AI45Research/SafeWork-R1

Full fine-tune vs Qwen/Qwen2.5-VL-72B-Instruct. Fine-tune: 99% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/2, Norms 134/226, Attention 560/688, MLP 240/436, lm_head 1/1

2 derivatives checked

• mradermacher/SafeWork-R1-i1-GGUF: Quantization
• mradermacher/SafeWork-R1-GGUF: Quantization

On the Hub · Downloads on Model Pulse