mradermacher/Linnaeus-0.1.0-2B-merged-GGUF

Same weights, converted vs pi-dal/Linnaeus-0.1.0-2B-merged. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 33 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24

On the Hub · Downloads on Model Pulse