A continuation of OpenHermes 2 model, trained on additional code datasets. Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
모달리티
컨텍스트
4K
출시일
2023년 11월 20일
지식 기준일
2023년 9월