Our new X account is live! Follow @wizwand_team for updates

Question Answering on TruthfulQA zero-shot

62.03TruthfulQA Score

Solar-0-70B

Updated 4d ago

Evaluation Results

Method	Links
Solar-0-70B 2024.02		62.03	73.77
BitDelta 2024.02		62.03	73.57
BitDelta-Initial 2024.02		59.08	73.14
BitDelta 2024.02		58.39	66.2
Mistral-7B v0.1 Instruct 2024.02		55.93	60.36
BitDelta 2024.02		55.23	61.1
Zephyr-7B-β 2024.02		55.12	65.22
BitDelta 2024.02		54.91	66.97
BitDelta-Initial 2024.02		54.53	66.12
Dolphin 2.2.1 2024.02		54.02	67.31
Llama 2-70B Chat 2024.02		52.77	68.82
BitDelta 2024.02		51.37	69.14
BitDelta-Initial 2024.02		51.27	63.83
BitDelta-Initial 2024.02		48.14	67.58
Llama 2-70B 2024.02		44.82	71.81
Mistral-7B v0.1 2024.02		42.6	65.98
BitDelta-Initial 2024.02		41.63	66.01
MPT-7B-Chat 2024.02		40.22	56.5
BitDelta 2024.02		39.87	56.52
BitDelta-Initial 2024.02		38.96	57.11
MPT-7B 2024.02		33.37	37.95