YanLabs/gemma-3-27b-it-abliterated-normpreserve-v1-GGUF

Same weights, converted (fewer layers) vs YanLabs/gemma-3-27b-it-abliterated-normpreserve-v1. YanLabs/gemma-3-27b-it-abliterated-normpreserve-v1-GGUF matches part of YanLabs/gemma-3-27b-it-abliterated-normpreserve-v1 (808 of its 1247 tensors; the rest of YanLabs/gemma-3-27b-it-abliterated-normpreserve-v1 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248

On the Hub · Downloads on Model Pulse