Instructions to use lerugray/the-basel-program-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lerugray/the-basel-program-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lerugray/the-basel-program-7b",
	filename="the-basel-program-7b-Q5_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lerugray/the-basel-program-7b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lerugray/the-basel-program-7b:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf lerugray/the-basel-program-7b:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lerugray/the-basel-program-7b:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf lerugray/the-basel-program-7b:Q5_K_M

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 lerugray/the-basel-program-7b:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf lerugray/the-basel-program-7b:Q5_K_M

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 lerugray/the-basel-program-7b:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lerugray/the-basel-program-7b:Q5_K_M

Use Docker

docker model run hf.co/lerugray/the-basel-program-7b:Q5_K_M

LM Studio
Jan

vLLM

How to use lerugray/the-basel-program-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lerugray/the-basel-program-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lerugray/the-basel-program-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lerugray/the-basel-program-7b:Q5_K_M

Ollama
How to use lerugray/the-basel-program-7b with Ollama:
```
ollama run hf.co/lerugray/the-basel-program-7b:Q5_K_M
```

Unsloth Studio

How to use lerugray/the-basel-program-7b 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 lerugray/the-basel-program-7b 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 lerugray/the-basel-program-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lerugray/the-basel-program-7b to start chatting

Atomic Chat new
Docker Model Runner
How to use lerugray/the-basel-program-7b with Docker Model Runner:
```
docker model run hf.co/lerugray/the-basel-program-7b:Q5_K_M
```

Lemonade

How to use lerugray/the-basel-program-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lerugray/the-basel-program-7b:Q5_K_M

Run and chat with the model

lemonade run user.the-basel-program-7b-Q5_K_M

List all available models

lemonade list

the-basel-program-7b / README.md

lerugray

Upload README.md with huggingface_hub

998c887 verified 8 days ago

preview code

Raw

History Blame Contribute Delete

1.88 kB

metadata

license: cc-by-nc-4.0
language:
  - en
base_model:
  - Qwen/Qwen2.5-7B-Instruct
library_name: gguf
tags:
  - gguf
  - the-elect
  - register-model
pipeline_tag: text-generation

THE BASEL PROGRAM -- a Theodor Herzl register model (7B)

A 7B register model tuned to write in the voice of Theodor Herzl (1860-1904), founder of political Zionism, in the register of Der Judenstaat: formal, architectural, grimly lucid.

Landing page: https://lerugray.github.io/the-basel-program-7b/
Part of: The Elect voice lab; The Reprobate counter-canon
Base: Qwen2.5-7B-Instruct, completion fine-tune (Unsloth), GGUF Q5_K_M

What it is

Completion-trained on 146 rows of Herzl's own words -- exclusively the 1896 d'Avigdor public-domain English translation of Der Judenstaat (the lean v1; Congress speeches and diaries held for a v2). Elicited with a study-visit lead-in:

A visitor comes to Theodor Herzl's study and puts this question to him: [your question]

Run (Ollama)

ollama create the-basel-program -f Modelfile.the-basel-program
ollama run the-basel-program "Is antisemitism a prejudice that reform will cure?"

Disclaimer

This is not Herzl, not an oracle, and not a factual source. It imitates the register of Der Judenstaat and holds Herzl's actual historical positions -- antisemitism as a structural reaction rather than a curable prejudice, the failure of assimilation, the state as a problem of engineering. It will not hedge or break character. It invents names, dates, and citations; read it for register, not record. A register artifact run as the anti-Elect adversary in a one-person voice lab.

License CC-BY-NC-4.0. Public-domain source material; training corpus withheld. Attribution: Ray Weiss / The Elect / The Reprobate.