Heouzen/Huihui-Qwen3-VL-8B-Instruct-FP8-abliterated

Partial fine-tune vs huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated. Partial change: 86% of the weights changed (attention, mlp), in 36 of 36 layers.

Tensors changed: Embeddings 0/4, Norms 0/261, MLP 232/232, Attention 252/252, lm_head 0/1

On the Hub · Downloads on Model Pulse