The model card said 0.5B. The checkpoint stores 494M. Both are right.

Automated excerpt

So: six checkpoints, two of them with tied embeddings, two of them mixture-of-experts, each one's stored tensor count recomputed from its own config.json and compared against what the API reports. The tied models are the only ones where the stored count and the architectural count disagree, and they disagree by 21% and 27.6%. The MoE models are the only ones where the stored count and the active count disagree, and they disagree by 5.3x and 3.6x.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.