mradermacher/KoSOLAR-v0.2-gugutypus-10.7B-GGUF

Same weights, converted vs oneonlee/KoSOLAR-v0.2-gugutypus-10.7B. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse