lora
an archive of posts with this tag
| May 23, 2026 | A haiku VLM: SFT did the work, KTO collapsed at λ=1.0 |
|---|---|
| May 22, 2026 | A 7B math fine-tune on 8× H100: SFT +6.4, DPO +0.6 |
an archive of posts with this tag
| May 23, 2026 | A haiku VLM: SFT did the work, KTO collapsed at λ=1.0 |
|---|---|
| May 22, 2026 | A 7B math fine-tune on 8× H100: SFT +6.4, DPO +0.6 |