Situus/STARK-WEB-12B-v1.7-gguf
Same weights, converted vs Situus/STARK-WEB-12B-v1.7. Same weights stored in another dtype (BF16 → F16/F32), plus 49 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184
Same weights, converted vs Situus/STARK-WEB-12B-v1.7. Same weights stored in another dtype (BF16 → F16/F32), plus 49 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/184