DataSoul/QwQ-32B-Flash-merge

Full fine-tune vs DataSoul/Sky-T1-32B-Flash-abliterated-merge1. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 127/129, MLP 192/192, Attention 448/448

1 derivatives checked

• mradermacher/QwQ-32B-Flash-merge-GGUF: Quantization

On the Hub · Downloads on Model Pulse