Language Modeling on LAMBADA (Normalized Accuracy)
37.26Normalized AccuracyMHF (H4B16K)
Evaluation Results
| Method | Links | |
|---|---|---|
| MHF (H4B16K)Model Scale=3B, Embedding Parameters (Emb)=138M, Decoder Parameters (Dec)=2.8B, Evaluation Protocol=Zero-shot2026.06 | 37.26 | |
| MHF (H3B10K)Model Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.06 | 35.78 | |
| MHF (H4B16K)Model Scale=1B, Embedding Parameters (Emb)=138M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.06 | 35.34 | |
| Standard+2LModel Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=1.0B, Evaluation Protocol=Zero-shot2026.06 | 30.66 | |
| StandardModel Scale=1B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=0.9B, Evaluation Protocol=Zero-shot2026.06 | 30.41 | |
| StandardModel Scale=3B, Embedding Parameters (Emb)=65M, Decoder Parameters (Dec)=2.8B, Evaluation Protocol=Zero-shot2026.06 | 28.64 | |
| Standard+4LModel Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=116M, Evaluation Protocol=Zero-shot2026.06 | 19.64 | |
| MHF (H4B16K)Model Scale=100M, Embedding Parameters (Emb)=52M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.06 | 18.79 | |
| MHF (H3B10K)Model Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.06 | 16.4 | |
| StandardModel Scale=100M, Embedding Parameters (Emb)=25M, Decoder Parameters (Dec)=87M, Evaluation Protocol=Zero-shot2026.06 | 15.33 |