NullpoLab/Agents-A1-4B-Heretic-ARA-Refusals8-GGUF

Same weights, converted vs NullpoLab/Agents-A1-4B-Heretic-ARA-Refusals8. Same weights stored in another dtype (BF16 → BF16/F32), plus 24 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32

On the Hub · Downloads on Model Pulse