mradermacher/Fara-7B-Abliterated-v2-GGUF

Same weights, converted (fewer layers) vs josephmayo/Fara-7B-Abliterated-v2. mradermacher/Fara-7B-Abliterated-v2-GGUF matches part of josephmayo/Fara-7B-Abliterated-v2 (339 of its 729 tensors; the rest of josephmayo/Fara-7B-Abliterated-v2 has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196

On the Hub · Downloads on Model Pulse