Qwen2.5-7B-Instruct


Find this model in the Qwen2.5-small model summary

Qwen2.5-7B-Instruct Model Set Plots

Qwen2.5-small Compared to Base Model Plots

Qwen2.5-7B-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 18944 3584 5.285714 3.340768 0.018778 -3.624028 431
2 dense 18944 3584 5.285714 3.702887 0.023065 -4.640151 227
3 dense 18944 3584 5.285714 3.272981 0.015728 -3.171403 244
4 dense 3584 512 7.000000 2.476425 0.034357 -4.901859 149
5 dense 3584 3584 1.000000 3.032192 0.022444 -5.485919 155
6 dense 3584 3584 1.000000 2.700031 0.026584 -4.429347 121
7 dense 3584 512 7.000000 4.309447 0.028433 -11.849292 48
8 dense 18944 3584 5.285714 3.516675 0.015180 -3.841979 389
9 dense 18944 3584 5.285714 3.092141 0.022464 -3.280316 235
10 dense 18944 3584 5.285714 2.893224 0.016703 -2.985746 208
11 dense 3584 512 7.000000 1.887514 0.034784 -3.820115 130 over-trained
12 dense 3584 3584 1.000000 2.729576 0.018518 -4.170244 107
13 dense 3584 3584 1.000000 2.240056 0.043018 -3.678363 132
14 dense 3584 512 7.000000 2.988304 0.025212 -7.254538 65
15 dense 18944 3584 5.285714 3.600286 0.008153 -5.043187 414
16 dense 18944 3584 5.285714 2.912229 0.021585 -3.066321 438
17 dense 18944 3584 5.285714 3.215265 0.022846 -3.832565 71
18 dense 3584 512 7.000000 2.563995 0.021622 -5.838127 88
19 dense 3584 3584 1.000000 3.093114 0.027701 -5.498288 57
20 dense 3584 3584 1.000000 2.577238 0.025221 -4.466618 194
21 dense 3584 512 7.000000 3.338095 0.031411 -8.621973 57
22 dense 18944 3584 5.285714 3.885821 0.014098 -6.013244 268
23 dense 18944 3584 5.285714 3.301498 0.012782 -3.273227 320
24 dense 18944 3584 5.285714 3.203965 0.016418 -3.724071 223
25 dense 3584 512 7.000000 2.409313 0.026655 -5.389429 144
26 dense 3584 3584 1.000000 3.357950 0.020733 -5.936343 80
27 dense 3584 3584 1.000000 2.717490 0.031321 -4.717442 121
28 dense 3584 512 7.000000 3.674333 0.023274 -9.742663 63
29 dense 18944 3584 5.285714 3.903233 0.012423 -6.027030 150
30 dense 18944 3584 5.285714 3.425027 0.009688 -3.551312 493
31 dense 18944 3584 5.285714 3.123245 0.013376 -3.789504 308
32 dense 3584 512 7.000000 2.421098 0.033456 -5.598962 131
33 dense 3584 3584 1.000000 2.812477 0.041652 -5.174648 162
34 dense 3584 3584 1.000000 2.441206 0.019818 -4.198433 239
35 dense 3584 512 7.000000 3.646659 0.032364 -9.379685 56
36 dense 18944 3584 5.285714 3.731889 0.018389 -5.733463 194
37 dense 18944 3584 5.285714 3.422786 0.013183 -3.599123 604
38 dense 18944 3584 5.285714 3.184171 0.009589 -3.840290 239
39 dense 3584 512 7.000000 2.586199 0.020966 -5.894905 119
40 dense 3584 3584 1.000000 2.794288 0.040980 -4.957611 112
41 dense 3584 3584 1.000000 2.432513 0.013139 -3.882224 297
42 dense 3584 512 7.000000 3.319053 0.037375 -8.407389 76
43 dense 3584 512 7.000000 2.406575 0.022472 -5.330249 155
44 dense 3584 3584 1.000000 3.083246 0.025696 -5.387391 91
45 dense 3584 3584 1.000000 2.362178 0.017926 -4.018627 350
46 dense 3584 512 7.000000 3.384748 0.020551 -7.887295 61
47 dense 18944 3584 5.285714 3.482950 0.016432 -3.997663 632
48 dense 18944 3584 5.285714 3.873909 0.011037 -6.037006 191
49 dense 18944 3584 5.285714 3.235936 0.007721 -4.003470 246
50 dense 18944 3584 5.285714 3.107872 0.010587 -3.435312 229
51 dense 18944 3584 5.285714 3.746805 0.015276 -5.716847 209
52 dense 18944 3584 5.285714 3.150748 0.010825 -3.228269 593
53 dense 3584 3584 1.000000 3.151121 0.028847 -5.835386 107
54 dense 3584 512 7.000000 2.517986 0.031521 -5.691648 112
55 dense 3584 512 7.000000 3.735738 0.037855 -10.159252 66
56 dense 3584 3584 1.000000 2.407158 0.021815 -3.924178 268
57 dense 3584 512 7.000000 2.720115 0.026416 -6.528205 103
58 dense 18944 3584 5.285714 3.648584 0.011364 -5.679353 201
59 dense 18944 3584 5.285714 3.062797 0.008507 -3.069658 542
60 dense 18944 3584 5.285714 3.100901 0.009903 -3.379357 176
61 dense 3584 3584 1.000000 2.566981 0.025607 -4.450676 221
62 dense 3584 3584 1.000000 3.149107 0.032413 -5.736487 84
63 dense 3584 512 7.000000 4.033172 0.038788 -10.342362 28
64 dense 3584 512 7.000000 3.577693 0.038823 -9.128690 63
65 dense 3584 512 7.000000 2.538263 0.029848 -5.918769 85
66 dense 18944 3584 5.285714 3.421914 0.018017 -4.174359 94
67 dense 3584 3584 1.000000 2.351847 0.021991 -3.495912 250
68 dense 3584 3584 1.000000 2.981832 0.029388 -5.401211 101
69 dense 18944 3584 5.285714 3.255176 0.010321 -3.342122 433
70 dense 18944 3584 5.285714 3.783096 0.012872 -5.766445 169
71 dense 18944 3584 5.285714 3.137784 0.008741 -3.101045 518
72 dense 18944 3584 5.285714 4.155593 0.014174 -6.506255 153
73 dense 3584 3584 1.000000 2.437651 0.023072 -3.961335 227
74 dense 3584 3584 1.000000 1.891702 0.072984 -3.491135 1118 over-trained
75 dense 3584 512 7.000000 2.490444 0.033765 -5.778061 123
76 dense 3584 512 7.000000 3.705520 0.030724 -9.134811 47
77 dense 18944 3584 5.285714 3.310491 0.013553 -3.778478 136
78 dense 18944 3584 5.285714 3.196713 0.016553 -3.516245 163
79 dense 18944 3584 5.285714 4.244998 0.020952 -6.757568 107
80 dense 18944 3584 5.285714 3.030878 0.005721 -2.992861 353
81 dense 3584 512 7.000000 4.377579 0.036314 -11.154900 29
82 dense 3584 3584 1.000000 2.562910 0.027325 -4.250817 178
83 dense 3584 3584 1.000000 1.885765 0.075091 -3.714373 1060 over-trained
84 dense 3584 512 7.000000 2.757964 0.029988 -6.606196 81
85 dense 3584 512 7.000000 2.614358 0.028033 -5.871083 102
86 dense 18944 3584 5.285714 3.116052 0.016266 -3.448654 199
87 dense 18944 3584 5.285714 2.988090 0.006347 -2.965255 329
88 dense 18944 3584 5.285714 4.105979 0.017897 -6.484913 116
89 dense 3584 3584 1.000000 1.887867 0.067331 -3.471513 1010 over-trained
90 dense 3584 3584 1.000000 2.528656 0.029889 -4.216677 197
91 dense 3584 512 7.000000 4.233730 0.037010 -11.411644 35
92 dense 3584 3584 1.000000 2.537313 0.036241 -4.195305 217
93 dense 18944 3584 5.285714 4.278959 0.016326 -6.852499 108
94 dense 3584 512 7.000000 2.651043 0.041677 -6.326861 101
95 dense 18944 3584 5.285714 3.264234 0.011989 -3.600479 129
96 dense 18944 3584 5.285714 3.061310 0.009258 -3.002699 204
97 dense 3584 512 7.000000 4.197162 0.036523 -11.329908 56
98 dense 3584 3584 1.000000 1.811337 0.066650 -3.614281 1183 over-trained
99 dense 3584 512 7.000000 2.664044 0.036176 -6.402884 114
100 dense 18944 3584 5.285714 3.185356 0.011987 -3.490404 167
101 dense 3584 512 7.000000 4.636405 0.033027 -12.594284 36
102 dense 3584 3584 1.000000 1.823903 0.078929 -3.652344 1103 over-trained
103 dense 3584 3584 1.000000 2.491835 0.035033 -4.065751 272
104 dense 18944 3584 5.285714 4.096274 0.017709 -6.468150 144
105 dense 18944 3584 5.285714 2.983215 0.009049 -2.896674 276
106 dense 18944 3584 5.285714 4.231499 0.019191 -6.873094 89
107 dense 18944 3584 5.285714 2.887538 0.007715 -2.844487 253
108 dense 18944 3584 5.285714 3.053522 0.012463 -3.418379 176
109 dense 3584 512 7.000000 2.689211 0.028713 -6.337475 99
110 dense 3584 3584 1.000000 1.805820 0.078048 -3.495499 1122 over-trained
111 dense 3584 3584 1.000000 2.448785 0.037893 -4.343755 264
112 dense 3584 512 7.000000 3.934712 0.037144 -10.322008 52
113 dense 18944 3584 5.285714 4.266911 0.020813 -6.805295 91
114 dense 18944 3584 5.285714 2.886900 0.010385 -2.844989 239
115 dense 18944 3584 5.285714 3.088611 0.013417 -3.402081 149
116 dense 3584 512 7.000000 2.783345 0.047555 -6.646059 84
117 dense 3584 3584 1.000000 1.771331 0.071113 -3.524980 1238 over-trained
118 dense 3584 3584 1.000000 2.617786 0.036829 -4.405243 164
119 dense 3584 512 7.000000 4.506514 0.038791 -12.271777 35
120 dense 18944 3584 5.285714 4.074465 0.021989 -6.320835 91
121 dense 18944 3584 5.285714 2.903967 0.013243 -2.850818 182
122 dense 18944 3584 5.285714 3.041100 0.013577 -3.339758 198
123 dense 3584 512 7.000000 2.725217 0.038393 -6.593663 123
124 dense 3584 3584 1.000000 1.878666 0.087224 -3.453725 1057 over-trained
125 dense 3584 3584 1.000000 2.582357 0.030128 -4.317275 179
126 dense 3584 512 7.000000 4.164873 0.034350 -11.118704 59
127 dense 18944 3584 5.285714 3.905247 0.020552 -5.544317 108
128 dense 18944 3584 5.285714 2.918007 0.011444 -2.822267 178
129 dense 18944 3584 5.285714 3.073060 0.011264 -3.317761 173
130 dense 3584 512 7.000000 2.677159 0.042356 -6.437693 90
131 dense 3584 3584 1.000000 1.760713 0.079968 -3.317813 1208 over-trained
132 dense 3584 3584 1.000000 2.539170 0.038109 -4.220024 196
133 dense 3584 512 7.000000 4.663366 0.049718 -13.005406 44
134 dense 18944 3584 5.285714 4.135879 0.025811 -6.157307 69
135 dense 18944 3584 5.285714 2.918575 0.012311 -2.820809 191
136 dense 18944 3584 5.285714 3.035494 0.014751 -3.109055 254
137 dense 3584 512 7.000000 2.643249 0.044478 -6.064884 116
138 dense 3584 3584 1.000000 1.784613 0.064303 -3.209583 1142 over-trained
139 dense 3584 3584 1.000000 2.549878 0.047875 -4.269137 211
140 dense 3584 512 7.000000 4.268723 0.031378 -11.201447 40
141 dense 18944 3584 5.285714 4.367630 0.034752 -7.088047 82
142 dense 18944 3584 5.285714 2.985145 0.010980 -3.113118 207
143 dense 18944 3584 5.285714 3.149279 0.011517 -3.608860 181
144 dense 3584 512 7.000000 3.177485 0.041815 -7.653565 55
145 dense 3584 3584 1.000000 1.780069 0.072396 -3.664179 1202 over-trained
146 dense 3584 3584 1.000000 2.664466 0.040239 -4.581560 175
147 dense 3584 512 7.000000 4.206780 0.041585 -11.200545 55
148 dense 18944 3584 5.285714 4.529061 0.023131 -7.492775 88
149 dense 18944 3584 5.285714 3.168511 0.011689 -3.524070 154
150 dense 18944 3584 5.285714 3.331889 0.017649 -4.119764 180
151 dense 3584 512 7.000000 2.991785 0.026924 -7.210872 75
152 dense 3584 3584 1.000000 1.824632 0.080212 -3.534647 1220 over-trained
153 dense 3584 3584 1.000000 2.534592 0.035668 -4.478188 244
154 dense 3584 512 7.000000 4.544833 0.042267 -12.793041 50
155 dense 18944 3584 5.285714 3.270119 0.011680 -3.746493 168
156 dense 18944 3584 5.285714 3.428445 0.014783 -4.373946 201
157 dense 3584 512 7.000000 2.769691 0.036582 -6.431898 85
158 dense 3584 3584 1.000000 1.929996 0.087598 -3.201333 1101 over-trained
159 dense 3584 3584 1.000000 2.720730 0.040593 -4.606027 139
160 dense 3584 512 7.000000 4.159775 0.041573 -10.831371 41
161 dense 18944 3584 5.285714 4.356084 0.021544 -6.919779 127
162 dense 18944 3584 5.285714 4.274004 0.015960 -6.635674 175
163 dense 18944 3584 5.285714 3.273720 0.010317 -3.718226 311
164 dense 18944 3584 5.285714 3.449448 0.015224 -4.446819 252
165 dense 3584 512 7.000000 2.889115 0.025320 -6.684956 86
166 dense 3584 3584 1.000000 3.693204 0.034508 -6.077320 98
167 dense 3584 3584 1.000000 2.541299 0.028953 -4.380039 237
168 dense 3584 512 7.000000 4.110068 0.038394 -11.001303 56
169 dense 18944 3584 5.285714 4.296471 0.012024 -6.514128 177
170 dense 18944 3584 5.285714 3.265415 0.014279 -3.823588 337
171 dense 18944 3584 5.285714 3.504927 0.018527 -4.410312 255
172 dense 3584 512 7.000000 2.910547 0.021157 -6.864169 89
173 dense 3584 3584 1.000000 3.176497 0.038664 -4.265022 159
174 dense 3584 3584 1.000000 2.633019 0.027946 -4.538562 198
175 dense 3584 512 7.000000 3.718309 0.030226 -8.936186 40
176 dense 18944 3584 5.285714 4.131151 0.015282 -5.895472 208
177 dense 18944 3584 5.285714 3.123879 0.012924 -3.658365 457
178 dense 18944 3584 5.285714 3.331856 0.015545 -4.178452 367
179 dense 3584 512 7.000000 2.886057 0.035729 -6.864687 83
180 dense 3584 3584 1.000000 3.691440 0.022429 -6.195002 86
181 dense 3584 3584 1.000000 2.640177 0.031058 -4.504743 207
182 dense 3584 512 7.000000 3.598717 0.030915 -8.972972 66
183 dense 18944 3584 5.285714 3.747557 0.008316 -4.712964 293
184 dense 18944 3584 5.285714 2.921875 0.014099 -2.744802 463
185 dense 18944 3584 5.285714 3.168118 0.015355 -3.088783 382
186 dense 3584 512 7.000000 2.766663 0.024284 -6.434418 110
187 dense 3584 3584 1.000000 2.877632 0.050971 -3.081272 172
188 dense 3584 3584 1.000000 2.515341 0.023255 -3.825720 189
189 dense 3584 512 7.000000 2.956150 0.017530 -6.408234 132
190 dense 18944 3584 5.285714 3.397786 0.034416 -3.292643 506
191 dense 18944 3584 5.285714 2.980434 0.018731 -2.027572 567
192 dense 18944 3584 5.285714 3.230781 0.022551 -2.604666 455
193 dense 3584 512 7.000000 2.501601 0.020487 -5.118930 143
194 dense 3584 3584 1.000000 2.895362 0.037132 -3.718095 24
195 dense 3584 3584 1.000000 2.559183 0.032989 -3.674887 213
196 dense 3584 512 7.000000 2.744256 0.020208 -6.012969 124