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
Chat prompt?
#3
by apepkuss79 - opened
What's the chat prompt in plain text? Thanks!
check the bottom of file https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/main/tokenizer_config.json
the prompt can be reconstructed by removing the pseudo code parts and constructing the correct prompt for your use case
I tried something like this and it worked (note the weird character they use instead of a regular underscore):
<|begin▁of▁sentence|>You are a helpful assistant<|User|>if there are 20 persons in a room, how likely is it that two of them share the same birthday date (not considering the year)?<|Assistant|><|end▁of▁sentence|><|Assistant|>
Thank you so much!
apepkuss79 changed discussion status to closed