abhaymin/Ornith-1.5-Cyclos-1M-Uncensored
Full fine-tune vs 0xKitkat/Ornith-1.5-35B-A3B-Uncensored. Fine-tune: 91% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/5, Norms 0/247, Attention 40/392, MLP 200/1165, lm_head 0/1, other 0/1
2 derivatives checked
- mradermacher/Ornith-1.5-Cyclos-1M-Uncensored-GGUF: Quantization
- mradermacher/Ornith-1.5-Cyclos-1M-Uncensored-i1-GGUF: Quantization