Chat on OMGEval (test)
2,900English ScoreGuanaco-13b
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Guanaco-13bBackbone=Llama-2-13b, SFT Data=Guanaco Dataset2024.02 | 2,900 | 860 | 1,690 | 1,540 | 1,730 | 1,750 | |
| UltraLink-LMBackbone=Llama-2-13b, SFT Data=UltraLink2024.02 | 2,880 | 2,190 | 2,350 | 3,760 | 2,900 | 2,820 | |
| Chimera-inst-chat-13bBackbone=Llama-13b, SFT Data=Phoenix SFT data2024.02 | 1,550 | 970 | 1,180 | 1,370 | 1,380 | 1,290 | |
| Okapi-7bBackbone=Llama-2-7b, SFT Data=Okapi Dataset2024.02 | 880 | 620 | 500 | 1,210 | 870 | 820 | |
| PolyLM-Chat-13bBackbone=PolyLM-13b, SFT Data=Closed-source2024.02 | 770 | 1,400 | 610 | 550 | 480 | 760 | |
| Phoenix-inst-chat-7bBackbone=Bloomz-7b1, SFT Data=Phoenix SFT data2024.02 | 690 | 1,330 | 740 | 290 | 810 | 770 | |
| Guanaco-7bBackbone=Llama-2-7b, SFT Data=Guanaco Dataset2024.02 | 460 | 380 | 40 | 180 | 120 | 240 | |
| PolyLM-Multialpaca-13bBackbone=PolyLM-13b, SFT Data=Multialpaca2024.02 | 340 | 500 | 210 | 510 | 220 | 360 | |
| Bloomz-7b1-mtBackbone=Bloomz-7b1, SFT Data=xP3mt2024.02 | 0 | 90 | 10 | 50 | 30 | 40 |