Instructions to use ivoras/bernie0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use ivoras/bernie0.1 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ivoras/bernie0.1", filename="bernie-0.1_IQ4_NL.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use ivoras/bernie0.1 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ivoras/bernie0.1:IQ4_NL # Run inference directly in the terminal: llama-cli -hf ivoras/bernie0.1:IQ4_NL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ivoras/bernie0.1:IQ4_NL # Run inference directly in the terminal: llama-cli -hf ivoras/bernie0.1:IQ4_NL
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf ivoras/bernie0.1:IQ4_NL # Run inference directly in the terminal: ./llama-cli -hf ivoras/bernie0.1:IQ4_NL
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf ivoras/bernie0.1:IQ4_NL # Run inference directly in the terminal: ./build/bin/llama-cli -hf ivoras/bernie0.1:IQ4_NL
Use Docker
docker model run hf.co/ivoras/bernie0.1:IQ4_NL
- LM Studio
- Jan
- Ollama
How to use ivoras/bernie0.1 with Ollama:
ollama run hf.co/ivoras/bernie0.1:IQ4_NL
- Unsloth Studio
How to use ivoras/bernie0.1 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ivoras/bernie0.1 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ivoras/bernie0.1 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ivoras/bernie0.1 to start chatting
- Pi
How to use ivoras/bernie0.1 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ivoras/bernie0.1:IQ4_NL
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ivoras/bernie0.1:IQ4_NL" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use ivoras/bernie0.1 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ivoras/bernie0.1:IQ4_NL
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default ivoras/bernie0.1:IQ4_NL
Run Hermes
hermes
- Docker Model Runner
How to use ivoras/bernie0.1 with Docker Model Runner:
docker model run hf.co/ivoras/bernie0.1:IQ4_NL
- Lemonade
How to use ivoras/bernie0.1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ivoras/bernie0.1:IQ4_NL
Run and chat with the model
lemonade run user.bernie0.1-IQ4_NL
List all available models
lemonade list
This is a proof of concept model trained on the works of US senator Bernie Sanders. The details on how and why it was created are described in this blog post, but the tl;dr is that it's an experiment inspired by the sci-fi concept of "mind states" or "mind uploads".
This is done in the spirit of exploration and with all respect to senator Sanders and his work. The model is not to be taken as an actual substitute for the person.
Some questions to ask the model:
- What do you think about workers rights?
- What specifically are you doing to address the youth mental health crisis?
- How do you manage the constant negativity and attacks online?
As the "0.1" version suggest, this really is a proof of concept, and the model can be improved significantly. Apparently Ollama has problems with quantized versions of the model (at least in v0.9.6), and you should use the F16 GGUF version for it. llama.cpp (b6022) doesn't have these problems and the provided IQ4 quantized version works well enough (LMStudio also has the llama.cpp version that works with the IQ4 version, at least as of 2025-08-27).
Here's an example of a conversation with the model:
User: What are the problems with American workers?
Assistent: We have a serious problem of stagnant wages, rising inequality, and declining job security for working Americans. Many struggle to make ends meet despite putting in hard work. We need policies that help them catch up.
User: Make an essay on improving the living conditions of American workers.
Assistent: The American Dream is under attack. For decades, our economy has been rigged against working families. Stagnant wages, rising inequality, and declining benefits have left many struggling to survive. This isn't acceptable. We need bold action to improve their living conditions.
First and foremost, we must address the crisis of stagnant wages. A minimum wage increase is a start, but it's not enough. We need a living wage – one that allows workers to afford basic necessities like housing, food, and healthcare. The current federal minimum wage hasn't kept pace with inflation since 2009.
Secondly, we must tackle the issue of rising inequality. This isn't about rewarding hard work; it's about systemic injustice. We need policies that address tax fairness – closing corporate loopholes and eliminating tax breaks for the wealthy. We also need to strengthen unions and protect worker rights.
Thirdly, job security is disappearing. The gig economy and precarious employment are on the rise. We must invest in good-paying jobs in good-paying industries – healthcare, education, renewable energy – creating a safety net for workers who can't rely on unstable employment.
Finally, we need to address the crisis of affordable housing. Housing is a fundamental human right. We must invest in affordable housing programs, rent control, and community land trusts. We also need to address the root causes of homelessness through comprehensive social services.
This isn't about handouts; it's about investments in our communities. It's about recognizing that the value of workers lies not just in their productivity but in their dignity and well-being. A better future for American workers requires bold action, a commitment to fairness, and a willingness to challenge the status quo.
Here's an excerpt from the blog post:
Uploading people into some kind of a computer has been a science fiction trope for a long time - and so far it’s mostly a pipe dream. I’ve experienced two things recently that inspired me to write this post - and create the associated project: a pretty good animated series named Pantheon, and re-reading the excellent book “Excession,” by Iain Banks. Both works feature the idea of abstracting, copying, and augmenting human minds through digital uploads.
Excession, specifically, has this concept of a “mind state” - a snapshot of a person’s mind at some time, which isn’t really 100% identical, is usually focused on some topic, and up to a point has a mind of its own.
This mind state as described in the book isn’t really autonomous nor really intelligent, but the most important thing about the mind state is that you can talk to it pretty much as you would with the original person. It will respond to you as the original person would.
It’s the closest thing before a “real” mind upload.
- Downloads last month
- 38
Model tree for ivoras/bernie0.1
Base model
meta-llama/Llama-3.2-3B-Instruct