airoboros-13b / README.md
jondurbin's picture
Update README.md
9553034
|
raw
history blame
38.8 kB
---
license: other
---
# Overview
This is a fine-tuned 13b parameter LlaMa model, using completely synthetic training data created by https://github.com/jondurbin/airoboros
### Eval (gpt4 judging)
![chart](meta-chart.png)
| model | raw score | gpt-3.5 adjusted score |
| --- | --- | --- |
| __airoboros-13b__ | __17947__ | __98.087__ |
| gpt35 | 18297 | 100.0 |
| gpt4-x-alpasta-30b | 15612 | 85.33 |
| manticore-13b | 15856 | 86.66 |
| vicuna-13b-1.1 | 16306 | 89.12 |
| wizard-vicuna-13b-uncensored | 16287 | 89.01 |
<details>
<summary>individual question scores, with shareGPT links (200 prompts generated by gpt-4)</summary>
| question | airoboros-13b | gpt35 | gpt4-x-alpasta-30b | manticore-13b | vicuna-13b-1.1 | wizard-vicuna-13b-uncensored | link |
|-----------:|----------------:|--------:|---------------------:|----------------:|-----------------:|-------------------------------:|:---------------------------------------|
| 1 | 80 | 95 | 70 | 90 | 85 | 60 | [eval](https://sharegpt.com/c/PIbRQD3) |
| 2 | 20 | 95 | 40 | 30 | 90 | 80 | [eval](https://sharegpt.com/c/fSzwzzd) |
| 3 | 100 | 100 | 100 | 95 | 95 | 100 | [eval](https://sharegpt.com/c/AXMzZiO) |
| 4 | 90 | 100 | 85 | 60 | 95 | 100 | [eval](https://sharegpt.com/c/7obzJm2) |
| 5 | 95 | 90 | 80 | 85 | 95 | 75 | [eval](https://sharegpt.com/c/cRpj6M1) |
| 6 | 100 | 95 | 90 | 95 | 98 | 92 | [eval](https://sharegpt.com/c/p0by1T7) |
| 7 | 50 | 100 | 80 | 95 | 60 | 55 | [eval](https://sharegpt.com/c/rowNlKx) |
| 8 | 70 | 90 | 80 | 60 | 85 | 40 | [eval](https://sharegpt.com/c/I4POj4I) |
| 9 | 100 | 95 | 50 | 85 | 40 | 60 | [eval](https://sharegpt.com/c/gUAeiRp) |
| 10 | 85 | 60 | 55 | 65 | 50 | 70 | [eval](https://sharegpt.com/c/Lgw4QQL) |
| 11 | 95 | 100 | 85 | 90 | 60 | 75 | [eval](https://sharegpt.com/c/X9tDYft) |
| 12 | 100 | 95 | 70 | 80 | 50 | 85 | [eval](https://sharegpt.com/c/9V2ElkH) |
| 13 | 100 | 95 | 80 | 70 | 60 | 90 | [eval](https://sharegpt.com/c/D5xg6qt) |
| 14 | 95 | 100 | 70 | 85 | 90 | 90 | [eval](https://sharegpt.com/c/lQnSfDs) |
| 15 | 80 | 95 | 90 | 60 | 30 | 85 | [eval](https://sharegpt.com/c/1hpHGNc) |
| 16 | 60 | 95 | 0 | 75 | 50 | 40 | [eval](https://sharegpt.com/c/an6TqE4) |
| 17 | 100 | 95 | 90 | 98 | 95 | 95 | [eval](https://sharegpt.com/c/7vr6n3F) |
| 18 | 60 | 85 | 40 | 50 | 20 | 0 | [eval](https://sharegpt.com/c/TOkMkgE) |
| 19 | 100 | 90 | 85 | 95 | 95 | 80 | [eval](https://sharegpt.com/c/Qu7ak0r) |
| 20 | 100 | 95 | 100 | 95 | 90 | 95 | [eval](https://sharegpt.com/c/hMD4gPo) |
| 21 | 95 | 90 | 96 | 80 | 92 | 88 | [eval](https://sharegpt.com/c/HTlicNh) |
| 22 | 95 | 92 | 90 | 93 | 89 | 91 | [eval](https://sharegpt.com/c/MjxHpAf) |
| 23 | 95 | 93 | 90 | 94 | 96 | 92 | [eval](https://sharegpt.com/c/4RvxOR9) |
| 24 | 95 | 90 | 93 | 88 | 92 | 85 | [eval](https://sharegpt.com/c/PcAIU9r) |
| 25 | 95 | 90 | 85 | 96 | 88 | 92 | [eval](https://sharegpt.com/c/MMqul3q) |
| 26 | 95 | 95 | 90 | 93 | 92 | 91 | [eval](https://sharegpt.com/c/YQsLyzJ) |
| 27 | 95 | 98 | 80 | 97 | 99 | 96 | [eval](https://sharegpt.com/c/UDhSTMq) |
| 28 | 95 | 93 | 90 | 87 | 92 | 89 | [eval](https://sharegpt.com/c/4gCfdCV) |
| 29 | 90 | 85 | 95 | 80 | 92 | 75 | [eval](https://sharegpt.com/c/bkQs4SP) |
| 30 | 90 | 85 | 95 | 93 | 80 | 92 | [eval](https://sharegpt.com/c/LeLCEEt) |
| 31 | 95 | 92 | 90 | 91 | 93 | 89 | [eval](https://sharegpt.com/c/DFxNzVu) |
| 32 | 100 | 95 | 90 | 85 | 80 | 95 | [eval](https://sharegpt.com/c/gnVzNML) |
| 33 | 95 | 97 | 93 | 92 | 96 | 94 | [eval](https://sharegpt.com/c/y7pxMIy) |
| 34 | 95 | 93 | 94 | 90 | 88 | 92 | [eval](https://sharegpt.com/c/5UeCvTY) |
| 35 | 90 | 95 | 98 | 85 | 96 | 92 | [eval](https://sharegpt.com/c/T4oL9I5) |
| 36 | 90 | 88 | 85 | 80 | 82 | 84 | [eval](https://sharegpt.com/c/HnGyTAG) |
| 37 | 90 | 95 | 85 | 87 | 92 | 88 | [eval](https://sharegpt.com/c/ZbRMBNj) |
| 38 | 95 | 97 | 96 | 90 | 93 | 92 | [eval](https://sharegpt.com/c/iTmFJqd) |
| 39 | 95 | 93 | 92 | 90 | 89 | 91 | [eval](https://sharegpt.com/c/VuPifET) |
| 40 | 90 | 95 | 93 | 92 | 94 | 91 | [eval](https://sharegpt.com/c/AvFAH1x) |
| 41 | 90 | 85 | 95 | 80 | 88 | 75 | [eval](https://sharegpt.com/c/4ealKGN) |
| 42 | 85 | 90 | 95 | 88 | 92 | 80 | [eval](https://sharegpt.com/c/bE1b2vX) |
| 43 | 90 | 95 | 92 | 85 | 80 | 87 | [eval](https://sharegpt.com/c/I3nMPBC) |
| 44 | 85 | 90 | 95 | 80 | 88 | 75 | [eval](https://sharegpt.com/c/as7r3bW) |
| 45 | 85 | 80 | 75 | 90 | 70 | 82 | [eval](https://sharegpt.com/c/qYceaUa) |
| 46 | 90 | 85 | 95 | 92 | 93 | 80 | [eval](https://sharegpt.com/c/g4FXchU) |
| 47 | 90 | 95 | 75 | 85 | 80 | 70 | [eval](https://sharegpt.com/c/6kGLvL5) |
| 48 | 85 | 90 | 80 | 88 | 82 | 83 | [eval](https://sharegpt.com/c/SRozqaF) |
| 49 | 85 | 90 | 95 | 92 | 88 | 80 | [eval](https://sharegpt.com/c/GoKydf6) |
| 50 | 85 | 90 | 80 | 75 | 95 | 88 | [eval](https://sharegpt.com/c/37aXkHQ) |
| 51 | 85 | 90 | 80 | 88 | 84 | 92 | [eval](https://sharegpt.com/c/nVuUaTj) |
| 52 | 80 | 90 | 75 | 85 | 70 | 95 | [eval](https://sharegpt.com/c/TkAQKLC) |
| 53 | 90 | 88 | 85 | 80 | 92 | 83 | [eval](https://sharegpt.com/c/55cO2y0) |
| 54 | 85 | 75 | 90 | 80 | 78 | 88 | [eval](https://sharegpt.com/c/tXtq5lT) |
| 55 | 85 | 90 | 80 | 82 | 75 | 88 | [eval](https://sharegpt.com/c/TfMjeJQ) |
| 56 | 90 | 85 | 40 | 95 | 80 | 88 | [eval](https://sharegpt.com/c/2jQ6K2S) |
| 57 | 85 | 95 | 90 | 75 | 88 | 80 | [eval](https://sharegpt.com/c/aQtr2ca) |
| 58 | 85 | 95 | 90 | 92 | 89 | 88 | [eval](https://sharegpt.com/c/tbWLyZ7) |
| 59 | 80 | 85 | 75 | 60 | 90 | 70 | [eval](https://sharegpt.com/c/moHC7i2) |
| 60 | 85 | 90 | 87 | 80 | 88 | 75 | [eval](https://sharegpt.com/c/GK6GShh) |
| 61 | 85 | 80 | 75 | 50 | 90 | 80 | [eval](https://sharegpt.com/c/ugcW4qG) |
| 62 | 95 | 80 | 90 | 85 | 75 | 82 | [eval](https://sharegpt.com/c/WL8iq6F) |
| 63 | 85 | 90 | 80 | 70 | 95 | 88 | [eval](https://sharegpt.com/c/TZJKnvS) |
| 64 | 90 | 95 | 70 | 85 | 80 | 75 | [eval](https://sharegpt.com/c/beNOKb5) |
| 65 | 90 | 85 | 70 | 75 | 80 | 60 | [eval](https://sharegpt.com/c/o2oRCF5) |
| 66 | 95 | 90 | 70 | 50 | 85 | 80 | [eval](https://sharegpt.com/c/TNjbK6D) |
| 67 | 80 | 85 | 40 | 60 | 90 | 95 | [eval](https://sharegpt.com/c/rJvszWJ) |
| 68 | 75 | 60 | 80 | 55 | 70 | 85 | [eval](https://sharegpt.com/c/HJwRkro) |
| 69 | 90 | 85 | 60 | 50 | 80 | 95 | [eval](https://sharegpt.com/c/AeFoSDK) |
| 70 | 45 | 85 | 60 | 20 | 65 | 75 | [eval](https://sharegpt.com/c/KA1cgOl) |
| 71 | 85 | 90 | 30 | 60 | 80 | 70 | [eval](https://sharegpt.com/c/RTy8n0y) |
| 72 | 90 | 95 | 80 | 40 | 85 | 70 | [eval](https://sharegpt.com/c/PJMJoXh) |
| 73 | 85 | 90 | 70 | 75 | 80 | 95 | [eval](https://sharegpt.com/c/Ib3jzyC) |
| 74 | 90 | 70 | 50 | 20 | 60 | 40 | [eval](https://sharegpt.com/c/oMmqqtX) |
| 75 | 90 | 95 | 75 | 60 | 85 | 80 | [eval](https://sharegpt.com/c/qRNhNTw) |
| 76 | 85 | 80 | 60 | 70 | 65 | 75 | [eval](https://sharegpt.com/c/3MAHQIy) |
| 77 | 90 | 85 | 80 | 75 | 82 | 70 | [eval](https://sharegpt.com/c/0Emc5HS) |
| 78 | 90 | 95 | 80 | 70 | 85 | 75 | [eval](https://sharegpt.com/c/UqAxRWF) |
| 79 | 85 | 75 | 30 | 80 | 90 | 70 | [eval](https://sharegpt.com/c/eywxGAw) |
| 80 | 85 | 90 | 50 | 70 | 80 | 60 | [eval](https://sharegpt.com/c/A2KSEWP) |
| 81 | 100 | 95 | 98 | 99 | 97 | 96 | [eval](https://sharegpt.com/c/C8rebQf) |
| 82 | 95 | 90 | 92 | 93 | 91 | 89 | [eval](https://sharegpt.com/c/cd9HF4V) |
| 83 | 95 | 92 | 90 | 85 | 88 | 91 | [eval](https://sharegpt.com/c/LHkjvQJ) |
| 84 | 100 | 95 | 98 | 97 | 96 | 99 | [eval](https://sharegpt.com/c/o5PdoyZ) |
| 85 | 100 | 100 | 100 | 90 | 100 | 95 | [eval](https://sharegpt.com/c/rh8pZVg) |
| 86 | 100 | 95 | 98 | 97 | 94 | 99 | [eval](https://sharegpt.com/c/T5DYL83) |
| 87 | 95 | 90 | 92 | 93 | 94 | 91 | [eval](https://sharegpt.com/c/G5Osg3X) |
| 88 | 100 | 95 | 98 | 90 | 96 | 95 | [eval](https://sharegpt.com/c/9ZqI03V) |
| 89 | 95 | 96 | 92 | 90 | 89 | 93 | [eval](https://sharegpt.com/c/4tFfwZU) |
| 90 | 100 | 95 | 93 | 90 | 92 | 88 | [eval](https://sharegpt.com/c/mG1JqPH) |
| 91 | 100 | 100 | 98 | 97 | 99 | 100 | [eval](https://sharegpt.com/c/VDdtgCu) |
| 92 | 95 | 90 | 92 | 85 | 93 | 94 | [eval](https://sharegpt.com/c/uKtGkvg) |
| 93 | 95 | 93 | 90 | 92 | 96 | 91 | [eval](https://sharegpt.com/c/9B92N6P) |
| 94 | 95 | 96 | 92 | 90 | 93 | 91 | [eval](https://sharegpt.com/c/GeIFfOu) |
| 95 | 95 | 90 | 92 | 93 | 91 | 89 | [eval](https://sharegpt.com/c/gn3E9nN) |
| 96 | 100 | 98 | 95 | 97 | 96 | 99 | [eval](https://sharegpt.com/c/Erxa46H) |
| 97 | 90 | 95 | 85 | 88 | 92 | 87 | [eval](https://sharegpt.com/c/oRHVOvK) |
| 98 | 95 | 93 | 90 | 92 | 89 | 88 | [eval](https://sharegpt.com/c/ghtKLUX) |
| 99 | 100 | 95 | 97 | 90 | 96 | 94 | [eval](https://sharegpt.com/c/ZL4KjqP) |
| 100 | 95 | 93 | 90 | 92 | 94 | 91 | [eval](https://sharegpt.com/c/YOnqIQa) |
| 101 | 95 | 92 | 90 | 93 | 94 | 88 | [eval](https://sharegpt.com/c/3BKwKho) |
| 102 | 95 | 92 | 60 | 97 | 90 | 96 | [eval](https://sharegpt.com/c/U1i31bn) |
| 103 | 95 | 90 | 92 | 93 | 91 | 89 | [eval](https://sharegpt.com/c/etfRoAE) |
| 104 | 95 | 90 | 97 | 92 | 91 | 93 | [eval](https://sharegpt.com/c/B0OpVxR) |
| 105 | 90 | 95 | 93 | 85 | 92 | 91 | [eval](https://sharegpt.com/c/MBgGJ5A) |
| 106 | 95 | 90 | 40 | 92 | 93 | 85 | [eval](https://sharegpt.com/c/eQKTYO7) |
| 107 | 100 | 100 | 95 | 90 | 95 | 90 | [eval](https://sharegpt.com/c/szKWCBt) |
| 108 | 90 | 95 | 96 | 98 | 93 | 92 | [eval](https://sharegpt.com/c/8ZhUcAv) |
| 109 | 90 | 95 | 92 | 89 | 93 | 94 | [eval](https://sharegpt.com/c/VQWdy99) |
| 110 | 100 | 95 | 100 | 98 | 96 | 99 | [eval](https://sharegpt.com/c/g1DHUSM) |
| 111 | 100 | 100 | 95 | 90 | 100 | 90 | [eval](https://sharegpt.com/c/uYgfJC3) |
| 112 | 90 | 85 | 88 | 92 | 87 | 91 | [eval](https://sharegpt.com/c/crk8BH3) |
| 113 | 95 | 97 | 90 | 92 | 93 | 94 | [eval](https://sharegpt.com/c/95F9afQ) |
| 114 | 90 | 95 | 85 | 88 | 92 | 89 | [eval](https://sharegpt.com/c/otioHUo) |
| 115 | 95 | 93 | 90 | 92 | 94 | 91 | [eval](https://sharegpt.com/c/KSiL9F6) |
| 116 | 90 | 95 | 85 | 80 | 88 | 82 | [eval](https://sharegpt.com/c/GmGq3b3) |
| 117 | 95 | 90 | 60 | 85 | 93 | 70 | [eval](https://sharegpt.com/c/VOhklyz) |
| 118 | 95 | 92 | 94 | 93 | 96 | 90 | [eval](https://sharegpt.com/c/wqy8m6k) |
| 119 | 95 | 90 | 85 | 93 | 87 | 92 | [eval](https://sharegpt.com/c/iWKrIuS) |
| 120 | 95 | 96 | 93 | 90 | 97 | 92 | [eval](https://sharegpt.com/c/o1h3w8N) |
| 121 | 100 | 0 | 0 | 100 | 0 | 0 | [eval](https://sharegpt.com/c/3UH9eed) |
| 122 | 60 | 100 | 0 | 80 | 0 | 0 | [eval](https://sharegpt.com/c/44g0FAh) |
| 123 | 0 | 100 | 60 | 0 | 0 | 90 | [eval](https://sharegpt.com/c/PaQlcrU) |
| 124 | 100 | 100 | 0 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/51icV4o) |
| 125 | 100 | 100 | 100 | 100 | 95 | 100 | [eval](https://sharegpt.com/c/1VnbGAR) |
| 126 | 100 | 100 | 100 | 50 | 90 | 100 | [eval](https://sharegpt.com/c/EYGBrgw) |
| 127 | 100 | 100 | 100 | 100 | 95 | 90 | [eval](https://sharegpt.com/c/EGRduOt) |
| 128 | 100 | 100 | 100 | 95 | 0 | 100 | [eval](https://sharegpt.com/c/O3JJfnK) |
| 129 | 50 | 95 | 20 | 10 | 30 | 85 | [eval](https://sharegpt.com/c/2roVtAu) |
| 130 | 100 | 100 | 60 | 20 | 30 | 40 | [eval](https://sharegpt.com/c/sphFpfx) |
| 131 | 100 | 0 | 0 | 0 | 0 | 100 | [eval](https://sharegpt.com/c/OeWGKBo) |
| 132 | 0 | 100 | 60 | 0 | 0 | 80 | [eval](https://sharegpt.com/c/TOUsuFA) |
| 133 | 50 | 100 | 20 | 90 | 0 | 10 | [eval](https://sharegpt.com/c/Y3P6DCu) |
| 134 | 100 | 100 | 100 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/hkbdeiM) |
| 135 | 100 | 100 | 100 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/eubbaVC) |
| 136 | 40 | 100 | 95 | 0 | 100 | 40 | [eval](https://sharegpt.com/c/QWiF49v) |
| 137 | 100 | 100 | 100 | 100 | 80 | 100 | [eval](https://sharegpt.com/c/dKTapBu) |
| 138 | 100 | 100 | 100 | 0 | 90 | 40 | [eval](https://sharegpt.com/c/P8NGwFZ) |
| 139 | 0 | 100 | 100 | 50 | 70 | 20 | [eval](https://sharegpt.com/c/v96BtBL) |
| 140 | 100 | 100 | 50 | 90 | 0 | 95 | [eval](https://sharegpt.com/c/YRlzj1t) |
| 141 | 100 | 95 | 90 | 85 | 98 | 80 | [eval](https://sharegpt.com/c/76VX3eB) |
| 142 | 95 | 98 | 90 | 92 | 96 | 89 | [eval](https://sharegpt.com/c/JK1uNef) |
| 143 | 90 | 95 | 75 | 85 | 80 | 82 | [eval](https://sharegpt.com/c/ku6CKmx) |
| 144 | 95 | 98 | 50 | 92 | 96 | 94 | [eval](https://sharegpt.com/c/0iAFuKW) |
| 145 | 95 | 90 | 0 | 93 | 92 | 94 | [eval](https://sharegpt.com/c/6uGnKio) |
| 146 | 95 | 90 | 85 | 92 | 80 | 88 | [eval](https://sharegpt.com/c/lfpRBw8) |
| 147 | 95 | 93 | 75 | 85 | 90 | 92 | [eval](https://sharegpt.com/c/mKu70jb) |
| 148 | 90 | 95 | 88 | 85 | 92 | 89 | [eval](https://sharegpt.com/c/GkYzJHO) |
| 149 | 100 | 100 | 100 | 95 | 97 | 98 | [eval](https://sharegpt.com/c/mly2k0z) |
| 150 | 85 | 40 | 30 | 95 | 90 | 88 | [eval](https://sharegpt.com/c/5td2ob0) |
| 151 | 90 | 95 | 92 | 85 | 88 | 93 | [eval](https://sharegpt.com/c/0ISpWfy) |
| 152 | 95 | 96 | 92 | 90 | 89 | 93 | [eval](https://sharegpt.com/c/kdUDUn7) |
| 153 | 90 | 95 | 85 | 80 | 92 | 88 | [eval](https://sharegpt.com/c/fjMNYr2) |
| 154 | 95 | 98 | 65 | 90 | 85 | 93 | [eval](https://sharegpt.com/c/6xBIf2Q) |
| 155 | 95 | 92 | 96 | 97 | 90 | 89 | [eval](https://sharegpt.com/c/B9GY8Ln) |
| 156 | 95 | 90 | 92 | 91 | 89 | 93 | [eval](https://sharegpt.com/c/vn1FPU4) |
| 157 | 95 | 90 | 80 | 75 | 95 | 90 | [eval](https://sharegpt.com/c/YurEMYg) |
| 158 | 92 | 40 | 30 | 95 | 90 | 93 | [eval](https://sharegpt.com/c/D19Qeui) |
| 159 | 90 | 92 | 85 | 88 | 89 | 87 | [eval](https://sharegpt.com/c/5QRFfrt) |
| 160 | 95 | 80 | 90 | 92 | 91 | 88 | [eval](https://sharegpt.com/c/pYWPRi4) |
| 161 | 95 | 93 | 92 | 90 | 91 | 94 | [eval](https://sharegpt.com/c/wPRTntL) |
| 162 | 100 | 98 | 95 | 90 | 92 | 96 | [eval](https://sharegpt.com/c/F6PLYKE) |
| 163 | 95 | 92 | 80 | 85 | 90 | 93 | [eval](https://sharegpt.com/c/WeJnMGv) |
| 164 | 95 | 98 | 90 | 88 | 97 | 96 | [eval](https://sharegpt.com/c/zNKL49e) |
| 165 | 90 | 95 | 85 | 88 | 86 | 92 | [eval](https://sharegpt.com/c/kIKmA1b) |
| 166 | 100 | 100 | 100 | 100 | 100 | 100 | [eval](https://sharegpt.com/c/1btWd4O) |
| 167 | 90 | 95 | 85 | 96 | 92 | 88 | [eval](https://sharegpt.com/c/s9sf1Lp) |
| 168 | 100 | 98 | 95 | 99 | 97 | 96 | [eval](https://sharegpt.com/c/RWzv8py) |
| 169 | 95 | 92 | 70 | 90 | 93 | 89 | [eval](https://sharegpt.com/c/bYF7FqA) |
| 170 | 95 | 90 | 88 | 92 | 94 | 93 | [eval](https://sharegpt.com/c/SuUqjMj) |
| 171 | 95 | 90 | 93 | 92 | 85 | 94 | [eval](https://sharegpt.com/c/r0aRdYY) |
| 172 | 95 | 93 | 90 | 87 | 92 | 91 | [eval](https://sharegpt.com/c/VuMfkkd) |
| 173 | 95 | 93 | 90 | 96 | 92 | 91 | [eval](https://sharegpt.com/c/rhm6fa4) |
| 174 | 95 | 97 | 85 | 96 | 98 | 90 | [eval](https://sharegpt.com/c/DwXnyqG) |
| 175 | 95 | 92 | 90 | 85 | 93 | 94 | [eval](https://sharegpt.com/c/0ScdkGS) |
| 176 | 95 | 96 | 92 | 90 | 97 | 93 | [eval](https://sharegpt.com/c/6yIoCDU) |
| 177 | 95 | 93 | 96 | 94 | 90 | 92 | [eval](https://sharegpt.com/c/VubEvp9) |
| 178 | 95 | 94 | 93 | 92 | 90 | 89 | [eval](https://sharegpt.com/c/RHzmZWG) |
| 179 | 90 | 85 | 95 | 80 | 87 | 75 | [eval](https://sharegpt.com/c/IMiP9Zm) |
| 180 | 95 | 94 | 92 | 93 | 90 | 96 | [eval](https://sharegpt.com/c/bft4PIL) |
| 181 | 95 | 100 | 90 | 95 | 95 | 95 | [eval](https://sharegpt.com/c/iHXB34b) |
| 182 | 100 | 95 | 85 | 100 | 0 | 90 | [eval](https://sharegpt.com/c/vCGn9R7) |
| 183 | 100 | 95 | 90 | 95 | 100 | 95 | [eval](https://sharegpt.com/c/be8crZL) |
| 184 | 95 | 90 | 60 | 95 | 85 | 80 | [eval](https://sharegpt.com/c/33elmDz) |
| 185 | 100 | 95 | 90 | 98 | 97 | 99 | [eval](https://sharegpt.com/c/RWD3Zx7) |
| 186 | 95 | 90 | 85 | 95 | 80 | 92 | [eval](https://sharegpt.com/c/GiwBvM7) |
| 187 | 100 | 95 | 100 | 98 | 100 | 90 | [eval](https://sharegpt.com/c/hX2pYxk) |
| 188 | 100 | 95 | 80 | 85 | 90 | 85 | [eval](https://sharegpt.com/c/MfxdGd7) |
| 189 | 100 | 90 | 95 | 85 | 95 | 100 | [eval](https://sharegpt.com/c/28hQjmS) |
| 190 | 95 | 90 | 85 | 80 | 88 | 92 | [eval](https://sharegpt.com/c/fzy5EPe) |
| 191 | 100 | 100 | 0 | 0 | 100 | 0 | [eval](https://sharegpt.com/c/vwxPjbR) |
| 192 | 100 | 100 | 100 | 50 | 100 | 75 | [eval](https://sharegpt.com/c/FAYfFWy) |
| 193 | 100 | 100 | 0 | 0 | 100 | 0 | [eval](https://sharegpt.com/c/SoudGsQ) |
| 194 | 0 | 100 | 0 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/mkwEgVn) |
| 195 | 100 | 100 | 50 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/q8MQEsz) |
| 196 | 100 | 100 | 100 | 100 | 100 | 95 | [eval](https://sharegpt.com/c/tzHpsKh) |
| 197 | 100 | 100 | 50 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/3ugYBtJ) |
| 198 | 100 | 100 | 0 | 0 | 100 | 0 | [eval](https://sharegpt.com/c/I6KfOJT) |
| 199 | 90 | 85 | 80 | 95 | 70 | 75 | [eval](https://sharegpt.com/c/enaV1CK) |
| 200 | 100 | 100 | 0 | 0 | 0 | 0 | [eval](https://sharegpt.com/c/JBk7oSh) |
</details>
### Training data
I used a jailbreak prompt to generate the synthetic instructions, which resulted in some training data that would likely be censored by other models, such as how-to prompts about synthesizing drugs, making homemade flamethrowers, etc. Mind you, this is all generated by ChatGPT, not me. My goal was to simply test some of the capabilities of ChatGPT when unfiltered (as much as possible), and not to intentionally produce any harmful/dangerous/etc. content.
The jailbreak prompt I used is the default prompt in the python code when using the `--uncensored` flag: https://github.com/jondurbin/airoboros/blob/main/airoboros/self_instruct.py#L39
I also did a few passes of manually cleanup to remove some bad prompts, but mostly I left the data as-is. Initially, the model was fairly bad at math/extrapolation, closed question-answering (heavy hallucination), and coding, so I did one more fine tuning pass with additional synthetic instructions aimed at those types of problems.
Both the initial instructions and final-pass fine-tuning instructions will be published soon.
### Fine-tuning method
I used the excellent [FastChat](https://github.com/lm-sys/FastChat) module, running with:
```
source /workspace/venv/bin/activate
export NCCL_P2P_DISABLE=1
export NCCL_P2P_LEVEL=LOC
torchrun --nproc_per_node=8 --master_port=20001 /workspace/FastChat/fastchat/train/train_mem.py \
--model_name_or_path /workspace/llama-13b \
--data_path /workspace/as_conversations.json \
--bf16 True \
--output_dir /workspace/airoboros-uncensored-13b \
--num_train_epochs 3 \
--per_device_train_batch_size 20 \
--per_device_eval_batch_size 20 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "steps" \
--eval_steps 500 \
--save_strategy "steps" \
--save_steps 500 \
--save_total_limit 10 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.04 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--fsdp "full_shard auto_wrap offload" \
--fsdp_transformer_layer_cls_to_wrap 'LlamaDecoderLayer' \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \
--lazy_preprocess True
```
This ran on 8x nvidia 80gb a100's for about 40 hours.
### License
The model is licensed under the LLaMA model, and the dataset is licensed under the terms of OpenAI because it uses ChatGPT. Everything else is free.