Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct-abliterated
Full fine-tune vs Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 0/33, MLP 48/48, Attention 64/64
3 derivatives checked
- mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF: Same weights, converted
- itlwas/Vikhr-Llama-3.2-1B-Instruct-abliterated-Q4_K_M-GGUF: Quantization
- amtk/Vikhr-Llama-3.2-1B-Instruct-abliterated-Q4_K_M-GGUF: Quantization