Named Entity Recognition on n2c2 University of Washington (UW) 2022
87.6F1 ScoreFull FT
Evaluation results
| Method | Links | |
|---|---|---|
| Full FTBase model=gpt-oss 20B, Trainable Parameters=100.0%2026.04 | 87.6 | |
| MPTBase model=gpt-oss 20B, Trainable Parameters=<0.05%2026.04 | 87.1 | |
| Full FTBase model=Meditron3 8B, Trainable Parameters=100.0%2026.04 | 86.1 | |
| LoRABase model=gpt-oss 20B, Trainable Parameters=~2.50%2026.04 | 85.8 | |
| MPTBase model=Meditron3 8B, Trainable Parameters=<0.05%2026.04 | 85.7 | |
| LoRABase model=Meditron3 8B, Trainable Parameters=~2.50%2026.04 | 84.1 | |
| Full FTBase model=LLaMA 3.1 8B, Trainable Parameters=100.0%2026.04 | 83.2 | |
| MPTBase model=LLaMA 3.1 8B, Trainable Parameters=<0.05%2026.04 | 82.4 | |
| LoRABase model=LLaMA 3.1 8B, Trainable Parameters=~2.50%2026.04 | 81 | |
| PTBase model=gpt-oss 20B, Trainable Parameters=<0.05%2026.04 | 80.4 | |
| PTBase model=Meditron3 8B, Trainable Parameters=<0.05%2026.04 | 78.5 | |
| PTBase model=LLaMA 3.1 8B, Trainable Parameters=<0.05%2026.04 | 75.2 |