TucanoBR/Tucano-1b1-Instruct
LoRA-style vs TucanoBR/Tucano-1b1. 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 22 of 22 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/45, MLP 66/66, Attention 88/88
1 derivatives checked
- tensorblock/Tucano-1b1-Instruct-GGUF: Quantization