zetasepic/Mistral-Small-Instruct-2409-abliterated
Partial fine-tune vs mistralai/Mistral-Small-Instruct-2409. Partial change: 74% of the weights changed (attention, embeddings, mlp), in 56 of 56 layers.
Tensors changed: Embeddings 1/1, Norms 0/113, MLP 112/168, Attention 224/224, lm_head 0/1
1 derivatives checked
- bartowski/zetasepic_Mistral-Small-Instruct-2409-abliterated-GGUF: Same weights, converted