anasali4151/llama3.1-heretic-unsensored
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/llama3.1-heretic-unsensored-GGUF: Same weights, converted
- mradermacher/llama3.1-heretic-unsensored-i1-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.