sh0ck0r/Forgotten-Safeword-70B-v5.0-heretic
Full fine-tune vs SicariusSicariiStuff/Negative_LLAMA_70B. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 1/1
2 derivatives checked
- mradermacher/Forgotten-Safeword-70B-v5.0-heretic-i1-GGUF: Quantization
- mradermacher/Forgotten-Safeword-70B-v5.0-heretic-GGUF: Quantization