blascotobasco/Nemotron-Cascade-2-96E-A3B
LoRA-style vs nvidia/Nemotron-Cascade-2-30B-A3B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, up_proj changed, in 23 of 52 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, other 0/161, Norms 0/76, MLP 1960/2032, Attention 0/24, lm_head 0/1
2 derivatives checked
- mradermacher/Nemotron-Cascade-2-96E-A3B-i1-GGUF: Quantization
- mradermacher/Nemotron-Cascade-2-96E-A3B-GGUF: Quantization