I want to run the DeepSeek-V3 model inference using the Hugging-Face Transformer library (>= v4.51.0). I read that you can do the following to do that (download the model and run it) from transformers import pipeline messages = [ {"role": "user", "content": "Who are you?"}, ] pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1", trust_remote_code=True) pipe(messages) My issue is that I already downloaded the DeepSeek-V3 hugging-face repository separately, and I just want to tell the Transformer where it is on my local machine, so that it can run the inference. How can I achieve that ? (sorry if this kind of questions has already been asked, but I am kind of struggling, and it would take a really long time just to download the whole model again). Continue reading...
