Mawdistical/Squelching-Fantasies-70B
Full fine-tune vs TheSkullery/Unnamed-Exp-70b-v0.7.A. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320
3 derivatives checked
- mradermacher/Squelching-Fantasies-70B-i1-GGUF: Quantization
- Mawdistical/Squelching-Fantasies-70B-GGUF: Quantization
- mradermacher/Squelching-Fantasies-70B-GGUF: Quantization