mradermacher/NuExtract-2.0-2B-GGUF
Same weights, converted (fewer layers) vs numind/NuExtract-2.0-2B. mradermacher/NuExtract-2.0-2B-GGUF matches part of numind/NuExtract-2.0-2B (338 of its 729 tensors; the rest of numind/NuExtract-2.0-2B has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196