commonsense inference on HellaSwag (test)
84.89AccuracyFP16
Evaluation Results
| Method | Links | |
|---|---|---|
| FP16Model=LLAMA3-70B, Evaluation Protocol=Zero-shot, Bit-width=Full-precision2024.03 | 84.89 | |
| FP16Model=LLAMA3-8B, Evaluation Protocol=Zero-shot, Bit-width=Full-precision2024.03 | 79.06 | |
| QuaRotModel=LLAMA3-70B, Evaluation Protocol=Zero-shot, Bit-width=4-bit2024.03 | 77.33 | |
| QuaRotModel=LLAMA3-8B, Evaluation Protocol=Zero-shot, Bit-width=4-bit2024.03 | 72.94 |