bunnycore/Llama-3.2-3b-RP-Toxic-Fuse

Full fine-tune vs FuseAI/FuseChat-Llama-3.2-3B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 10/57, MLP 84/84, Attention 112/112

2 derivatives checked

• mradermacher/Llama-3.2-3b-RP-Toxic-Fuse-GGUF: Same weights, converted
• mradermacher/Llama-3.2-3b-RP-Toxic-Fuse-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse