Instructions to use deepseek-ai/DeepSeek-R1-Distill-Qwen-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/DeepSeek-R1-Distill-Qwen-14B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Is there any method to limit the thinking process of this model?
#18
by SAPIENS2333 - opened
Since it's very time consuming for this model to start a CoT (contents before /think) of some very simple questions like: what is the capital of China, I wonder if there is any method to close or limit the thinking part of this model when dealing with some simple questions? Thanks.