Delta-Vector/Plesio-32B
LoRA-style vs Delta-Vector/Rei-V1-32B-Base. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_up_proj, k_proj, o_proj, q_proj, v_proj changed, in 61 of 61 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/245, MLP 122/122, Attention 244/244
3 derivatives checked
- mradermacher/Plesio-32B-i1-GGUF: Quantization
- mradermacher/Plesio-32B-GGUF: Quantization
- DevQuasar/Delta-Vector.Plesio-32B-GGUF: Same weights, converted