SicariusSicariiStuff/Fiendish_LLAMA_3B
Full fine-tune vs meta-llama/Llama-3.2-3B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
5 derivatives checked
- mradermacher/Fiendish_LLAMA_3B-GGUF: Same weights, converted
- mradermacher/Fiendish_LLAMA_3B-i1-GGUF: Quantization
- SicariusSicariiStuff/Fiendish_LLAMA_3B_iMatrix: Quantization
- SicariusSicariiStuff/Fiendish_LLAMA_3B_GGUF: Quantization
- SicariusSicariiStuff/Fiendish_LLAMA_3B_Abliterated: Abliterated