expertai/LLaMAntino-3-SLIMER-IT-PARALLEL
LoRA-style vs swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 96/128, lm_head 0/1
1 derivatives checked
- mradermacher/LLaMAntino-3-SLIMER-IT-PARALLEL-GGUF: Same weights, converted