DataSoul/Sky-T1-32B-Flash-abliterated-merge1

Full fine-tune vs NovaSky-AI/Sky-T1-32B-Flash. Fine-tune: 95% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 121/129, MLP 192/192, Attention 447/448, lm_head 0/1

3 derivatives checked

• mradermacher/Sky-T1-32B-Flash-abliterated-merge1-i1-GGUF: Quantization
• mradermacher/Sky-T1-32B-Flash-abliterated-merge1-GGUF: Quantization
• DataSoul/QwQ-32B-Flash-merge: Full fine-tune

On the Hub · Downloads on Model Pulse