Llama3-8B
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Watermark Detection | Llama3-8B generated text max 30 tokens | Detection Time (s)0.008 | 6 | |
| In-Context Learning | Llama3-8B Scenario 3: More layers (L={0,4,8,...}) | Accuracy80.43 | 3 | |
| In-Context Learning | Llama3-8B Scenario 1: Diff. Pos. (P={4}) | Accuracy74.1 | 3 |
Showing 3 of 3 rows