Language Modeling on WikiText-2 context length 8192 (test)
6.5Perplexity
Llama3.1-8B-Instruct Baseline
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
| 6.5 | ||
2026.02 | 7.32 | |
2026.02 | 11.13 | |
2026.02 | 12.75 | |
2026.02 | 1,000,000 |
Llama3.1-8B-Instruct Baseline
| Method | Links | |
|---|---|---|
| 6.5 | ||
2026.02 | 7.32 | |
2026.02 | 11.13 | |
2026.02 | 12.75 | |
2026.02 | 1,000,000 |