[–] K0IN 17d ago ↗ Is the classification model available, would be cool to have this in the toolbox. [–] coolspot 17d ago ↗ Here is the harness - https://github.com/litemars/LLM-Fingerprinter .Classifier is an ensemble of Random Forest (45%) + SVM (45%) + MLP (10%).Code is very easy to run using your own OpenRouter key, here is a training gist - https://gist.github.com/CoolSpot/bcd4545daf763d9196dea3bb0b5... .
[–] coolspot 17d ago ↗ Here is the harness - https://github.com/litemars/LLM-Fingerprinter .Classifier is an ensemble of Random Forest (45%) + SVM (45%) + MLP (10%).Code is very easy to run using your own OpenRouter key, here is a training gist - https://gist.github.com/CoolSpot/bcd4545daf763d9196dea3bb0b5... .
[–] tgrowazay 17d ago ↗ > which makes GLM-5.2 slightly closer to Opus 4.5 than Opus 4.6 isSo, glm is more related to opus than opus to opus?
3 comments
[ 2.7 ms ] story [ 20.6 ms ] threadClassifier is an ensemble of Random Forest (45%) + SVM (45%) + MLP (10%).
Code is very easy to run using your own OpenRouter key, here is a training gist - https://gist.github.com/CoolSpot/bcd4545daf763d9196dea3bb0b5... .
So, glm is more related to opus than opus to opus?