mradermacher/AFM-4.5B-Uncensored-Abliterated-GGUF

Same weights, converted vs Securelayer7/AFM-4.5B-Uncensored-Abliterated. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/73, MLP 0/72, Attention 0/144

On the Hub · Downloads on Model Pulse