Building a fully local

DeepSeek-R1 is a strong performing, open source reasoning model with several distilled versions that can be run locally. Here, we walk through the DeepSeek-R1 paper to review the details of the training methodology, download the 14b distilled model via Ollama, test generation / JSON-mode, and then test it in a fully local "deep research" assistant that performs web-research / summarization w/ an iterative reflection step to improve its results.

Video notes:
https://mirror-feeling-d80.not....ion.site/DeepSeek-R1

Code repo:
https://github.com/langchain-a....i/ollama-deep-resear

Related video on reasoning models:
https://www.youtube.com/watch?v=f0RbwrBcFmc

Prior build-from-scratch video for an earlier version of this research assistant:
https://www.youtube.com/watch?v=XGuTzHoqlj8