Find this model in the GLM model summary
Model source: https://huggingface.co/THUDM/glm-2b
layer_type | N | M | Q | alpha | D | alpha-hat | log_SN | rank_loss | |
---|---|---|---|---|---|---|---|---|---|
layer_id | |||||||||
2 | DENSE | 2048 | 1025 | 2.00 | 2.42 | 0.10 | 2.22 | 0.92 | 0 |
3 | DENSE | 2048 | 1025 | 2.00 | 2.09 | 0.10 | 2.80 | 1.34 | 0 |
5 | DENSE | 6144 | 2048 | 3.00 | 2.52 | 0.02 | 4.80 | 1.90 | 0 |
6 | DENSE | 2048 | 2048 | 1.00 | 4.43 | 0.03 | 0.87 | 0.20 | 9 |
8 | DENSE | 8192 | 2048 | 4.00 | 4.39 | 0.04 | 8.32 | 1.90 | 0 |
9 | DENSE | 8192 | 2048 | 4.00 | 5.82 | 0.03 | 6.30 | 1.08 | 0 |
11 | DENSE | 6144 | 2048 | 3.00 | 2.72 | 0.03 | 4.24 | 1.56 | 0 |
12 | DENSE | 2048 | 2048 | 1.00 | 2.28 | 0.02 | 2.55 | 1.12 | 4 |
14 | DENSE | 8192 | 2048 | 4.00 | 3.07 | 0.02 | 7.07 | 2.31 | 0 |
15 | DENSE | 8192 | 2048 | 4.00 | 4.11 | 0.03 | 6.98 | 1.70 | 0 |
17 | DENSE | 6144 | 2048 | 3.00 | 2.39 | 0.02 | 3.81 | 1.59 | 0 |
18 | DENSE | 2048 | 2048 | 1.00 | 2.57 | 0.05 | 3.02 | 1.18 | 4 |
20 | DENSE | 8192 | 2048 | 4.00 | 2.75 | 0.01 | 6.25 | 2.28 | 0 |
21 | DENSE | 8192 | 2048 | 4.00 | 3.86 | 0.03 | 8.13 | 2.10 | 0 |
23 | DENSE | 6144 | 2048 | 3.00 | 2.50 | 0.02 | 4.24 | 1.70 | 0 |
24 | DENSE | 2048 | 2048 | 1.00 | 2.90 | 0.05 | 3.97 | 1.37 | 4 |
26 | DENSE | 8192 | 2048 | 4.00 | 2.81 | 0.02 | 6.42 | 2.29 | 0 |
27 | DENSE | 8192 | 2048 | 4.00 | 3.68 | 0.04 | 7.77 | 2.11 | 0 |
29 | DENSE | 6144 | 2048 | 3.00 | 2.54 | 0.02 | 4.18 | 1.65 | 0 |
30 | DENSE | 2048 | 2048 | 1.00 | 3.74 | 0.05 | 3.93 | 1.05 | 4 |
32 | DENSE | 8192 | 2048 | 4.00 | 2.95 | 0.02 | 6.69 | 2.27 | 0 |
33 | DENSE | 8192 | 2048 | 4.00 | 3.68 | 0.03 | 7.72 | 2.10 | 0 |
35 | DENSE | 6144 | 2048 | 3.00 | 2.48 | 0.02 | 4.11 | 1.66 | 0 |
36 | DENSE | 2048 | 2048 | 1.00 | 6.29 | 0.06 | 4.62 | 0.73 | 3 |
38 | DENSE | 8192 | 2048 | 4.00 | 2.89 | 0.01 | 6.20 | 2.15 | 0 |
39 | DENSE | 8192 | 2048 | 4.00 | 3.88 | 0.03 | 6.31 | 1.63 | 0 |
41 | DENSE | 6144 | 2048 | 3.00 | 2.56 | 0.02 | 4.04 | 1.58 | 0 |
42 | DENSE | 2048 | 2048 | 1.00 | 3.69 | 0.05 | 2.83 | 0.77 | 4 |
44 | DENSE | 8192 | 2048 | 4.00 | 2.90 | 0.01 | 6.02 | 2.08 | 0 |
45 | DENSE | 8192 | 2048 | 4.00 | 3.22 | 0.04 | 4.22 | 1.31 | 0 |
47 | DENSE | 6144 | 2048 | 3.00 | 2.78 | 0.02 | 4.41 | 1.59 | 0 |
48 | DENSE | 2048 | 2048 | 1.00 | 4.99 | 0.05 | 3.67 | 0.73 | 3 |
50 | DENSE | 8192 | 2048 | 4.00 | 2.95 | 0.02 | 6.01 | 2.04 | 0 |
51 | DENSE | 8192 | 2048 | 4.00 | 3.20 | 0.03 | 4.08 | 1.27 | 0 |
53 | DENSE | 6144 | 2048 | 3.00 | 3.06 | 0.03 | 4.58 | 1.50 | 0 |
54 | DENSE | 2048 | 2048 | 1.00 | 3.62 | 0.04 | 2.51 | 0.69 | 3 |
56 | DENSE | 8192 | 2048 | 4.00 | 3.14 | 0.02 | 6.43 | 2.04 | 0 |
57 | DENSE | 8192 | 2048 | 4.00 | 4.79 | 0.04 | 6.57 | 1.37 | 0 |
59 | DENSE | 6144 | 2048 | 3.00 | 2.93 | 0.03 | 4.55 | 1.55 | 0 |
60 | DENSE | 2048 | 2048 | 1.00 | 3.90 | 0.05 | 2.63 | 0.67 | 3 |
62 | DENSE | 8192 | 2048 | 4.00 | 3.16 | 0.02 | 6.42 | 2.03 | 0 |
63 | DENSE | 8192 | 2048 | 4.00 | 3.32 | 0.05 | 4.19 | 1.26 | 0 |
65 | DENSE | 6144 | 2048 | 3.00 | 2.83 | 0.04 | 4.27 | 1.51 | 0 |
66 | DENSE | 2048 | 2048 | 1.00 | 4.80 | 0.06 | 3.26 | 0.68 | 3 |
68 | DENSE | 8192 | 2048 | 4.00 | 3.09 | 0.03 | 6.22 | 2.01 | 0 |
69 | DENSE | 8192 | 2048 | 4.00 | 3.55 | 0.04 | 4.52 | 1.27 | 0 |
71 | DENSE | 6144 | 2048 | 3.00 | 2.81 | 0.03 | 4.13 | 1.47 | 0 |
72 | DENSE | 2048 | 2048 | 1.00 | 3.57 | 0.06 | 2.62 | 0.73 | 4 |
74 | DENSE | 8192 | 2048 | 4.00 | 2.98 | 0.02 | 5.95 | 2.00 | 0 |
75 | DENSE | 8192 | 2048 | 4.00 | 3.33 | 0.05 | 4.08 | 1.22 | 0 |
77 | DENSE | 6144 | 2048 | 3.00 | 2.89 | 0.04 | 4.28 | 1.48 | 0 |
78 | DENSE | 2048 | 2048 | 1.00 | 7.06 | 0.06 | 5.14 | 0.73 | 3 |
80 | DENSE | 8192 | 2048 | 4.00 | 3.01 | 0.03 | 6.01 | 2.00 | 0 |
81 | DENSE | 8192 | 2048 | 4.00 | 3.15 | 0.05 | 3.78 | 1.20 | 0 |
83 | DENSE | 6144 | 2048 | 3.00 | 2.92 | 0.03 | 4.60 | 1.58 | 0 |
84 | DENSE | 2048 | 2048 | 1.00 | 4.41 | 0.06 | 2.99 | 0.68 | 3 |
86 | DENSE | 8192 | 2048 | 4.00 | 3.56 | 0.04 | 7.01 | 1.97 | 0 |
87 | DENSE | 8192 | 2048 | 4.00 | 3.36 | 0.05 | 4.05 | 1.21 | 0 |
89 | DENSE | 6144 | 2048 | 3.00 | 2.88 | 0.03 | 4.53 | 1.57 | 0 |
90 | DENSE | 2048 | 2048 | 1.00 | 3.94 | 0.06 | 2.92 | 0.74 | 4 |
92 | DENSE | 8192 | 2048 | 4.00 | 3.23 | 0.04 | 6.26 | 1.94 | 0 |
93 | DENSE | 8192 | 2048 | 4.00 | 3.11 | 0.05 | 3.85 | 1.24 | 0 |
95 | DENSE | 6144 | 2048 | 3.00 | 2.81 | 0.02 | 5.48 | 1.95 | 0 |
96 | DENSE | 2048 | 2048 | 1.00 | 3.23 | 0.05 | 2.45 | 0.76 | 4 |
98 | DENSE | 8192 | 2048 | 4.00 | 3.01 | 0.04 | 5.83 | 1.94 | 0 |
99 | DENSE | 8192 | 2048 | 4.00 | 3.19 | 0.04 | 3.92 | 1.23 | 0 |
101 | DENSE | 6144 | 2048 | 3.00 | 2.76 | 0.03 | 4.26 | 1.55 | 0 |
102 | DENSE | 2048 | 2048 | 1.00 | 3.13 | 0.07 | 2.29 | 0.73 | 3 |
104 | DENSE | 8192 | 2048 | 4.00 | 3.66 | 0.04 | 7.06 | 1.93 | 0 |
105 | DENSE | 8192 | 2048 | 4.00 | 3.40 | 0.05 | 4.22 | 1.24 | 0 |
107 | DENSE | 6144 | 2048 | 3.00 | 2.66 | 0.04 | 4.10 | 1.54 | 0 |
108 | DENSE | 2048 | 2048 | 1.00 | 2.80 | 0.06 | 2.30 | 0.82 | 3 |
110 | DENSE | 8192 | 2048 | 4.00 | 3.84 | 0.03 | 7.37 | 1.92 | 0 |
111 | DENSE | 8192 | 2048 | 4.00 | 3.55 | 0.04 | 4.46 | 1.26 | 0 |
113 | DENSE | 6144 | 2048 | 3.00 | 3.03 | 0.03 | 4.74 | 1.57 | 0 |
114 | DENSE | 2048 | 2048 | 1.00 | 3.43 | 0.06 | 2.55 | 0.74 | 4 |
116 | DENSE | 8192 | 2048 | 4.00 | 3.15 | 0.03 | 6.10 | 1.94 | 0 |
117 | DENSE | 8192 | 2048 | 4.00 | 4.12 | 0.04 | 5.06 | 1.23 | 0 |
119 | DENSE | 6144 | 2048 | 3.00 | 3.10 | 0.02 | 4.95 | 1.59 | 0 |
120 | DENSE | 2048 | 2048 | 1.00 | 3.57 | 0.05 | 2.45 | 0.69 | 3 |
122 | DENSE | 8192 | 2048 | 4.00 | 4.05 | 0.03 | 7.83 | 1.93 | 0 |
123 | DENSE | 8192 | 2048 | 4.00 | 3.98 | 0.05 | 4.56 | 1.15 | 0 |
125 | DENSE | 6144 | 2048 | 3.00 | 3.03 | 0.03 | 4.69 | 1.55 | 0 |
126 | DENSE | 2048 | 2048 | 1.00 | 3.60 | 0.09 | 2.50 | 0.69 | 4 |
128 | DENSE | 8192 | 2048 | 4.00 | 3.89 | 0.03 | 7.55 | 1.94 | 0 |
129 | DENSE | 8192 | 2048 | 4.00 | 3.54 | 0.04 | 4.13 | 1.17 | 0 |
131 | DENSE | 6144 | 2048 | 3.00 | 3.17 | 0.02 | 4.76 | 1.50 | 0 |
132 | DENSE | 2048 | 2048 | 1.00 | 10.66 | 0.07 | 6.63 | 0.62 | 3 |
134 | DENSE | 8192 | 2048 | 4.00 | 3.95 | 0.02 | 7.68 | 1.94 | 0 |
135 | DENSE | 8192 | 2048 | 4.00 | 3.76 | 0.04 | 4.46 | 1.19 | 0 |
137 | DENSE | 6144 | 2048 | 3.00 | 3.34 | 0.02 | 5.25 | 1.57 | 0 |
138 | DENSE | 2048 | 2048 | 1.00 | 8.98 | 0.05 | 6.51 | 0.72 | 3 |
140 | DENSE | 8192 | 2048 | 4.00 | 4.03 | 0.02 | 7.87 | 1.95 | 0 |
141 | DENSE | 8192 | 2048 | 4.00 | 3.94 | 0.04 | 4.88 | 1.24 | 0 |
143 | DENSE | 6144 | 2048 | 3.00 | 3.39 | 0.02 | 5.91 | 1.74 | 0 |
144 | DENSE | 2048 | 2048 | 1.00 | 8.73 | 0.05 | 6.66 | 0.76 | 2 |
146 | DENSE | 8192 | 2048 | 4.00 | 4.05 | 0.02 | 7.92 | 1.95 | 0 |
147 | DENSE | 8192 | 2048 | 4.00 | 4.62 | 0.04 | 5.96 | 1.29 | 0 |
149 | DENSE | 6144 | 2048 | 3.00 | 3.57 | 0.02 | 5.88 | 1.65 | 0 |
150 | DENSE | 2048 | 2048 | 1.00 | 7.15 | 0.02 | 5.41 | 0.76 | 3 |
152 | DENSE | 8192 | 2048 | 4.00 | 4.14 | 0.02 | 8.13 | 1.96 | 0 |
153 | DENSE | 8192 | 2048 | 4.00 | 4.51 | 0.03 | 5.58 | 1.24 | 0 |
155 | DENSE | 6144 | 2048 | 3.00 | 3.67 | 0.02 | 6.10 | 1.66 | 0 |
156 | DENSE | 2048 | 2048 | 1.00 | 7.48 | 0.07 | 6.84 | 0.92 | 3 |
158 | DENSE | 8192 | 2048 | 4.00 | 4.13 | 0.02 | 8.10 | 1.96 | 0 |
159 | DENSE | 8192 | 2048 | 4.00 | 5.22 | 0.01 | 6.50 | 1.25 | 0 |
161 | DENSE | 6144 | 2048 | 3.00 | 4.00 | 0.01 | 6.22 | 1.56 | 0 |
162 | DENSE | 2048 | 2048 | 1.00 | 7.30 | 0.06 | 7.03 | 0.96 | 3 |
164 | DENSE | 8192 | 2048 | 4.00 | 4.18 | 0.02 | 8.24 | 1.97 | 0 |
165 | DENSE | 8192 | 2048 | 4.00 | 5.03 | 0.01 | 6.46 | 1.28 | 0 |
167 | DENSE | 6144 | 2048 | 3.00 | 3.67 | 0.02 | 6.75 | 1.84 | 0 |
168 | DENSE | 2048 | 2048 | 1.00 | 7.69 | 0.06 | 7.64 | 0.99 | 2 |
170 | DENSE | 8192 | 2048 | 4.00 | 4.11 | 0.02 | 8.11 | 1.97 | 0 |
171 | DENSE | 8192 | 2048 | 4.00 | 4.99 | 0.01 | 6.58 | 1.32 | 0 |
173 | DENSE | 6144 | 2048 | 3.00 | 3.55 | 0.02 | 6.01 | 1.69 | 0 |
174 | DENSE | 2048 | 2048 | 1.00 | 7.70 | 0.08 | 7.44 | 0.97 | 2 |
176 | DENSE | 8192 | 2048 | 4.00 | 4.24 | 0.02 | 8.38 | 1.98 | 0 |
177 | DENSE | 8192 | 2048 | 4.00 | 5.04 | 0.01 | 6.63 | 1.32 | 0 |
179 | DENSE | 6144 | 2048 | 3.00 | 3.68 | 0.02 | 6.29 | 1.71 | 0 |
180 | DENSE | 2048 | 2048 | 1.00 | 6.99 | 0.06 | 7.02 | 1.00 | 2 |
182 | DENSE | 8192 | 2048 | 4.00 | 4.24 | 0.03 | 8.41 | 1.98 | 0 |
183 | DENSE | 8192 | 2048 | 4.00 | 4.98 | 0.02 | 6.51 | 1.31 | 0 |
185 | DENSE | 6144 | 2048 | 3.00 | 3.30 | 0.01 | 5.29 | 1.60 | 0 |
186 | DENSE | 2048 | 2048 | 1.00 | 7.04 | 0.07 | 6.87 | 0.98 | 2 |
188 | DENSE | 8192 | 2048 | 4.00 | 4.41 | 0.04 | 8.78 | 1.99 | 0 |
189 | DENSE | 8192 | 2048 | 4.00 | 5.18 | 0.02 | 6.58 | 1.27 | 0 |
191 | DENSE | 6144 | 2048 | 3.00 | 3.26 | 0.01 | 5.26 | 1.61 | 0 |
192 | DENSE | 2048 | 2048 | 1.00 | 7.29 | 0.08 | 7.09 | 0.97 | 2 |
194 | DENSE | 8192 | 2048 | 4.00 | 4.54 | 0.04 | 9.08 | 2.00 | 0 |
195 | DENSE | 8192 | 2048 | 4.00 | 5.33 | 0.02 | 6.97 | 1.31 | 0 |
197 | DENSE | 6144 | 2048 | 3.00 | 3.25 | 0.01 | 5.24 | 1.61 | 0 |
198 | DENSE | 2048 | 2048 | 1.00 | 6.27 | 0.08 | 6.81 | 1.09 | 2 |
200 | DENSE | 8192 | 2048 | 4.00 | 5.07 | 0.05 | 10.20 | 2.01 | 0 |
201 | DENSE | 8192 | 2048 | 4.00 | 5.10 | 0.02 | 6.81 | 1.33 | 0 |
203 | DENSE | 6144 | 2048 | 3.00 | 3.42 | 0.04 | 5.61 | 1.64 | 0 |
204 | DENSE | 2048 | 2048 | 1.00 | 5.42 | 0.08 | 7.06 | 1.30 | 2 |
206 | DENSE | 8192 | 2048 | 4.00 | 5.09 | 0.06 | 10.27 | 2.02 | 0 |
207 | DENSE | 8192 | 2048 | 4.00 | 5.00 | 0.02 | 7.47 | 1.49 | 0 |
209 | DENSE | 6144 | 2048 | 3.00 | 3.34 | 0.04 | 5.49 | 1.64 | 0 |
210 | DENSE | 2048 | 2048 | 1.00 | 5.21 | 0.08 | 6.98 | 1.34 | 1 |
212 | DENSE | 8192 | 2048 | 4.00 | 4.75 | 0.05 | 9.81 | 2.07 | 0 |
213 | DENSE | 8192 | 2048 | 4.00 | 4.49 | 0.01 | 7.68 | 1.71 | 0 |
215 | DENSE | 6144 | 2048 | 3.00 | 2.91 | 0.03 | 5.14 | 1.77 | 0 |
216 | DENSE | 2048 | 2048 | 1.00 | 4.86 | 0.07 | 6.65 | 1.37 | 3 |
218 | DENSE | 8192 | 2048 | 4.00 | 4.41 | 0.05 | 10.03 | 2.27 | 0 |
219 | DENSE | 8192 | 2048 | 4.00 | 4.76 | 0.02 | 7.43 | 1.56 | 0 |
221 | DENSE | 2048 | 2048 | 1.00 | 48.35 | 0.12 | 24.43 | 0.51 | 2 |