Language Modeling on OpenWebText 10k
11.5023PerplexityFP16
Evaluation Results
| Method | Links | |
|---|---|---|
| FP16Model=Llama-3.2-1B2025.11 | 11.5023 | |
| IntAttentionModel=Llama-3.2-1B2025.11 | 12.3178 | |
| Quant-OnlyModel=Llama-3.2-1B2025.11 | 12.7931 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| FP16Model=Llama-3.2-1B2025.11 | 11.5023 | |
| IntAttentionModel=Llama-3.2-1B2025.11 | 12.3178 | |
| Quant-OnlyModel=Llama-3.2-1B2025.11 | 12.7931 |