mradermacher/SmolVLM-256M-Detection-GGUF
Same weights, converted (fewer layers) vs shreydan/SmolVLM-256M-Detection. mradermacher/SmolVLM-256M-Detection-GGUF matches part of shreydan/SmolVLM-256M-Detection (273 of its 471 tensors; the rest of shreydan/SmolVLM-256M-Detection has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/61, MLP 0/90, Attention 0/120