Instruction Following on UnNI
0.614ScoreOurs 12
Evaluation results
| Method | Links | |
|---|---|---|
| Ours 12Distillation Method=Random Sampling KD, Number of Unique Tokens=12, Teacher Model Size=8B, Student Model Size=3B, Evaluation Judge=Llama 3.1 405B Instruct2025.03 | 0.614 | |
| FullKDDistillation Method=Full KD, Teacher Model Size=8B, Student Model Size=3B, Evaluation Judge=Llama 3.1 405B Instruct2025.03 | 0.61 | |
| CEDistillation Method=None (Cross-Entropy), Teacher Model Size=8B, Student Model Size=3B, Evaluation Judge=Llama 3.1 405B Instruct2025.03 | 0.604 | |
| Top-K 50Distillation Method=Top-K KD, Number of Unique Tokens=50, Teacher Model Size=8B, Student Model Size=3B, Evaluation Judge=Llama 3.1 405B Instruct2025.03 | 0.583 | |
| Top-K 12Distillation Method=Top-K KD, Number of Unique Tokens=12, Teacher Model Size=8B, Student Model Size=3B, Evaluation Judge=Llama 3.1 405B Instruct2025.03 | 0.58 |