VTXAI/Helvete-nano
LoRA-style vs syntropy-ai/Soren-1-Small. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/79, Embeddings 0/1, Attention 24/168, MLP 72/72
1 derivatives checked
- Xetro/Helvete-nano-Q4_K_M-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.