Mungert/gpt-oss-safeguard-20b-GGUF
Full fine-tune vs openai/gpt-oss-20b. Mungert/gpt-oss-safeguard-20b-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 48/48, Attention 168/192, lm_head 1/1, Embeddings 1/1