nickprock/zagreus-0.4B-CulturaViva-ITA-Chat
LoRA-style vs mii-llm/zagreus-0.4B-ita. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/65, MLP 96/96, Attention 128/128
1 derivatives checked
- mradermacher/zagreus-0.4B-CulturaViva-ITA-Chat-GGUF: Same weights, converted