Question Answering On Hellaswag
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Shakti-LLM (2.5B) | 52.4 | SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments | - |
0 of 1 row(s) selected.