bartowski/stepfun-ai_GELab-Zero-4B-preview-GGUF
Same weights, converted (fewer layers) vs stepfun-ai/GELab-Zero-4B-preview. bartowski/stepfun-ai_GELab-Zero-4B-preview-GGUF matches part of stepfun-ai/GELab-Zero-4B-preview (398 of its 713 tensors; the rest of stepfun-ai/GELab-Zero-4B-preview has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144