Hugging Face's logo

Pinaster
/
GLM-5.2_5layer

Safetensors
glm_moe_dsa
Model card Files
xet
 Community
Pinaster commited on
Commit
0957795
·
verified ·
1 Parent(s): fee26f7

Add GLM-5.2 5-layer pruned model for CI smoke tests

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +119 -0
  3. config.json +223 -0
  4. generation_config.json +12 -0
  5. model-00001-of-00282.safetensors +3 -0
  6. model-00002-of-00282.safetensors +3 -0
  7. model-00038-of-00282.safetensors +3 -0
  8. model-00075-of-00282.safetensors +3 -0
  9. model-00076-of-00282.safetensors +3 -0
  10. model-00077-of-00282.safetensors +3 -0
  11. model-00078-of-00282.safetensors +3 -0
  12. model-00079-of-00282.safetensors +3 -0
  13. model-00116-of-00282.safetensors +3 -0
  14. model-00117-of-00282.safetensors +3 -0
  15. model-00118-of-00282.safetensors +3 -0
  16. model-00119-of-00282.safetensors +3 -0
  17. model-00120-of-00282.safetensors +3 -0
  18. model-00282-of-00282.safetensors +3 -0
  19. model.safetensors.index.json +0 -0
  20. tokenizer.json +3 -0
  21. tokenizer_config.json +33 -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 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- set effective_reasoning_effort = 'high' if reasoning_effort is defined and reasoning_effort == 'high' else 'max' -%}
3
+ {%- if (enable_thinking is not defined or enable_thinking) and effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}
4
+ {%- if tools -%}
5
+ {%- macro tool_to_json(tool) -%}
6
+ {%- set ns_tool = namespace(first=true) -%}
7
+ {{ '{' -}}
8
+ {%- for k, v in tool.items() -%}
9
+ {%- if k != 'defer_loading' and k != 'strict' -%}
10
+ {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}
11
+ {%- set ns_tool.first = false -%}
12
+ "{{ k }}": {{ v | tojson(ensure_ascii=False) }}
13
+ {%- endif -%}
14
+ {%- endfor -%}
15
+ {{- '}' -}}
16
+ {%- endmacro -%}
17
+ <|system|>
18
+ # Tools
19
+
20
+ You may call one or more functions to assist with the user query.
21
+
22
+ You are provided with function signatures within <tools></tools> XML tags:
23
+ <tools>
24
+ {% for tool in tools %}
25
+ {%- if 'function' in tool -%}
26
+ {%- set tool = tool['function'] -%}
27
+ {%- endif -%}
28
+ {% if tool.defer_loading is not defined or not tool.defer_loading %}
29
+ {{ tool_to_json(tool) }}
30
+ {% endif %}
31
+ {% endfor %}
32
+ </tools>
33
+
34
+ For each function call, output the function name and arguments within the following XML format:
35
+ <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 -%}
36
+ {%- macro visible_text(content) -%}
37
+ {%- if content is string -%}
38
+ {{- content }}
39
+ {%- elif content is iterable and content is not mapping -%}
40
+ {%- for item in content -%}
41
+ {%- if item is mapping and item.type == 'text' -%}
42
+ {{- item.text }}
43
+ {%- elif item is string -%}
44
+ {{- item }}
45
+ {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
46
+ {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
47
+ {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
48
+ {%- endif -%}
49
+ {%- endfor -%}
50
+ {%- else -%}
51
+ {{- content }}
52
+ {%- endif -%}
53
+ {%- endmacro -%}
54
+ {%- set ns = namespace(last_user_index=-1) -%}
55
+ {%- for m in messages %}
56
+ {%- if m.role == 'user' %}
57
+ {%- set ns.last_user_index = loop.index0 -%}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {%- for m in messages -%}
61
+ {%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}
62
+ {%- elif m.role == 'assistant' -%}
63
+ <|assistant|>
64
+ {%- set content = visible_text(m.content) %}
65
+ {%- if m.reasoning_content is string %}
66
+ {%- set reasoning_content = m.reasoning_content %}
67
+ {%- elif '</think>' in content %}
68
+ {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}
69
+ {%- set content = content.split('</think>')[-1] %}
70
+ {%- endif %}
71
+ {%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}
72
+ {{ '<think>' + reasoning_content + '</think>'}}
73
+ {%- else -%}
74
+ {{ '<think></think>' }}
75
+ {%- endif -%}
76
+ {%- if content.strip() -%}
77
+ {{ content.strip() }}
78
+ {%- endif -%}
79
+ {% if m.tool_calls %}
80
+ {% for tc in m.tool_calls %}
81
+ {%- if tc.function %}
82
+ {%- set tc = tc.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>' + tc.name -}}
85
+ {% 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 %}
86
+ {% endif %}
87
+ {%- elif m.role == 'tool' -%}
88
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
89
+ {{- '<|observation|>' -}}
90
+ {%- endif %}
91
+ {%- if m.content is string -%}
92
+ {{- '<tool_response>' + m.content + '</tool_response>' -}}
93
+ {%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == "tool_reference" -%}
94
+ {{- '<tool_response><tools>\n' -}}
95
+ {% for tr in m.content %}
96
+ {%- for tool in tools -%}
97
+ {%- if 'function' in tool -%}
98
+ {%- set tool = tool['function'] -%}
99
+ {%- endif -%}
100
+ {%- if tool.name == tr.name -%}
101
+ {{- tool_to_json(tool) + '\n' -}}
102
+ {%- endif -%}
103
+ {%- endfor -%}
104
+ {%- endfor -%}
105
+ {{- '</tools></tool_response>' -}}
106
+ {%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%}
107
+ {%- for tr in m.content -%}
108
+ {{- '<tool_response>' + tr.output + '</tool_response>' -}}
109
+ {%- endfor -%}
110
+ {%- else -%}
111
+ {{- '<tool_response>' + visible_text(m.content) + '</tool_response>' -}}
112
+ {% endif -%}
113
+ {%- elif m.role == 'system' -%}
114
+ <|system|>{{ visible_text(m.content) }}
115
+ {%- endif -%}
116
+ {%- endfor -%}
117
+ {%- if add_generation_prompt -%}
118
+ <|assistant|>{{- '<think></think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}
119
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GlmMoeDsaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": [
9
+ 154820,
10
+ 154827,
11
+ 154829
12
+ ],
13
+ "ep_size": 1,
14
+ "first_k_dense_replace": 3,
15
+ "head_dim": 192,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 6144,
18
+ "index_head_dim": 128,
19
+ "index_n_heads": 32,
20
+ "index_share_for_mtp_iteration": true,
21
+ "index_skip_topk_offset": 3,
22
+ "index_topk": 2048,
23
+ "index_topk_freq": 4,
24
+ "index_topk_pattern": null,
25
+ "indexer_rope_interleave": true,
26
+ "indexer_types": [
27
+ "full",
28
+ "full",
29
+ "full",
30
+ "shared",
31
+ "shared",
32
+ "shared",
33
+ "full",
34
+ "shared",
35
+ "shared",
36
+ "shared",
37
+ "full",
38
+ "shared",
39
+ "shared",
40
+ "shared",
41
+ "full",
42
+ "shared",
43
+ "shared",
44
+ "shared",
45
+ "full",
46
+ "shared",
47
+ "shared",
48
+ "shared",
49
+ "full",
50
+ "shared",
51
+ "shared",
52
+ "shared",
53
+ "full",
54
+ "shared",
55
+ "shared",
56
+ "shared",
57
+ "full",
58
+ "shared",
59
+ "shared",
60
+ "shared",
61
+ "full",
62
+ "shared",
63
+ "shared",
64
+ "shared",
65
+ "full",
66
+ "shared",
67
+ "shared",
68
+ "shared",
69
+ "full",
70
+ "shared",
71
+ "shared",
72
+ "shared",
73
+ "full",
74
+ "shared",
75
+ "shared",
76
+ "shared",
77
+ "full",
78
+ "shared",
79
+ "shared",
80
+ "shared",
81
+ "full",
82
+ "shared",
83
+ "shared",
84
+ "shared",
85
+ "full",
86
+ "shared",
87
+ "shared",
88
+ "shared",
89
+ "full",
90
+ "shared",
91
+ "shared",
92
+ "shared",
93
+ "full",
94
+ "shared",
95
+ "shared",
96
+ "shared",
97
+ "full",
98
+ "shared",
99
+ "shared",
100
+ "shared",
101
+ "full",
102
+ "shared",
103
+ "shared",
104
+ "shared"
105
+ ],
106
+ "initializer_range": 0.02,
107
+ "intermediate_size": 12288,
108
+ "kv_lora_rank": 512,
109
+ "max_position_embeddings": 1048576,
110
+ "mlp_layer_types": [
111
+ "dense",
112
+ "dense",
113
+ "dense",
114
+ "sparse",
115
+ "sparse",
116
+ "sparse",
117
+ "sparse",
118
+ "sparse",
119
+ "sparse",
120
+ "sparse",
121
+ "sparse",
122
+ "sparse",
123
+ "sparse",
124
+ "sparse",
125
+ "sparse",
126
+ "sparse",
127
+ "sparse",
128
+ "sparse",
129
+ "sparse",
130
+ "sparse",
131
+ "sparse",
132
+ "sparse",
133
+ "sparse",
134
+ "sparse",
135
+ "sparse",
136
+ "sparse",
137
+ "sparse",
138
+ "sparse",
139
+ "sparse",
140
+ "sparse",
141
+ "sparse",
142
+ "sparse",
143
+ "sparse",
144
+ "sparse",
145
+ "sparse",
146
+ "sparse",
147
+ "sparse",
148
+ "sparse",
149
+ "sparse",
150
+ "sparse",
151
+ "sparse",
152
+ "sparse",
153
+ "sparse",
154
+ "sparse",
155
+ "sparse",
156
+ "sparse",
157
+ "sparse",
158
+ "sparse",
159
+ "sparse",
160
+ "sparse",
161
+ "sparse",
162
+ "sparse",
163
+ "sparse",
164
+ "sparse",
165
+ "sparse",
166
+ "sparse",
167
+ "sparse",
168
+ "sparse",
169
+ "sparse",
170
+ "sparse",
171
+ "sparse",
172
+ "sparse",
173
+ "sparse",
174
+ "sparse",
175
+ "sparse",
176
+ "sparse",
177
+ "sparse",
178
+ "sparse",
179
+ "sparse",
180
+ "sparse",
181
+ "sparse",
182
+ "sparse",
183
+ "sparse",
184
+ "sparse",
185
+ "sparse",
186
+ "sparse",
187
+ "sparse",
188
+ "sparse"
189
+ ],
190
+ "model_type": "glm_moe_dsa",
191
+ "moe_intermediate_size": 2048,
192
+ "moe_layer_freq": 1,
193
+ "n_group": 1,
194
+ "n_routed_experts": 256,
195
+ "n_shared_experts": 1,
196
+ "norm_topk_prob": true,
197
+ "num_attention_heads": 64,
198
+ "num_experts_per_tok": 8,
199
+ "num_hidden_layers": 5,
200
+ "num_key_value_heads": 64,
201
+ "num_nextn_predict_layers": 1,
202
+ "pad_token_id": 154820,
203
+ "pretraining_tp": 1,
204
+ "q_lora_rank": 2048,
205
+ "qk_head_dim": 256,
206
+ "qk_nope_head_dim": 192,
207
+ "qk_rope_head_dim": 64,
208
+ "rms_norm_eps": 1e-05,
209
+ "rope_interleave": true,
210
+ "rope_parameters": {
211
+ "rope_theta": 8000000,
212
+ "rope_type": "default"
213
+ },
214
+ "routed_scaling_factor": 2.5,
215
+ "scoring_func": "sigmoid",
216
+ "tie_word_embeddings": false,
217
+ "topk_group": 1,
218
+ "topk_method": "noaux_tc",
219
+ "transformers_version": "5.12.0",
220
+ "use_cache": true,
221
+ "v_head_dim": 256,
222
+ "vocab_size": 154880
223
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 154820,
5
+ 154827,
6
+ 154829
7
+ ],
8
+ "pad_token_id": 154820,
9
+ "temperature": 1.0,
10
+ "top_p": 0.95,
11
+ "transformers_version": "5.12.0"
12
+ }
model-00001-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004bf9404964da8ea71ea2d3ebf02148fa766b956bd4fca3f54b093e58a6a74c
3
+ size 5342821416
model-00002-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e51c7c2c22ae3e5d2d4f4706ad917b04cf140c3f1743fd42d47fcb177cb31d3
3
+ size 67108984
model-00038-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82595223f733f465fb923409703735f85da5ca28a0a7045a5439054d922af974
3
+ size 801799616
model-00075-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf4a6ac886004adaf5e6b33b689ec29c33eebc1660a59b4900bcb21422ce2c4
3
+ size 931152424
model-00076-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c65131e725c858d2e458da91b443ba95488b0f1343129fc629cbc3d35350d6c
3
+ size 5360347104
model-00077-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68aceb515ad523d9794318ec8578b68fbe9e42648bf222ccd337e1fdac02b23d
3
+ size 5360347104
model-00078-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8720873631cb258ece1f196e7f389e39b219901a4c49db2328f783fc78e4ee15
3
+ size 5360346952
model-00079-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c59b42b5a95bdc9b5b922c26ff50cfbc97878489db17570663bf9421fe543919
3
+ size 2723969648
model-00116-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447b01c0958cb1b35c675256dff1f1d13b84e782d332a204237eaf93de043bee
3
+ size 3598743040
model-00117-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703e4dfbea787c84c26fbb6b0200378262cf2e2c5e48d563a7fcc9b10a75ee19
3
+ size 5360347104
model-00118-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec6264b97ff493fea3d61a44b999da9e1af4202ded96a9929478ae4c2610b88
3
+ size 5360347064
model-00119-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a69af73c4d8bd4d5858defdc5c82294c1e01d67fe34b23adf48a4ee6c69242
3
+ size 5349617128
model-00120-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a22435ddf819088c6b102f81dc673c41be5f12bb868874ee4aa444de80585b
3
+ size 67108984
model-00282-of-00282.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e26cafa850631ede0839584e4b396a7058466998bdf8e7bae2775f77d1a4b44
3
+ size 12376
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
3
+ size 20217442
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": false,
4
+ "do_lower_case": false,
5
+ "eos_token": "<|endoftext|>",
6
+ "extra_special_tokens": [
7
+ "<|endoftext|>",
8
+ "[MASK]",
9
+ "[gMASK]",
10
+ "[sMASK]",
11
+ "<sop>",
12
+ "<eop>",
13
+ "<|system|>",
14
+ "<|user|>",
15
+ "<|assistant|>",
16
+ "<|observation|>",
17
+ "<|begin_of_image|>",
18
+ "<|end_of_image|>",
19
+ "<|begin_of_video|>",
20
+ "<|end_of_video|>",
21
+ "<|begin_of_audio|>",
22
+ "<|end_of_audio|>",
23
+ "<|begin_of_transcription|>",
24
+ "<|end_of_transcription|>"
25
+ ],
26
+ "is_local": true,
27
+ "model_max_length": 1048576,
28
+ "model_specific_special_tokens": {},
29
+ "pad_token": "<|endoftext|>",
30
+ "padding_side": "left",
31
+ "remove_space": false,
32
+ "tokenizer_class": "TokenizersBackend"
33
+ }