AI45Research/SafeWork-R1-DeepSeek-70B

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Llama-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, Attention 320/320, MLP 240/240, Norms 110/161, lm_head 1/1

2 derivatives checked

• mradermacher/SafeWork-R1-DeepSeek-70B-i1-GGUF: Quantization
• mradermacher/SafeWork-R1-DeepSeek-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse