poolside-laguna-hackathon/Laguna-XS.2-GGUF

Same weights, converted vs poolside/Laguna-XS.2. Same weights stored in another dtype (BF16 → F16/F32), plus 196 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/159, Attention 0/160

On the Hub · Downloads on Model Pulse