# Use a pipeline as a high-level helper from transformers import pipeline messages = [ {"role": "user", "content": """your task is to generate 6 scenes each of 6 seconds on topic of Mughal empire. make it in a structured way with individual title for each heading."""}] pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-R1-Distill-Llama-70B") pipe(messages) I have tried adding my token on both GPU and CPU parts. But I want to use the model efficiently on CPU. How do I fix it? Continue reading...
