Hugging Face's logo

mlboydaisuke
/
GLM-4.7-Flash-CoreAI

Text Generation
Core ML
core-ai
apple
Mixture of Experts
mla
on-device
metal
Model card Files
xet
 Community
mlboydaisuke commited on
Commit
a3f8528
·
verified ·
1 Parent(s): 2f8deff

GLM-4.7-Flash: sym8 gather_qmm bundle (2.6x, clean int8)

Browse files
Files changed (9) hide show
  1. .gitattributes +2 -0
  2. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/main.hash +1 -0
  3. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/main.mlirb +3 -0
  4. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/metadata.json +3 -0
  5. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/metadata.json +28 -0
  6. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/chat_template.jinja +86 -0
  7. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/special_tokens_map.json +36 -0
  8. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/tokenizer.json +3 -0
  9. gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/tokenizer_config.json +321 -0
.gitattributes CHANGED
@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  gpu-pipelined/glm_4_7_flash_decode_int8hu_block32_sym/glm_4_7_flash_decode_int8hu_block32_sym.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
37
  gpu-pipelined/glm_4_7_flash_decode_int8hu_block32_sym/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  gpu-pipelined/glm_4_7_flash_decode_int8hu_block32_sym/glm_4_7_flash_decode_int8hu_block32_sym.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
37
  gpu-pipelined/glm_4_7_flash_decode_int8hu_block32_sym/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
39
+ gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/main.hash ADDED
@@ -0,0 +1 @@
 
 
1
+ �LSk�p�BS�\���Fh�J��O��`>�M�H
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/main.mlirb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64c536bb370a14253e5aa5cede1cb4668da4a98d74f8fb860063e9a4de2a448
3
+ size 32119129387
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/glm_4_7_flash_decode_sym8_gather.aimodel/metadata.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "assetVersion" : "2.0"
3
+ }
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/metadata.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata_version": "0.2",
3
+ "kind": "llm",
4
+ "name": "glm_4_7_flash_decode_sym8_gather",
5
+ "assets": {
6
+ "main": "glm_4_7_flash_decode_sym8_gather.aimodel"
7
+ },
8
+ "language": {
9
+ "tokenizer": "zai-org/GLM-4.7-Flash",
10
+ "vocab_size": 154880,
11
+ "max_context_length": 8192,
12
+ "embedded_tokenizer": true,
13
+ "function_map": {
14
+ "main": [
15
+ "main"
16
+ ]
17
+ }
18
+ },
19
+ "source": {
20
+ "model_definition": "torch",
21
+ "hf_model_id": "zai-org/GLM-4.7-Flash"
22
+ },
23
+ "compression": null,
24
+ "compilation": {
25
+ "date": "2026-06-13T02:57:17.634982+00:00",
26
+ "targets": []
27
+ }
28
+ }
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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}<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 -%}
17
+ {%- macro visible_text(content) -%}
18
+ {%- if content is string -%}
19
+ {{- content }}
20
+ {%- elif content is iterable and content is not mapping -%}
21
+ {%- for item in content -%}
22
+ {%- if item is mapping and item.type == 'text' -%}
23
+ {{- item.text }}
24
+ {%- elif item is string -%}
25
+ {{- item }}
26
+ {%- endif -%}
27
+ {%- endfor -%}
28
+ {%- else -%}
29
+ {{- content }}
30
+ {%- endif -%}
31
+ {%- endmacro -%}
32
+ {%- set ns = namespace(last_user_index=-1) %}
33
+ {%- for m in messages %}
34
+ {%- if m.role == 'user' %}
35
+ {% set ns.last_user_index = loop.index0 -%}
36
+ {%- endif %}
37
+ {%- endfor %}
38
+ {% for m in messages %}
39
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
40
+ {%- elif m.role == 'assistant' -%}
41
+ <|assistant|>
42
+ {%- set reasoning_content = '' %}
43
+ {%- set content = visible_text(m.content) %}
44
+ {%- if m.reasoning_content is string %}
45
+ {%- set reasoning_content = m.reasoning_content %}
46
+ {%- else %}
47
+ {%- if '</think>' in content %}
48
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
49
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}
53
+ {{ '<think>' + reasoning_content.strip() + '</think>'}}
54
+ {%- else -%}
55
+ {{ '</think>' }}
56
+ {%- endif -%}
57
+ {%- if content.strip() -%}
58
+ {{ content.strip() }}
59
+ {%- endif -%}
60
+ {% if m.tool_calls %}
61
+ {% for tc in m.tool_calls %}
62
+ {%- if tc.function %}
63
+ {%- set tc = tc.function %}
64
+ {%- endif %}
65
+ {{- '<tool_call>' + tc.name -}}
66
+ {% 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 %}
67
+ {% endif %}
68
+ {%- elif m.role == 'tool' -%}
69
+ {%- if m.content is string -%}
70
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
71
+ {{- '<|observation|>' }}
72
+ {%- endif %}
73
+ {{- '<tool_response>' }}
74
+ {{- m.content }}
75
+ {{- '</tool_response>' }}
76
+ {%- else -%}
77
+ <|observation|>{% for tr in m.content %}
78
+ <tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}
79
+ {% endif -%}
80
+ {%- elif m.role == 'system' -%}
81
+ <|system|>{{ visible_text(m.content) }}
82
+ {%- endif -%}
83
+ {%- endfor -%}
84
+ {%- if add_generation_prompt -%}
85
+ <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
86
+ {%- endif -%}
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
22
+ "eos_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "pad_token": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
3
+ size 20217442
gpu-pipelined/glm_4_7_flash_decode_sym8_gather/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,321 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "154820": {
4
+ "content": "<|endoftext|>",
5
+ "single_word": false,
6
+ "lstrip": false,
7
+ "rstrip": false,
8
+ "normalized": false,
9
+ "special": true
10
+ },
11
+ "154821": {
12
+ "content": "[MASK]",
13
+ "single_word": false,
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "normalized": false,
17
+ "special": true
18
+ },
19
+ "154822": {
20
+ "content": "[gMASK]",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "special": true
26
+ },
27
+ "154823": {
28
+ "content": "[sMASK]",
29
+ "single_word": false,
30
+ "lstrip": false,
31
+ "rstrip": false,
32
+ "normalized": false,
33
+ "special": true
34
+ },
35
+ "154824": {
36
+ "content": "<sop>",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false,
41
+ "special": true
42
+ },
43
+ "154825": {
44
+ "content": "<eop>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ "154826": {
52
+ "content": "<|system|>",
53
+ "single_word": false,
54
+ "lstrip": false,
55
+ "rstrip": false,
56
+ "normalized": false,
57
+ "special": true
58
+ },
59
+ "154827": {
60
+ "content": "<|user|>",
61
+ "single_word": false,
62
+ "lstrip": false,
63
+ "rstrip": false,
64
+ "normalized": false,
65
+ "special": true
66
+ },
67
+ "154828": {
68
+ "content": "<|assistant|>",
69
+ "single_word": false,
70
+ "lstrip": false,
71
+ "rstrip": false,
72
+ "normalized": false,
73
+ "special": true
74
+ },
75
+ "154829": {
76
+ "content": "<|observation|>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": false,
81
+ "special": true
82
+ },
83
+ "154830": {
84
+ "content": "<|begin_of_image|>",
85
+ "single_word": false,
86
+ "lstrip": false,
87
+ "rstrip": false,
88
+ "normalized": false,
89
+ "special": true
90
+ },
91
+ "154831": {
92
+ "content": "<|end_of_image|>",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": false,
97
+ "special": true
98
+ },
99
+ "154832": {
100
+ "content": "<|begin_of_video|>",
101
+ "single_word": false,
102
+ "lstrip": false,
103
+ "rstrip": false,
104
+ "normalized": false,
105
+ "special": true
106
+ },
107
+ "154833": {
108
+ "content": "<|end_of_video|>",
109
+ "single_word": false,
110
+ "lstrip": false,
111
+ "rstrip": false,
112
+ "normalized": false,
113
+ "special": true
114
+ },
115
+ "154834": {
116
+ "content": "<|begin_of_audio|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ "154835": {
124
+ "content": "<|end_of_audio|>",
125
+ "single_word": false,
126
+ "lstrip": false,
127
+ "rstrip": false,
128
+ "normalized": false,
129
+ "special": true
130
+ },
131
+ "154836": {
132
+ "content": "<|begin_of_transcription|>",
133
+ "single_word": false,
134
+ "lstrip": false,
135
+ "rstrip": false,
136
+ "normalized": false,
137
+ "special": true
138
+ },
139
+ "154837": {
140
+ "content": "<|end_of_transcription|>",
141
+ "single_word": false,
142
+ "lstrip": false,
143
+ "rstrip": false,
144
+ "normalized": false,
145
+ "special": true
146
+ },
147
+ "154838": {
148
+ "content": "<|code_prefix|>",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": false,
153
+ "special": false
154
+ },
155
+ "154839": {
156
+ "content": "<|code_middle|>",
157
+ "single_word": false,
158
+ "lstrip": false,
159
+ "rstrip": false,
160
+ "normalized": false,
161
+ "special": false
162
+ },
163
+ "154840": {
164
+ "content": "<|code_suffix|>",
165
+ "single_word": false,
166
+ "lstrip": false,
167
+ "rstrip": false,
168
+ "normalized": false,
169
+ "special": false
170
+ },
171
+ "154841": {
172
+ "content": "<think>",
173
+ "single_word": false,
174
+ "lstrip": false,
175
+ "rstrip": false,
176
+ "normalized": false,
177
+ "special": false
178
+ },
179
+ "154842": {
180
+ "content": "</think>",
181
+ "single_word": false,
182
+ "lstrip": false,
183
+ "rstrip": false,
184
+ "normalized": false,
185
+ "special": false
186
+ },
187
+ "154843": {
188
+ "content": "<tool_call>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": false
194
+ },
195
+ "154844": {
196
+ "content": "</tool_call>",
197
+ "single_word": false,
198
+ "lstrip": false,
199
+ "rstrip": false,
200
+ "normalized": false,
201
+ "special": false
202
+ },
203
+ "154845": {
204
+ "content": "<tool_response>",
205
+ "single_word": false,
206
+ "lstrip": false,
207
+ "rstrip": false,
208
+ "normalized": false,
209
+ "special": false
210
+ },
211
+ "154846": {
212
+ "content": "</tool_response>",
213
+ "single_word": false,
214
+ "lstrip": false,
215
+ "rstrip": false,
216
+ "normalized": false,
217
+ "special": false
218
+ },
219
+ "154847": {
220
+ "content": "<arg_key>",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": false,
225
+ "special": false
226
+ },
227
+ "154848": {
228
+ "content": "</arg_key>",
229
+ "single_word": false,
230
+ "lstrip": false,
231
+ "rstrip": false,
232
+ "normalized": false,
233
+ "special": false
234
+ },
235
+ "154849": {
236
+ "content": "<arg_value>",
237
+ "single_word": false,
238
+ "lstrip": false,
239
+ "rstrip": false,
240
+ "normalized": false,
241
+ "special": false
242
+ },
243
+ "154850": {
244
+ "content": "</arg_value>",
245
+ "single_word": false,
246
+ "lstrip": false,
247
+ "rstrip": false,
248
+ "normalized": false,
249
+ "special": false
250
+ },
251
+ "154851": {
252
+ "content": "/nothink",
253
+ "single_word": false,
254
+ "lstrip": false,
255
+ "rstrip": false,
256
+ "normalized": false,
257
+ "special": false
258
+ },
259
+ "154852": {
260
+ "content": "<|begin_of_box|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": false
266
+ },
267
+ "154853": {
268
+ "content": "<|end_of_box|>",
269
+ "single_word": false,
270
+ "lstrip": false,
271
+ "rstrip": false,
272
+ "normalized": false,
273
+ "special": false
274
+ },
275
+ "154854": {
276
+ "content": "<|image|>",
277
+ "single_word": false,
278
+ "lstrip": false,
279
+ "rstrip": false,
280
+ "normalized": false,
281
+ "special": false
282
+ },
283
+ "154855": {
284
+ "content": "<|video|>",
285
+ "single_word": false,
286
+ "lstrip": false,
287
+ "rstrip": false,
288
+ "normalized": 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
+ ],
312
+ "clean_up_tokenization_spaces": false,
313
+ "do_lower_case": false,
314
+ "eos_token": "<|endoftext|>",
315
+ "extra_special_tokens": {},
316
+ "model_max_length": 128000,
317
+ "pad_token": "<|endoftext|>",
318
+ "padding_side": "left",
319
+ "remove_space": false,
320
+ "tokenizer_class": "PreTrainedTokenizer"
321
+ }