
+ This model was converted to MLX format from [`zai-org/GLM-4.6V`]() using mlx-vlm version **0.3.4**.
14
+ Refer to the [original model card](https://huggingface.co/zai-org/GLM-4.6V) for more details on the model.
15
+ ## Use with mlx
16
+
17
+ ```bash
18
+ pip install -U mlx-vlm
19
+ ```
20
+
21
+ ```bash
22
+ python -m mlx_vlm.generate --model mlx-community/GLM-4.6V-mxfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
23
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {% elif m.content is iterable and m.content is not mapping %}
104
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
105
+ {{- '<|observation|>' }}
106
+ {%- endif %}
107
+ {{- '\n<tool_response>\n' }}
108
+ {%- for tr in m.content -%}
109
+ {%- if tr is mapping and tr.type is defined -%}
110
+ {%- set t = tr.type | lower -%}
111
+ {%- if t == 'text' and tr.text is defined -%}
112
+ {{ tr.text }}
113
+ {%- elif t in ['image', 'image_url'] -%}
114
+ <|begin_of_image|><|image|><|end_of_image|>
115
+ {%- elif t in ['video', 'video_url'] -%}
116
+ <|begin_of_video|><|video|><|end_of_video|>
117
+ {%- else -%}
118
+ {{ tr | tojson(ensure_ascii=False) }}
119
+ {%- endif -%}
120
+ {%- else -%}
121
+ {{ tr.output if tr.output is defined else tr }}
122
+ {%- endif -%}
123
+ {%- endfor -%}
124
+ {{- '\n</tool_response>' }}
125
+ {%- else -%}
126
+ <|observation|>{% for tr in m.content %}
127
+
128
+ <tool_response>
129
+ {{ tr.output if tr.output is defined else tr }}
130
+ </tool_response>{% endfor -%}
131
+ {% endif -%}
132
+ {# ====== 逻辑结束 ====== #}
133
+ {%- elif m.role == 'system' -%}
134
+ <|system|>
135
+ {{ visible_text(m.content) }}
136
+ {%- endif -%}
137
+ {%- endfor -%}
138
+ {%- if add_generation_prompt -%}
139
+ <|assistant|>
140
+ {{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
141
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "Glm4vMoeForConditionalGeneration"
5
+ ],
6
+ "bad_words_ids": null,
7
+ "begin_suppress_tokens": null,
8
+ "bos_token_id": null,
9
+ "chunk_size_feed_forward": 0,
10
+ "cross_attention_hidden_size": null,
11
+ "decoder_start_token_id": null,
12
+ "diversity_penalty": 0.0,
13
+ "do_sample": false,
14
+ "dtype": null,
15
+ "early_stopping": false,
16
+ "encoder_no_repeat_ngram_size": 0,
17
+ "eos_token_id": null,
18
+ "exponential_decay_length_penalty": null,
19
+ "finetuning_task": null,
20
+ "forced_bos_token_id": null,
21
+ "forced_eos_token_id": null,
22
+ "id2label": {
23
+ "0": "LABEL_0",
24
+ "1": "LABEL_1"
25
+ },
26
+ "image_end_token_id": 151340,
27
+ "image_start_token_id": 151339,
28
+ "image_token_id": 151363,
29
+ "is_decoder": false,
30
+ "is_encoder_decoder": false,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1
34
+ },
35
+ "length_penalty": 1.0,
36
+ "max_length": 20,
37
+ "min_length": 0,
38
+ "model_type": "glm4v_moe",
39
+ "no_repeat_ngram_size": 0,
40
+ "num_beam_groups": 1,
41
+ "num_beams": 1,
42
+ "num_return_sequences": 1,
43
+ "output_attentions": false,
44
+ "output_hidden_states": false,
45
+ "output_scores": false,
46
+ "pad_token_id": null,
47
+ "prefix": null,
48
+ "problem_type": null,
49
+ "pruned_heads": {},
50
+ "quantization": {
51
+ "group_size": 32,
52
+ "bits": 4,
53
+ "mode": "mxfp4"
54
+ },
55
+ "quantization_config": {
56
+ "group_size": 32,
57
+ "bits": 4,
58
+ "mode": "mxfp4"
59
+ },
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "sep_token_id": null,
65
+ "suppress_tokens": null,
66
+ "task_specific_params": null,
67
+ "temperature": 1.0,
68
+ "text_config": {
69
+ "return_dict": true,
70
+ "output_hidden_states": false,
71
+ "torchscript": false,
72
+ "dtype": "bfloat16",
73
+ "pruned_heads": {},
74
+ "tie_word_embeddings": false,
75
+ "chunk_size_feed_forward": 0,
76
+ "is_encoder_decoder": false,
77
+ "is_decoder": false,
78
+ "cross_attention_hidden_size": null,
79
+ "add_cross_attention": false,
80
+ "tie_encoder_decoder": false,
81
+ "architectures": null,
82
+ "finetuning_task": null,
83
+ "id2label": {
84
+ "0": "LABEL_0",
85
+ "1": "LABEL_1"
86
+ },
87
+ "label2id": {
88
+ "LABEL_0": 0,
89
+ "LABEL_1": 1
90
+ },
91
+ "task_specific_params": null,
92
+ "problem_type": null,
93
+ "tokenizer_class": null,
94
+ "prefix": null,
95
+ "bos_token_id": null,
96
+ "pad_token_id": 151329,
97
+ "eos_token_id": [
98
+ 151329,
99
+ 151336,
100
+ 151338
101
+ ],
102
+ "sep_token_id": null,
103
+ "decoder_start_token_id": null,
104
+ "max_length": 20,
105
+ "min_length": 0,
106
+ "do_sample": false,
107
+ "early_stopping": false,
108
+ "num_beams": 1,
109
+ "temperature": 1.0,
110
+ "top_k": 50,
111
+ "top_p": 1.0,
112
+ "typical_p": 1.0,
113
+ "repetition_penalty": 1.0,
114
+ "length_penalty": 1.0,
115
+ "no_repeat_ngram_size": 0,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "bad_words_ids": null,
118
+ "num_return_sequences": 1,
119
+ "output_scores": false,
120
+ "return_dict_in_generate": false,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "remove_invalid_values": false,
124
+ "exponential_decay_length_penalty": null,
125
+ "suppress_tokens": null,
126
+ "begin_suppress_tokens": null,
127
+ "num_beam_groups": 1,
128
+ "diversity_penalty": 0.0,
129
+ "_name_or_path": "",
130
+ "head_dim": 128,
131
+ "model_type": "Glm4vMoe_text",
132
+ "num_nextn_predict_layers": 0,
133
+ "qk_layernorm": false,
134
+ "rope_parameters": {
135
+ "mrope_section": [
136
+ 8,
137
+ 12,
138
+ 12
139
+ ],
140
+ "partial_rotary_factor": 0.5,
141
+ "rope_theta": 500000,
142
+ "rope_type": "default"
143
+ },
144
+ "use_qk_norm": false,
145
+ "tf_legacy_loss": false,
146
+ "use_bfloat16": false,
147
+ "vocab_size": 151552,
148
+ "max_position_embeddings": 131072,
149
+ "hidden_size": 4096,
150
+ "intermediate_size": 10944,
151
+ "num_hidden_layers": 46,
152
+ "num_attention_heads": 96,
153
+ "partial_rotary_factor": 0.5,
154
+ "num_key_value_heads": 8,
155
+ "hidden_act": "silu",
156
+ "initializer_range": 0.02,
157
+ "rms_norm_eps": 1e-05,
158
+ "use_cache": true,
159
+ "rope_theta": 10000.0,
160
+ "rope_scaling": null,
161
+ "attention_bias": true,
162
+ "attention_dropout": 0.0,
163
+ "moe_intermediate_size": 1408,
164
+ "num_experts_per_tok": 8,
165
+ "n_group": 1,
166
+ "topk_group": 1,
167
+ "n_shared_experts": 1,
168
+ "n_routed_experts": 128,
169
+ "routed_scaling_factor": 1.0,
170
+ "first_k_dense_replace": 1,
171
+ "norm_topk_prob": true,
172
+ "output_attentions": false
173
+ },
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": false,
177
+ "tokenizer_class": null,
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torchscript": false,
181
+ "transformers_version": "4.57.1",
182
+ "typical_p": 1.0,
183
+ "use_bfloat16": false,
184
+ "video_end_token_id": 151342,
185
+ "video_start_token_id": 151341,
186
+ "video_token_id": 151364,
187
+ "vision_config": {
188
+ "return_dict": true,
189
+ "output_hidden_states": false,
190
+ "torchscript": false,
191
+ "dtype": null,
192
+ "pruned_heads": {},
193
+ "tie_word_embeddings": true,
194
+ "chunk_size_feed_forward": 0,
195
+ "is_encoder_decoder": false,
196
+ "is_decoder": false,
197
+ "cross_attention_hidden_size": null,
198
+ "add_cross_attention": false,
199
+ "tie_encoder_decoder": false,
200
+ "architectures": null,
201
+ "finetuning_task": null,
202
+ "id2label": {
203
+ "0": "LABEL_0",
204
+ "1": "LABEL_1"
205
+ },
206
+ "label2id": {
207
+ "LABEL_0": 0,
208
+ "LABEL_1": 1
209
+ },
210
+ "task_specific_params": null,
211
+ "problem_type": null,
212
+ "tokenizer_class": null,
213
+ "prefix": null,
214
+ "bos_token_id": null,
215
+ "pad_token_id": null,
216
+ "eos_token_id": null,
217
+ "sep_token_id": null,
218
+ "decoder_start_token_id": null,
219
+ "max_length": 20,
220
+ "min_length": 0,
221
+ "do_sample": false,
222
+ "early_stopping": false,
223
+ "num_beams": 1,
224
+ "temperature": 1.0,
225
+ "top_k": 50,
226
+ "top_p": 1.0,
227
+ "typical_p": 1.0,
228
+ "repetition_penalty": 1.0,
229
+ "length_penalty": 1.0,
230
+ "no_repeat_ngram_size": 0,
231
+ "encoder_no_repeat_ngram_size": 0,
232
+ "bad_words_ids": null,
233
+ "num_return_sequences": 1,
234
+ "output_scores": false,
235
+ "return_dict_in_generate": false,
236
+ "forced_bos_token_id": null,
237
+ "forced_eos_token_id": null,
238
+ "remove_invalid_values": false,
239
+ "exponential_decay_length_penalty": null,
240
+ "suppress_tokens": null,
241
+ "begin_suppress_tokens": null,
242
+ "num_beam_groups": 1,
243
+ "diversity_penalty": 0.0,
244
+ "_name_or_path": "",
245
+ "hidden_dropout_prob": 0.0,
246
+ "model_type": "glm4v_moe",
247
+ "tf_legacy_loss": false,
248
+ "use_bfloat16": false,
249
+ "depth": 24,
250
+ "hidden_size": 1536,
251
+ "hidden_act": "silu",
252
+ "num_heads": 12,
253
+ "in_channels": 3,
254
+ "image_size": 336,
255
+ "patch_size": 14,
256
+ "spatial_merge_size": 2,
257
+ "temporal_patch_size": 2,
258
+ "out_hidden_size": 4096,
259
+ "intermediate_size": 10944,
260
+ "initializer_range": 0.02,
261
+ "rms_norm_eps": 1e-05,
262
+ "attention_bias": false,
263
+ "attention_dropout": 0.0,
264
+ "output_attentions": false
265
+ }
266
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_p": 0.6,
11
+ "temperature": 0.8,
12
+ "top_k": 2,
13
+ "transformers_version": "5.0.0rc0"
14
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3665199b0132f4b1e6034dc7b0ec4ba74bbd1c5a64e2e33c4bbeedc15755138e
3
+ size 5116168022
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cae710748f39096cf3eb2c535c87bdba2894d9885b4054048f193069c352c3b
3
+ size 5348000024
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff6cd704af66761eb56ccb0901f3b7aae3300380e7792af61585fc36b398d74
3
+ size 5001969955
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a526d4844c95eef57637fa5158a922644ec92373ed87169f6e4e244ffda324
3
+ size 5348000133
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cead56a8bd45b4a9d08f75aea82693d3a336e14e71914588fcc99ba74a68a20
3
+ size 5070192201
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca66b7583f71c66eaef3696e5fef7da332a7357911a38e3b26df9fc40c46a9b4
3
+ size 5348000121
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedb73a3e5c3b6f4baefae71d013826fdf1c7793bb4de2899798c8a18880b817
3
+ size 5001970058
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022c0acb22dc6f8444ff4675d0625df904311bdbb5b753ede032887e53431220
3
+ size 5348000149
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e010132cb28912d61b4cd7afcbc40295008fe27ba63180a7f3c090486eb3f39
3
+ size 5001970022
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:682a2c336eaf3082bb165e95b4de6ec44381a527d4fcb929c1bb66f2ba107f9e
3
+ size 5348000137
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2dd3534e82cd2e92c0d7589d432563b6c4f232e55ba4ac2832d6f994b3d60ed
3
+ size 5070192209
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6540100969d9c7ab4a9dc59bfa24c2d23606eaea900bf258a81b9f1ad1b7130f
3
+ size 1516547057
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {"shortest_edge": 12544, "longest_edge": 9633792},
3
+ "do_rescale": true,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [0.48145466, 0.4578275, 0.40821073],
8
+ "image_std": [0.26862954, 0.26130258, 0.27577711],
9
+ "image_processor_type": "Glm46VImageProcessor",
10
+ "processor_class": "Glm46VProcessor"
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|image|>",
20
+ "<|video|>",
21
+ "<|begin_of_transcription|>",
22
+ "<|end_of_transcription|>",
23
+ "<|code_prefix|>",
24
+ "<|code_middle|>",
25
+ "<|code_suffix|>",
26
+ "/nothink"
27
+ ],
28
+ "eos_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2ff52959093921034528ecd6a59926e5fd543f56f94f2a0034ed4ba458c0a86
3
+ size 19970698
tokenizer_config.json ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true
282
+ },
283
+ "151364": {
284
+ "content": "<|video|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
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
+ "<|image|>",
310
+ "<|video|>",
311
+ "<|begin_of_transcription|>",
312
+ "<|end_of_transcription|>",
313
+ "<|code_prefix|>",
314
+ "<|code_middle|>",
315
+ "<|code_suffix|>",
316
+ "/nothink"
317
+ ],
318
+ "clean_up_tokenization_spaces": false,
319
+ "do_lower_case": false,
320
+ "eos_token": "<|endoftext|>",
321
+ "extra_special_tokens": {},
322
+ "model_max_length": 128000,
323
+ "pad_token": "<|endoftext|>",
324
+ "padding_side": "left",
325
+ "remove_space": false,
326
+ "tokenizer_class": "PreTrainedTokenizerFast"
327
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {"shortest_edge": 12544, "longest_edge": 47040000},
3
+ "do_rescale": true,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [0.48145466, 0.4578275, 0.40821073],
8
+ "image_std": [0.26862954, 0.26130258, 0.27577711],
9
+ "video_processor_type": "Glm46VVideoProcessor",
10
+ "processor_class": "Glm46VProcessor"
11
+ }