bunnycore/Llama-3.2-3B-TitanFusion
Full fine-tune vs Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 112/112
2 derivatives checked
- mradermacher/Llama-3.2-3B-TitanFusion-i1-GGUF: Quantization
- mradermacher/Llama-3.2-3B-TitanFusion-GGUF: Same weights, converted