Tag
A practitioner shares surprising findings from fine-tuning a small open model to be genuinely better in practical use, not just on benchmarks.
A thread sharing field notes on fine-tuning, explaining how model architecture (e.g., heavily-quantized or mixture-of-experts) restricts which parts can be adjusted, urging practitioners to check model accessibility before planning work.
The author shares field notes showing that fine-tuning can improve a model's judgment by steering attention without adding new knowledge or weights, effectively changing its instincts rather than its IQ.