The model card said 0.5B. The checkpoint stores 494M. Both are right.
Qwen2.5-0.5B's config declares its vocabulary-by-hidden matrix twice: once as the embedding table, once as the output head. Its checkpoint stores that matrix once. Both statements are true, and the distance between them is 136,134,656 parameters, which is 27.6% of everything in the repo. I went and…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-06 07:46 · DEV Community — Machine Learning
The model card said 0.5B. The checkpoint stores 494M. Both are right.