Find this model in the RedPajama model summary
| layer_type | N | M | Q | alpha | D | alpha-hat | log_SN | rank_loss | |
|---|---|---|---|---|---|---|---|---|---|
| layer_id | |||||||||
| 4 | DENSE | 7680 | 2560 | 3.00 | 2.11 | 0.04 | 6.75 | 3.20 | 0 |
| 5 | DENSE | 2560 | 2560 | 1.00 | 3.42 | 0.05 | 4.17 | 1.22 | 7 |
| 6 | DENSE | 10240 | 2560 | 4.00 | 5.12 | 0.07 | 11.15 | 2.18 | 0 |
| 7 | DENSE | 10240 | 2560 | 4.00 | 7.96 | 0.06 | 14.75 | 1.85 | 0 |
| 10 | DENSE | 7680 | 2560 | 3.00 | 3.70 | 0.02 | 7.60 | 2.05 | 0 |
| 11 | DENSE | 2560 | 2560 | 1.00 | 4.83 | 0.02 | 7.00 | 1.45 | 2 |
| 12 | DENSE | 10240 | 2560 | 4.00 | 3.07 | 0.02 | 6.85 | 2.23 | 0 |
| 13 | DENSE | 10240 | 2560 | 4.00 | 4.05 | 0.04 | 6.20 | 1.53 | 0 |
| 16 | DENSE | 7680 | 2560 | 3.00 | 2.53 | 0.04 | 4.84 | 1.91 | 0 |
| 17 | DENSE | 2560 | 2560 | 1.00 | 4.03 | 0.03 | 6.63 | 1.64 | 3 |
| 18 | DENSE | 10240 | 2560 | 4.00 | 3.21 | 0.01 | 8.42 | 2.63 | 0 |
| 19 | DENSE | 10240 | 2560 | 4.00 | 3.80 | 0.01 | 7.56 | 1.99 | 0 |
| 22 | DENSE | 7680 | 2560 | 3.00 | 3.28 | 0.02 | 5.93 | 1.81 | 0 |
| 23 | DENSE | 2560 | 2560 | 1.00 | 3.96 | 0.04 | 6.77 | 1.71 | 4 |
| 24 | DENSE | 10240 | 2560 | 4.00 | 3.40 | 0.02 | 7.27 | 2.14 | 0 |
| 25 | DENSE | 10240 | 2560 | 4.00 | 4.07 | 0.01 | 7.03 | 1.73 | 0 |
| 28 | DENSE | 7680 | 2560 | 3.00 | 3.54 | 0.01 | 6.76 | 1.91 | 0 |
| 29 | DENSE | 2560 | 2560 | 1.00 | 3.62 | 0.04 | 5.70 | 1.57 | 2 |
| 30 | DENSE | 10240 | 2560 | 4.00 | 3.36 | 0.02 | 7.25 | 2.16 | 0 |
| 31 | DENSE | 10240 | 2560 | 4.00 | 3.96 | 0.02 | 6.84 | 1.73 | 0 |
| 34 | DENSE | 7680 | 2560 | 3.00 | 3.57 | 0.01 | 6.92 | 1.94 | 0 |
| 35 | DENSE | 2560 | 2560 | 1.00 | 3.69 | 0.04 | 5.82 | 1.58 | 3 |
| 36 | DENSE | 10240 | 2560 | 4.00 | 3.47 | 0.02 | 7.46 | 2.15 | 0 |
| 37 | DENSE | 10240 | 2560 | 4.00 | 3.94 | 0.02 | 6.30 | 1.60 | 0 |
| 40 | DENSE | 7680 | 2560 | 3.00 | 3.80 | 0.02 | 7.28 | 1.92 | 0 |
| 41 | DENSE | 2560 | 2560 | 1.00 | 5.01 | 0.04 | 7.88 | 1.57 | 2 |
| 42 | DENSE | 10240 | 2560 | 4.00 | 3.45 | 0.01 | 7.43 | 2.16 | 0 |
| 43 | DENSE | 10240 | 2560 | 4.00 | 3.95 | 0.04 | 6.26 | 1.58 | 0 |
| 46 | DENSE | 7680 | 2560 | 3.00 | 3.60 | 0.01 | 6.85 | 1.90 | 0 |
| 47 | DENSE | 2560 | 2560 | 1.00 | 4.47 | 0.04 | 6.94 | 1.55 | 3 |
| 48 | DENSE | 10240 | 2560 | 4.00 | 3.42 | 0.02 | 7.36 | 2.15 | 0 |
| 49 | DENSE | 10240 | 2560 | 4.00 | 3.74 | 0.04 | 6.11 | 1.64 | 0 |
| 52 | DENSE | 7680 | 2560 | 3.00 | 3.65 | 0.02 | 6.98 | 1.91 | 0 |
| 53 | DENSE | 2560 | 2560 | 1.00 | 4.64 | 0.04 | 7.73 | 1.67 | 3 |
| 54 | DENSE | 10240 | 2560 | 4.00 | 3.42 | 0.03 | 7.34 | 2.15 | 0 |
| 55 | DENSE | 10240 | 2560 | 4.00 | 3.88 | 0.04 | 6.33 | 1.63 | 0 |
| 58 | DENSE | 7680 | 2560 | 3.00 | 3.42 | 0.02 | 6.44 | 1.88 | 0 |
| 59 | DENSE | 2560 | 2560 | 1.00 | 3.79 | 0.04 | 5.89 | 1.55 | 2 |
| 60 | DENSE | 10240 | 2560 | 4.00 | 3.43 | 0.03 | 7.32 | 2.13 | 0 |
| 61 | DENSE | 10240 | 2560 | 4.00 | 3.93 | 0.04 | 6.64 | 1.69 | 0 |
| 64 | DENSE | 7680 | 2560 | 3.00 | 3.30 | 0.02 | 6.14 | 1.86 | 0 |
| 65 | DENSE | 2560 | 2560 | 1.00 | 4.05 | 0.03 | 6.52 | 1.61 | 2 |
| 66 | DENSE | 10240 | 2560 | 4.00 | 3.43 | 0.03 | 7.25 | 2.11 | 0 |
| 67 | DENSE | 10240 | 2560 | 4.00 | 5.76 | 0.04 | 9.30 | 1.62 | 0 |
| 70 | DENSE | 7680 | 2560 | 3.00 | 3.37 | 0.02 | 6.31 | 1.87 | 0 |
| 71 | DENSE | 2560 | 2560 | 1.00 | 4.30 | 0.05 | 6.91 | 1.61 | 3 |
| 72 | DENSE | 10240 | 2560 | 4.00 | 3.41 | 0.03 | 7.11 | 2.08 | 0 |
| 73 | DENSE | 10240 | 2560 | 4.00 | 3.73 | 0.04 | 6.06 | 1.62 | 0 |
| 76 | DENSE | 7680 | 2560 | 3.00 | 3.21 | 0.02 | 6.11 | 1.90 | 0 |
| 77 | DENSE | 2560 | 2560 | 1.00 | 4.51 | 0.05 | 6.86 | 1.52 | 3 |
| 78 | DENSE | 10240 | 2560 | 4.00 | 3.87 | 0.03 | 8.18 | 2.11 | 0 |
| 79 | DENSE | 10240 | 2560 | 4.00 | 3.67 | 0.04 | 6.15 | 1.68 | 0 |
| 82 | DENSE | 7680 | 2560 | 3.00 | 3.24 | 0.03 | 6.03 | 1.86 | 0 |
| 83 | DENSE | 2560 | 2560 | 1.00 | 4.42 | 0.04 | 7.27 | 1.64 | 2 |
| 84 | DENSE | 10240 | 2560 | 4.00 | 3.93 | 0.03 | 8.17 | 2.08 | 0 |
| 85 | DENSE | 10240 | 2560 | 4.00 | 3.75 | 0.03 | 6.24 | 1.66 | 0 |
| 88 | DENSE | 7680 | 2560 | 3.00 | 3.07 | 0.03 | 5.77 | 1.88 | 0 |
| 89 | DENSE | 2560 | 2560 | 1.00 | 4.97 | 0.06 | 8.07 | 1.63 | 4 |
| 90 | DENSE | 10240 | 2560 | 4.00 | 3.54 | 0.04 | 7.32 | 2.07 | 0 |
| 91 | DENSE | 10240 | 2560 | 4.00 | 3.98 | 0.03 | 6.58 | 1.65 | 0 |
| 94 | DENSE | 7680 | 2560 | 3.00 | 3.14 | 0.02 | 5.83 | 1.86 | 0 |
| 95 | DENSE | 2560 | 2560 | 1.00 | 4.66 | 0.06 | 7.32 | 1.57 | 2 |
| 96 | DENSE | 10240 | 2560 | 4.00 | 3.80 | 0.03 | 7.94 | 2.09 | 0 |
| 97 | DENSE | 10240 | 2560 | 4.00 | 4.87 | 0.04 | 8.14 | 1.67 | 0 |
| 100 | DENSE | 7680 | 2560 | 3.00 | 3.16 | 0.01 | 5.83 | 1.85 | 0 |
| 101 | DENSE | 2560 | 2560 | 1.00 | 3.76 | 0.04 | 6.29 | 1.67 | 3 |
| 102 | DENSE | 10240 | 2560 | 4.00 | 3.74 | 0.03 | 7.90 | 2.11 | 0 |
| 103 | DENSE | 10240 | 2560 | 4.00 | 4.36 | 0.03 | 6.96 | 1.60 | 0 |
| 106 | DENSE | 7680 | 2560 | 3.00 | 3.49 | 0.02 | 6.45 | 1.85 | 0 |
| 107 | DENSE | 2560 | 2560 | 1.00 | 3.88 | 0.06 | 6.40 | 1.65 | 3 |
| 108 | DENSE | 10240 | 2560 | 4.00 | 4.46 | 0.03 | 9.39 | 2.11 | 0 |
| 109 | DENSE | 10240 | 2560 | 4.00 | 4.63 | 0.02 | 7.79 | 1.68 | 0 |
| 112 | DENSE | 7680 | 2560 | 3.00 | 3.54 | 0.01 | 6.70 | 1.89 | 0 |
| 113 | DENSE | 2560 | 2560 | 1.00 | 5.26 | 0.04 | 9.09 | 1.73 | 3 |
| 114 | DENSE | 10240 | 2560 | 4.00 | 4.37 | 0.03 | 9.26 | 2.12 | 0 |
| 115 | DENSE | 10240 | 2560 | 4.00 | 4.90 | 0.01 | 8.35 | 1.70 | 0 |
| 118 | DENSE | 7680 | 2560 | 3.00 | 3.69 | 0.01 | 7.00 | 1.90 | 0 |
| 119 | DENSE | 2560 | 2560 | 1.00 | 4.86 | 0.05 | 8.03 | 1.65 | 2 |
| 120 | DENSE | 10240 | 2560 | 4.00 | 4.00 | 0.03 | 8.60 | 2.15 | 0 |
| 121 | DENSE | 10240 | 2560 | 4.00 | 5.28 | 0.01 | 8.83 | 1.67 | 0 |
| 124 | DENSE | 7680 | 2560 | 3.00 | 4.08 | 0.03 | 8.03 | 1.97 | 0 |
| 125 | DENSE | 2560 | 2560 | 1.00 | 6.43 | 0.07 | 11.12 | 1.73 | 2 |
| 126 | DENSE | 10240 | 2560 | 4.00 | 3.60 | 0.02 | 7.92 | 2.20 | 0 |
| 127 | DENSE | 10240 | 2560 | 4.00 | 6.55 | 0.02 | 10.53 | 1.61 | 0 |
| 130 | DENSE | 7680 | 2560 | 3.00 | 4.27 | 0.04 | 8.31 | 1.94 | 0 |
| 131 | DENSE | 2560 | 2560 | 1.00 | 6.44 | 0.07 | 10.21 | 1.59 | 2 |
| 132 | DENSE | 10240 | 2560 | 4.00 | 3.99 | 0.03 | 8.77 | 2.20 | 0 |
| 133 | DENSE | 10240 | 2560 | 4.00 | 6.79 | 0.02 | 10.14 | 1.49 | 0 |
| 136 | DENSE | 7680 | 2560 | 3.00 | 3.88 | 0.03 | 7.66 | 1.97 | 0 |
| 137 | DENSE | 2560 | 2560 | 1.00 | 6.87 | 0.06 | 10.98 | 1.60 | 1 |
| 138 | DENSE | 10240 | 2560 | 4.00 | 4.06 | 0.04 | 8.94 | 2.20 | 0 |
| 139 | DENSE | 10240 | 2560 | 4.00 | 7.03 | 0.02 | 9.65 | 1.37 | 0 |
| 142 | DENSE | 7680 | 2560 | 3.00 | 4.23 | 0.03 | 8.46 | 2.00 | 0 |
| 143 | DENSE | 2560 | 2560 | 1.00 | 7.12 | 0.06 | 10.30 | 1.45 | 2 |
| 144 | DENSE | 10240 | 2560 | 4.00 | 4.04 | 0.04 | 8.82 | 2.18 | 0 |
| 145 | DENSE | 10240 | 2560 | 4.00 | 7.05 | 0.03 | 10.36 | 1.47 | 0 |
| 148 | DENSE | 7680 | 2560 | 3.00 | 3.15 | 0.01 | 6.31 | 2.00 | 0 |
| 149 | DENSE | 2560 | 2560 | 1.00 | 7.62 | 0.08 | 10.86 | 1.43 | 2 |
| 150 | DENSE | 10240 | 2560 | 4.00 | 3.87 | 0.04 | 8.48 | 2.19 | 0 |
| 151 | DENSE | 10240 | 2560 | 4.00 | 6.60 | 0.04 | 9.37 | 1.42 | 0 |
| 154 | DENSE | 7680 | 2560 | 3.00 | 3.75 | 0.01 | 7.51 | 2.00 | 0 |
| 155 | DENSE | 2560 | 2560 | 1.00 | 6.43 | 0.04 | 9.46 | 1.47 | 2 |
| 156 | DENSE | 10240 | 2560 | 4.00 | 4.08 | 0.04 | 8.92 | 2.19 | 0 |
| 157 | DENSE | 10240 | 2560 | 4.00 | 7.80 | 0.02 | 10.15 | 1.30 | 0 |
| 160 | DENSE | 7680 | 2560 | 3.00 | 3.87 | 0.01 | 7.69 | 1.99 | 0 |
| 161 | DENSE | 2560 | 2560 | 1.00 | 7.42 | 0.03 | 9.38 | 1.26 | 2 |
| 162 | DENSE | 10240 | 2560 | 4.00 | 4.17 | 0.04 | 9.07 | 2.17 | 0 |
| 163 | DENSE | 10240 | 2560 | 4.00 | 7.67 | 0.02 | 10.29 | 1.34 | 0 |
| 166 | DENSE | 7680 | 2560 | 3.00 | 3.65 | 0.02 | 7.33 | 2.01 | 0 |
| 167 | DENSE | 2560 | 2560 | 1.00 | 6.65 | 0.02 | 9.30 | 1.40 | 2 |
| 168 | DENSE | 10240 | 2560 | 4.00 | 3.99 | 0.02 | 8.69 | 2.18 | 0 |
| 169 | DENSE | 10240 | 2560 | 4.00 | 8.42 | 0.02 | 12.05 | 1.43 | 0 |
| 172 | DENSE | 7680 | 2560 | 3.00 | 3.94 | 0.02 | 7.88 | 2.00 | 0 |
| 173 | DENSE | 2560 | 2560 | 1.00 | 5.79 | 0.02 | 7.39 | 1.28 | 2 |
| 174 | DENSE | 10240 | 2560 | 4.00 | 4.20 | 0.02 | 9.06 | 2.16 | 0 |
| 175 | DENSE | 10240 | 2560 | 4.00 | 6.96 | 0.03 | 12.16 | 1.75 | 0 |
| 178 | DENSE | 7680 | 2560 | 3.00 | 3.37 | 0.02 | 6.72 | 2.00 | 0 |
| 179 | DENSE | 2560 | 2560 | 1.00 | 7.40 | 0.05 | 9.36 | 1.27 | 2 |
| 180 | DENSE | 10240 | 2560 | 4.00 | 4.45 | 0.01 | 9.42 | 2.12 | 0 |
| 181 | DENSE | 10240 | 2560 | 4.00 | 5.96 | 0.03 | 12.78 | 2.15 | 0 |
| 184 | DENSE | 7680 | 2560 | 3.00 | 3.46 | 0.03 | 10.96 | 3.17 | 0 |
| 185 | DENSE | 2560 | 2560 | 1.00 | 4.99 | 0.03 | 8.29 | 1.66 | 2 |
| 186 | DENSE | 10240 | 2560 | 4.00 | 4.32 | 0.02 | 8.97 | 2.08 | 0 |
| 187 | DENSE | 10240 | 2560 | 4.00 | 4.94 | 0.02 | 10.66 | 2.16 | 0 |
| 190 | DENSE | 7680 | 2560 | 3.00 | 2.70 | 0.05 | 8.53 | 3.16 | 0 |
| 191 | DENSE | 2560 | 2560 | 1.00 | 3.91 | 0.06 | 8.56 | 2.19 | 2 |
| 192 | DENSE | 10240 | 2560 | 4.00 | 3.16 | 0.03 | 6.63 | 2.10 | 0 |
| 193 | DENSE | 10240 | 2560 | 4.00 | 4.02 | 0.04 | 8.67 | 2.16 | 0 |