mradermacher/kona2-small-3.8B-GGUF
Same weights, converted vs tbilisi-ai-lab/kona2-small-3.8B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64, lm_head 0/1
Same weights, converted vs tbilisi-ai-lab/kona2-small-3.8B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/64, Attention 0/64, lm_head 0/1