ApolloRaines/Sharona_Q27B-R_CodeSecurity_v2
Full fine-tune vs Qwen/Qwen3.5-27B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 192/192, Attention 448/448, Norms 209/209
2 derivatives checked
- mradermacher/Sharona_Q27B-R_CodeSecurity_v2-i1-GGUF: Quantization
- mradermacher/Sharona_Q27B-R_CodeSecurity_v2-GGUF: Quantization