mradermacher/XCurOS-1.2-8B-VLBF16-Instruct-GGUF
Same weights, converted (fewer layers) vs XCurOS/XCurOS1.2-8B-VLBF16-Instruct. mradermacher/XCurOS-1.2-8B-VLBF16-Instruct-GGUF matches part of XCurOS/XCurOS1.2-8B-VLBF16-Instruct (399 of its 750 tensors; the rest of XCurOS/XCurOS1.2-8B-VLBF16-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1