Mungert/gpt-oss-20b-Derestricted-GGUF
LoRA-style vs openai/gpt-oss-20b. Mungert/gpt-oss-20b-Derestricted-GGUF is a GGUF (Q8_0) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, router changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/49, MLP 10/48, Attention 58/192, lm_head 0/1, Embeddings 0/1