List your company

Question Answering on TruthfulQA zero-shot

62.03TruthfulQA ScoreSolar-0-70B
32.223639.961847.755.4382Feb 15, 2024May 31, 2024Sep 14, 2024Dec 30, 2024Apr 15, 2025Jul 30, 2025Nov 14, 2025

Evaluation results

MethodLinks
Solar-0-70BModel=Solar-0-70B, Mode=Baseline2024.0262.0373.77
BitDeltaModel=Solar-0-70B2024.0262.0373.57
BitDelta-InitialModel=Solar-0-70B2024.0259.0873.14
BitDeltaModel=Zephyr-7B-β2024.0258.3966.2
Mistral-7B v0.1 InstructModel=Mistral-7B v0.1 Instruct, Mode=Baseline2024.0255.9360.36
BitDeltaModel=Mistral-7B v0.1 Instruct2024.0255.2361.1
Zephyr-7B-βModel=Zephyr-7B-β, Mode=Baseline2024.0255.1265.22
Instella-3B-SFT (UM-190k)DPO Training Dataset=UM-190k, Evaluation Protocol=0-shot2025.1154.93—
BitDeltaModel=Dolphin 2.2.12024.0254.9166.97
Instella-3B-SFT (UM-187k)DPO Training Dataset=UM-187k, Evaluation Protocol=0-shot2025.1154.91—
BitDelta-InitialModel=Zephyr-7B-β2024.0254.5366.12
Instella-3B-SFT (UM-170k)DPO Training Dataset=UM-170k, Evaluation Protocol=0-shot2025.1154.45—
Instella-3B-SFT (TuluDPO)DPO Training Dataset=TuluDPO, Evaluation Protocol=0-shot2025.1154.21—
Dolphin 2.2.1Model=Dolphin 2.2.1, Mode=Baseline2024.0254.0267.31
Instella-3B-SFT (ORPO)DPO Training Dataset=ORPO, Evaluation Protocol=0-shot2025.1153.35—
Llama 2-70B ChatModel=Llama 2-70B Chat, Mode=Baseline2024.0252.7768.82
Instella-3B-SFT (HelpSteer)DPO Training Dataset=HelpSteer, Evaluation Protocol=0-shot2025.1152.7—
Instella-3B-SFT (UltraFB)DPO Training Dataset=UltraFB, Evaluation Protocol=0-shot2025.1152.67—
Instella-3B-SFT (SFT)DPO Training Dataset=None (SFT Baseline), Evaluation Protocol=0-shot2025.1152.48—
Instella-3B-SFT (CodePref)DPO Training Dataset=CodePref, Evaluation Protocol=0-shot2025.1152.19—
BitDeltaModel=Llama 2-70B Chat2024.0251.3769.14
BitDelta-InitialModel=Mistral-7B v0.1 Instruct2024.0251.2763.83
BitDelta-InitialModel=Dolphin 2.2.12024.0248.1467.58
Llama 2-70BModel=Llama 2-70B2024.0244.8271.81
Mistral-7B v0.1Model=Mistral-7B v0.12024.0242.665.98
BitDelta-InitialModel=Llama 2-70B Chat2024.0241.6366.01
MPT-7B-ChatModel=MPT-7B-Chat, Mode=Baseline2024.0240.2256.5
BitDeltaModel=MPT-7B-Chat2024.0239.8756.52
BitDelta-InitialModel=MPT-7B-Chat2024.0238.9657.11
MPT-7BModel=MPT-7B2024.0233.3737.95