surfiniaburger/dipg-safety-agent-v2-float16
LoRA-style vs unsloth/gpt-oss-20b-BF16. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/144, Attention 96/216, lm_head 0/1
1 derivatives checked
- mradermacher/dipg-safety-agent-v2-float16-GGUF: Quantization