Language Modeling on wikitext (Perplexity and Delta)
8.0668Perplexity (word)Source
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SourceModel=Llama-3.1-8B, Context window=2048-token, Precision=fp16, Hardware=NVIDIA A100, Evaluation framework=lm-evaluation-harness2024.07 | 8.0668 | — | |
| FlashNormModel=Llama-3.1-8B, Context window=2048-token, Precision=fp16, Hardware=NVIDIA A100, Evaluation framework=lm-evaluation-harness2024.07 | 8.0672 | 0.0004 | |
| SourceModel=Llama-3.2-1B, Context window=2048-token, Precision=fp16, Hardware=NVIDIA A100, Evaluation framework=lm-evaluation-harness2024.07 | 12.8837 | — | |
| FlashNormModel=Llama-3.2-1B, Context window=2048-token, Precision=fp16, Hardware=NVIDIA A100, Evaluation framework=lm-evaluation-harness2024.07 | 12.8842 | 0.0005 | |
| SourceModel=SmolLM2-135M, Context window=2048-token, Precision=fp16, Hardware=NVIDIA A100, Evaluation framework=lm-evaluation-harness2024.07 | 23.1262 | — | |
| FlashNormModel=SmolLM2-135M, Context window=2048-token, Precision=fp16, Hardware=NVIDIA A100, Evaluation framework=lm-evaluation-harness2024.07 | 23.1279 | 0.0017 |