Language Modeling on OLMo (val)
2.24Base CEOLMo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OLMo2025.12 | 2.24 | — | — | |
| Sparse Attention Post-TrainingTarget Cross-Entropy (τ)=2.29, Base Model=OLMo2025.12 | — | 2.287 | 0.44 |
Loading the SOTA2 catalog…
| Method | Links | |||
|---|---|---|---|---|
| OLMo2025.12 | 2.24 | — | — | |
| Sparse Attention Post-TrainingTarget Cross-Entropy (τ)=2.29, Base Model=OLMo2025.12 | — | 2.287 | 0.44 |