mradermacher/G9v3-3B-Heretic-Abliterated-GGUF

Same weights, converted vs Vortecks/G9v3-3B-Heretic-Abliterated. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/105, MLP 0/156, Attention 0/208

On the Hub · Downloads on Model Pulse