Language Modeling on The Pile non-copyrighted without Wikipedia (test)
0.559BPBSIFT
Evaluation Results
| Method | Links | |
|---|---|---|
| SIFTEvaluation Protocol=Test-Time FT, Base Model=Llama-3.2, Parameters=3B2024.10 | 0.559 | |
| SIFTEvaluation Protocol=Test-Time FT, Base Model=Phi-3, Parameters=3.8B2024.10 | 0.599 | |
| Jurassic-1Parameters=178B2024.10 | 0.601 | |
| SIFTEvaluation Protocol=Test-Time FT, Base Model=Llama-3.2, Parameters=1B2024.10 | 0.607 | |
| GLMParameters=130B2024.10 | 0.622 | |
| Llama-3.2Parameters=3B2024.10 | 0.627 | |
| Phi-3Parameters=3.8B2024.10 | 0.678 | |
| Llama-3.2Parameters=1B2024.10 | 0.684 |