s3nh/Ministral-3-14B-Instruct-2512-BF16-abliterated

Full fine-tune vs mistralai/Ministral-3-14B-Base-2512. Fine-tune: 97% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 54/131, MLP 120/192, Attention 160/256, other 2/4, lm_head 1/1

2 derivatives checked

• mradermacher/Ministral-3-14B-Instruct-2512-BF16-abliterated-GGUF: Quantization (fewer layers)
• mradermacher/Ministral-3-14B-Instruct-2512-BF16-abliterated-i1-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse