Qwen2.5-0.5B-Instruct


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

Qwen2.5-0.5B-Instruct Model Set Plots

Qwen2.5-small Compared to Base Model Plots

Qwen2.5-0.5B-Instruct Model Selected Details
id layer_type N M Q alpha D alpha-hat num_spikes warning
1 dense 4864 896 5.428571 8.040342 0.054421 11.211399 93 under-trained
2 dense 4864 896 5.428571 3.265221 0.052069 5.718243 374
3 dense 4864 896 5.428571 13.858658 0.081286 12.357890 58 under-trained
4 dense 896 128 7.000000 1.705504 0.080801 3.839151 50 over-trained
5 dense 896 896 1.000000 1.753546 0.098443 1.549687 333 over-trained
6 dense 896 896 1.000000 1.941109 0.044646 6.008260 72 over-trained
7 dense 896 128 7.000000 3.788853 0.135768 -1.038288 40
8 dense 896 128 7.000000 9.259229 0.083157 -2.977757 22 under-trained
9 dense 896 896 1.000000 3.506172 0.053103 4.418250 68
10 dense 896 128 7.000000 4.612226 0.095308 4.250618 31
11 dense 896 896 1.000000 4.748578 0.033730 4.257064 36
12 dense 4864 896 5.428571 3.893259 0.054545 6.519901 236
13 dense 4864 896 5.428571 7.166078 0.042981 9.934975 91 under-trained
14 dense 4864 896 5.428571 13.029151 0.126487 10.187965 85 under-trained
15 dense 4864 896 5.428571 4.719416 0.032387 8.123322 139
16 dense 4864 896 5.428571 6.908085 0.090775 10.516904 161 under-trained
17 dense 896 128 7.000000 4.347263 0.159526 3.361843 48
18 dense 896 896 1.000000 2.546359 0.123995 2.433509 234
19 dense 896 896 1.000000 3.784185 0.111680 4.024313 91
20 dense 896 128 7.000000 5.274816 0.136336 -1.362573 48
21 dense 4864 896 5.428571 7.537951 0.046343 9.785726 76 under-trained
22 dense 896 896 1.000000 3.896605 0.080914 3.597993 79
23 dense 896 128 7.000000 8.704572 0.154128 -0.904002 32 under-trained
24 dense 896 896 1.000000 5.545392 0.053260 3.805568 45
25 dense 4864 896 5.428571 5.998621 0.033834 7.733741 87
26 dense 4864 896 5.428571 18.585633 0.126233 14.931464 53 under-trained
27 dense 4864 896 5.428571 6.316034 0.032099 11.059773 93 under-trained
28 dense 896 128 7.000000 8.210047 0.107130 5.597431 13 under-trained
29 dense 896 896 1.000000 2.504616 0.116583 2.271184 201
30 dense 896 896 1.000000 4.700882 0.098050 3.501952 54
31 dense 896 128 7.000000 7.040867 0.119289 -0.109531 32 under-trained
32 dense 4864 896 5.428571 10.451870 0.071741 10.982097 87 under-trained
33 dense 4864 896 5.428571 4.935176 0.027320 8.847282 125
34 dense 4864 896 5.428571 7.076002 0.042569 10.347336 73 under-trained
35 dense 896 128 7.000000 5.839008 0.121620 3.393528 29
36 dense 896 128 7.000000 7.466681 0.147102 -0.174624 42 under-trained
37 dense 4864 896 5.428571 7.116280 0.045311 9.741597 70 under-trained
38 dense 4864 896 5.428571 5.049429 0.035409 9.535447 49
39 dense 4864 896 5.428571 7.549522 0.123157 6.440213 167 under-trained
40 dense 896 128 7.000000 6.243987 0.115955 3.710162 21 under-trained
41 dense 896 896 1.000000 7.337058 0.060886 5.719521 35 under-trained
42 dense 896 896 1.000000 2.753109 0.104305 2.425995 154
43 dense 896 896 1.000000 2.514152 0.112039 2.243148 200
44 dense 4864 896 5.428571 5.657994 0.046279 9.877973 106
45 dense 4864 896 5.428571 15.300423 0.124648 13.355082 60 under-trained
46 dense 896 128 7.000000 4.443214 0.153069 3.112632 48
47 dense 896 896 1.000000 4.278949 0.030678 3.322294 55
48 dense 896 128 7.000000 8.148426 0.135110 -0.110242 31 under-trained
49 dense 4864 896 5.428571 7.179381 0.049754 9.858648 72 under-trained
50 dense 4864 896 5.428571 5.650973 0.081246 7.601290 145
51 dense 4864 896 5.428571 5.138363 0.027620 9.244165 51
52 dense 4864 896 5.428571 10.677734 0.121782 9.331619 100 under-trained
53 dense 896 128 7.000000 4.094685 0.158592 2.251377 45
54 dense 896 896 1.000000 9.579512 0.121301 5.640510 35 under-trained
55 dense 896 896 1.000000 2.770068 0.103430 2.488193 144
56 dense 896 128 7.000000 7.368676 0.155450 -0.077994 42 under-trained
57 dense 896 128 7.000000 5.963473 0.124741 -0.325195 44
58 dense 896 896 1.000000 2.932539 0.106932 4.077917 158
59 dense 896 896 1.000000 4.293945 0.130296 3.242153 116
60 dense 4864 896 5.428571 6.238356 0.029236 9.272006 57 under-trained
61 dense 4864 896 5.428571 16.978627 0.110543 15.404228 38 under-trained
62 dense 4864 896 5.428571 5.369935 0.044810 9.280906 78
63 dense 896 128 7.000000 4.130552 0.104780 3.392419 25
64 dense 4864 896 5.428571 5.106457 0.055582 7.885743 94
65 dense 4864 896 5.428571 5.695533 0.047542 9.191383 61
66 dense 4864 896 5.428571 8.333649 0.099378 7.543141 117 under-trained
67 dense 896 128 7.000000 5.011675 0.124815 2.697092 26
68 dense 896 896 1.000000 2.916346 0.115069 1.694782 151
69 dense 896 896 1.000000 1.998083 0.116933 1.973538 259 over-trained
70 dense 896 128 7.000000 4.965142 0.142116 -0.034488 50
71 dense 4864 896 5.428571 6.002941 0.106294 5.637438 176 under-trained
72 dense 896 128 7.000000 9.433002 0.107955 0.946462 22 under-trained
73 dense 4864 896 5.428571 5.852468 0.042849 9.275457 85
74 dense 4864 896 5.428571 4.391382 0.083457 7.438902 165
75 dense 896 128 7.000000 2.668288 0.142165 1.663138 57
76 dense 896 896 1.000000 3.270324 0.127600 2.280287 169
77 dense 896 896 1.000000 3.589951 0.089913 3.851545 74
78 dense 4864 896 5.428571 4.025262 0.082214 6.194480 226
79 dense 896 128 7.000000 6.356385 0.113886 0.463906 37 under-trained
80 dense 896 896 1.000000 2.439577 0.119388 2.886963 161
81 dense 896 896 1.000000 3.871033 0.036450 3.943120 49
82 dense 896 128 7.000000 7.304252 0.154307 3.734054 18 under-trained
83 dense 4864 896 5.428571 5.627771 0.039644 9.317909 48
84 dense 4864 896 5.428571 5.882456 0.121028 7.937960 203
85 dense 4864 896 5.428571 8.572833 0.095292 7.927053 92 under-trained
86 dense 4864 896 5.428571 5.769841 0.042735 8.746235 63
87 dense 4864 896 5.428571 5.709195 0.036244 9.535468 62
88 dense 896 896 1.000000 3.064031 0.100022 2.879952 98
89 dense 896 128 7.000000 6.161392 0.118143 0.287017 42 under-trained
90 dense 896 128 7.000000 4.881164 0.145917 2.968580 30
91 dense 896 896 1.000000 5.894110 0.112254 4.319557 53
92 dense 4864 896 5.428571 4.302835 0.098392 6.717023 237
93 dense 896 128 7.000000 6.450270 0.142982 3.446783 21 under-trained
94 dense 896 896 1.000000 3.703193 0.121237 2.340584 119
95 dense 896 896 1.000000 2.264856 0.104320 2.167589 199
96 dense 896 128 7.000000 5.698374 0.154687 0.526115 49
97 dense 4864 896 5.428571 6.059626 0.024868 8.935609 58 under-trained
98 dense 4864 896 5.428571 9.116327 0.094115 8.967249 83 under-trained
99 dense 4864 896 5.428571 6.866573 0.022450 9.194867 63 under-trained
100 dense 4864 896 5.428571 5.201582 0.093304 8.216190 153
101 dense 4864 896 5.428571 10.379960 0.099741 10.154033 67 under-trained
102 dense 896 128 7.000000 4.464800 0.158862 2.581389 38
103 dense 896 896 1.000000 5.040300 0.081282 3.440180 47
104 dense 896 896 1.000000 2.472648 0.093339 2.273189 161
105 dense 896 128 7.000000 4.832291 0.132157 0.458495 64
106 dense 4864 896 5.428571 8.215156 0.040717 10.145047 59 under-trained
107 dense 4864 896 5.428571 5.911166 0.050139 9.862516 90
108 dense 4864 896 5.428571 12.829300 0.118830 12.688231 65 under-trained
109 dense 896 128 7.000000 3.982223 0.155055 2.210965 35
110 dense 896 896 1.000000 3.124897 0.069863 2.470788 95
111 dense 896 896 1.000000 2.500863 0.090518 2.302558 170
112 dense 896 128 7.000000 5.909795 0.133200 0.830423 38
113 dense 896 896 1.000000 2.467650 0.089664 2.838671 123
114 dense 896 128 7.000000 7.224839 0.155089 0.953820 34 under-trained
115 dense 4864 896 5.428571 8.476228 0.061991 11.432287 90 under-trained
116 dense 4864 896 5.428571 6.582619 0.046518 11.045835 98 under-trained
117 dense 4864 896 5.428571 9.162498 0.061427 11.311176 73 under-trained
118 dense 896 128 7.000000 2.925996 0.096023 1.796481 41
119 dense 896 896 1.000000 7.567919 0.060736 5.572995 29 under-trained
120 dense 896 128 7.000000 8.331153 0.137307 1.418412 28 under-trained
121 dense 896 896 1.000000 2.861464 0.088065 3.003921 98
122 dense 896 896 1.000000 5.370602 0.117772 5.339380 65
123 dense 896 128 7.000000 3.994296 0.131943 2.400430 27
124 dense 4864 896 5.428571 8.845118 0.121033 8.543534 117 under-trained
125 dense 4864 896 5.428571 6.431614 0.048163 11.214119 96 under-trained
126 dense 4864 896 5.428571 9.512996 0.066366 12.316115 77 under-trained
127 dense 4864 896 5.428571 7.229188 0.120315 7.198850 154 under-trained
128 dense 896 128 7.000000 4.246674 0.136454 2.106592 35
129 dense 896 896 1.000000 2.266186 0.131268 1.540139 268
130 dense 896 896 1.000000 2.810649 0.098799 2.769977 136
131 dense 896 128 7.000000 4.353987 0.154524 1.205799 74
132 dense 4864 896 5.428571 7.376154 0.058358 11.857703 72 under-trained
133 dense 4864 896 5.428571 9.739678 0.040235 11.787124 58 under-trained
134 dense 896 128 7.000000 5.521502 0.134602 1.302506 51
135 dense 896 896 1.000000 2.890111 0.090928 2.815623 150
136 dense 4864 896 5.428571 11.376712 0.048066 12.441277 42 under-trained
137 dense 4864 896 5.428571 6.637477 0.059823 11.310353 117 under-trained
138 dense 4864 896 5.428571 7.739570 0.126378 8.258122 145 under-trained
139 dense 896 128 7.000000 2.625498 0.152226 1.244735 78
140 dense 896 896 1.000000 2.025645 0.123803 1.453554 318
141 dense 4864 896 5.428571 6.676192 0.046666 10.951633 97 under-trained
142 dense 4864 896 5.428571 10.459114 0.044769 11.503720 58 under-trained
143 dense 896 128 7.000000 3.903641 0.131119 2.336452 26
144 dense 896 896 1.000000 7.708240 0.122041 6.165900 37 under-trained
145 dense 896 896 1.000000 2.444367 0.094987 2.560513 155
146 dense 896 128 7.000000 3.505638 0.145670 1.515202 82
147 dense 4864 896 5.428571 14.457317 0.053852 15.470645 38 under-trained
148 dense 4864 896 5.428571 8.479177 0.125430 8.909933 124 under-trained
149 dense 4864 896 5.428571 5.866510 0.048950 9.826199 111
150 dense 4864 896 5.428571 6.666003 0.083036 11.228750 129 under-trained
151 dense 896 896 1.000000 4.532203 0.105107 4.233377 104
152 dense 896 128 7.000000 5.733378 0.135498 3.315494 33
153 dense 896 128 7.000000 2.060075 0.108704 1.171895 67
154 dense 896 896 1.000000 2.462721 0.098281 2.546883 130
155 dense 4864 896 5.428571 7.198595 0.119965 7.850524 159 under-trained
156 dense 4864 896 5.428571 5.284220 0.033388 8.498887 110
157 dense 4864 896 5.428571 6.560228 0.081838 9.991615 130 under-trained
158 dense 896 128 7.000000 2.937743 0.089889 1.651481 29
159 dense 896 896 1.000000 5.723969 0.036925 5.573910 32
160 dense 896 896 1.000000 1.862237 0.111898 1.971595 311 over-trained
161 dense 896 128 7.000000 3.939963 0.158659 2.318404 53
162 dense 896 896 1.000000 4.105360 0.023106 5.035519 56
163 dense 4864 896 5.428571 7.795438 0.098367 9.859751 95 under-trained
164 dense 4864 896 5.428571 4.666909 0.051854 9.084435 197
165 dense 4864 896 5.428571 5.470770 0.071539 9.262204 174
166 dense 896 128 7.000000 3.274775 0.091676 1.613782 35
167 dense 896 896 1.000000 3.717732 0.061811 4.619922 41
168 dense 896 128 7.000000 3.951470 0.149750 2.878433 59