Hugging Face's logo

Pinaster
/
GLM-5.2_5layer

Safetensors
glm_moe_dsa
Model card Files
xet
 Community
Pinaster commited on
Commit
1c74913
·
verified ·
1 Parent(s): 0957795

Trim mlp_layer_types/indexer_types to num_hidden_layers=5 (transformers>=5.12 validate_layer_type enforces len==num_hidden_layers)

Browse files
Files changed (1) hide show
  1. config.json +1 -147
config.json CHANGED
@@ -28,79 +28,6 @@
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,
@@ -112,79 +39,6 @@
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",
@@ -220,4 +74,4 @@
220
  "use_cache": true,
221
  "v_head_dim": 256,
222
  "vocab_size": 154880
223
- }
 
28
  "full",
29
  "full",
30
  "shared",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "shared"
32
  ],
33
  "initializer_range": 0.02,
 
39
  "dense",
40
  "dense",
41
  "sparse",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  "sparse"
43
  ],
44
  "model_type": "glm_moe_dsa",
 
74
  "use_cache": true,
75
  "v_head_dim": 256,
76
  "vocab_size": 154880
77
+ }