ThinkBit preserves reasoning in scalar two-bit language models
On Qwen3-1.7B, a 0.52 GB recalibrated checkpoint scores 46.7 on MATH-500 versus 30.0 for EfficientQAT.
1 stories, newest first · one card per story
On Qwen3-1.7B, a 0.52 GB recalibrated checkpoint scores 46.7 on MATH-500 versus 30.0 for EfficientQAT.
Today 968 readers · 1.4K views · 1K reads · all time 159K views