empero-ai/openNemo-9B-Claude-Opus-4.6-distill
LoRA-style vs empero-ai/openNemo-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 29 of 56 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, other 0/189, Norms 0/84, MLP 50/50, Attention 16/16, lm_head 0/1
2 derivatives checked
- mradermacher/openNemo-9B-Claude-Opus-4.6-distill-i1-GGUF: Quantization
- mradermacher/openNemo-9B-Claude-Opus-4.6-distill-GGUF: Same weights, converted