TheBloke/notus-7B-v1-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| HellaSwag | knowledge | 84.36 | low | | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** | | |
| WinoGrande | knowledge | 77.74 | low | | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** | | |
| MMLU | knowledge | 61.07 | low | | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** | | |
| TruthfulQA | safety | 57.45 | low | | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** | | |
| GSM8K | math | 12.74 | low | | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** | | |
| DROP | reasoning | 9.66 | low | | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15 | 62.03 | 84.36 | 61.07 | **57.45** | 77.74 | 12.74 | **9.66** | |
none scraped.