mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF

Same weights, converted vs Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct-abliterated. Same weights stored in another dtype (F16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64

On the Hub · Downloads on Model Pulse