TouchNight/gemma-2-abliterated-Ifable-9B

Full fine-tune vs IlyaGusev/gemma-2-9b-it-abliterated. Fine-tune: 90% of the weights changed, across 42 of 42 layers.

Tensors changed: Embeddings 0/1, Norms 111/169, MLP 126/126, Attention 168/168

2 derivatives checked

• mradermacher/gemma-2-abliterated-Ifable-9B-i1-GGUF: Quantization
• mradermacher/gemma-2-abliterated-Ifable-9B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse