Novaciano/KobbleKiller-1.1B
Partial fine-tune vs Novaciano/TinyKiller-NSFW-DPO-1.1B. Partial change: 56% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 21 of 22 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 26/45, MLP 33/66, Attention 45/88
2 derivatives checked
- mradermacher/KobbleKiller-1.1B-i1-GGUF: Quantization
- mradermacher/KobbleKiller-1.1B-GGUF: Same weights, converted