mradermacher/Llama-3.2-3B-DPO-GGUF
Same weights, converted vs AIR-hl/Llama-3.2-3B-DPO. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112, lm_head 0/1
Same weights, converted vs AIR-hl/Llama-3.2-3B-DPO. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112, lm_head 0/1