ggml-org/Laguna-XS-2.1-GGUF
Same weights, converted vs poolside/Laguna-XS-2.1. Same weights stored in another dtype (BF16 → BF16/F32), plus 156 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/159, Attention 0/200
Same weights, converted vs poolside/Laguna-XS-2.1. Same weights stored in another dtype (BF16 → BF16/F32), plus 156 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/159, Attention 0/200