Data

Tools

Indexes

Applications

Experiments

Open Source Science

ollama_deepseek-r1

Example interacting with deepseek-r1 from Python

https://github.com/theopensciencenerd/ollama_deepseek-r1

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 4 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (14.0%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

Example interacting with deepseek-r1 from Python

Basic Info
  • Host: GitHub
  • Owner: TheOpenScienceNerd
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 30.3 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 2
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme Changelog License Citation

README.md

ORCID: Monks License: MIT DOI

DeepSeek-R1: research setup for working with Ollama, Python DeepSeek locally.

The materials in this repo provide a example Python code to prompt a local installation of DeepSeek-R1 using the python package ollama

See ollama documentation for installing LLMs locally on your machine.

License

The materials have been made available under an MIT license. The materials are as-is with no liability for the author. Please provide credit if you reuse the code in your own work.

Citation

Please feel free to use or adapt the code for your own work. But if so then a citation would be very much appreciated!

bibtex @software{ollama_deepseekr1, author = {Monks, Thomas }, license = {MIT}, title = {{@TheOpenScienceNerd: Interacting with DeepSeek-R1 via Python}}, url = {https://github.com/TheOpenScienceNerd/ollama_deepseek-r1}, doi = {https://doi.org/10.5281/zenodo.14876187} }

Installation instructions

Installing dependencies

All dependencies can be found in environment.yml and are pulled from conda-forge. To run the code locally, we recommend installing miniforge;

miniforge is Free and Open Source Software (FOSS) alternative to Anaconda and miniconda that uses conda-forge as the default channel for packages. It installs both conda and mamba (a drop in replacement for conda) package managers. We recommend mamba for faster resolving of dependencies and installation of packages.

navigating your terminal (or cmd prompt) to the directory containing the repo and issuing the following command:

bash mamba env create -f environment.yml

Activate the mamba environment using the following command:

bash mamba activate ollama

Run Jupyter-lab

bash jupyter-lab

Repo overview

. ├── binder │   └── ├── callcentresim │   ├── __init__.py │   ├── model.py │   └── output_analysis.py ├── CHANGELOG.md ├── CITATION.cff ├── environment.yml ├── LICENSE ├── 01_prompt_deepseek.ipynb ├── 02_conversations.ipynb └── README.md

  • environment.yml - contains the conda environment if you wish to work locally algorithm
  • 01_prompt_deepseek.ipynb - main notebook file containing the tutorial code for the interacting with a local deepseek-r1 via python.
  • 02_conversations.ipynb -tutorial to setup conversation history as context (data) and pass that to a local LLM via ollama.
  • CHANGES.md - changelog with record of notable changes to project between versions.
  • CITATION.cff - citation information for the package.
  • LICENSE - details of the MIT permissive license of this work.

Owner

  • Name: TheOpenScienceNerd
  • Login: TheOpenScienceNerd
  • Kind: organization
  • Location: United Kingdom

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: '@TheOpenScienceNerd: Interacting with DeepSeek-R1 via Python'
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: 'Thomas '
    family-names: Monks
    affiliation: University of Exeter
    orcid: 'https://orcid.org/0000-0003-2631-4481'
repository-code: 'https://github.com/TheOpenScienceNerd/replications-algorithm'
keywords:
  - DeepSeek
  - Ollama
  - python
  - open science
license: MIT

GitHub Events

Total
  • Release event: 2
  • Watch event: 1
  • Public event: 1
  • Push event: 8
  • Pull request event: 2
  • Fork event: 1
  • Create event: 3
Last Year
  • Release event: 2
  • Watch event: 1
  • Public event: 1
  • Push event: 8
  • Pull request event: 2
  • Fork event: 1
  • Create event: 3

Issues and Pull Requests

Last synced: 9 months ago

All Time
  • Total issues: 0
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • TomMonks (1)
Top Labels
Issue Labels
Pull Request Labels

Dependencies

environment.yml conda
  • jupyterlab 4.3.5.*
  • jupyterlab-plotly-extension 1.0.0.*
  • jupyterlab-spellchecker 0.8.4.*
  • numpy 2.2.3.*
  • pandas 2.2.3.*
  • pip 25.0.*
  • python 3.11.*