mradermacher/Pretrained-SCP-1B-QLoRA-GGUF
Same weights, converted vs AiAF/Pretrained-SCP-1B-QLoRA. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64
Same weights, converted vs AiAF/Pretrained-SCP-1B-QLoRA. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64