Instructions to use Offensivesec/ubuntu-support-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Offensivesec/ubuntu-support-llm with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Offensivesec/ubuntu-support-llm",
	filename="ubuntu-support-Q4_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 Offensivesec/ubuntu-support-llm with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Offensivesec/ubuntu-support-llm:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Offensivesec/ubuntu-support-llm:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Offensivesec/ubuntu-support-llm:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Offensivesec/ubuntu-support-llm:Q4_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 Offensivesec/ubuntu-support-llm:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Offensivesec/ubuntu-support-llm:Q4_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 Offensivesec/ubuntu-support-llm:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Offensivesec/ubuntu-support-llm:Q4_K_M

Use Docker

docker model run hf.co/Offensivesec/ubuntu-support-llm:Q4_K_M

LM Studio
Jan
Ollama
How to use Offensivesec/ubuntu-support-llm with Ollama:
```
ollama run hf.co/Offensivesec/ubuntu-support-llm:Q4_K_M
```

Unsloth Studio

How to use Offensivesec/ubuntu-support-llm 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 Offensivesec/ubuntu-support-llm 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 Offensivesec/ubuntu-support-llm to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Offensivesec/ubuntu-support-llm to start chatting

Docker Model Runner
How to use Offensivesec/ubuntu-support-llm with Docker Model Runner:
```
docker model run hf.co/Offensivesec/ubuntu-support-llm:Q4_K_M
```

Lemonade

How to use Offensivesec/ubuntu-support-llm with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Offensivesec/ubuntu-support-llm:Q4_K_M

Run and chat with the model

lemonade run user.ubuntu-support-llm-Q4_K_M

List all available models

lemonade list

Ubuntu Support LLM

A small GPT2-based model (51M params) fine-tuned on Ubuntu Q&A dialogue. Refuses all non-Ubuntu questions.

Model Details

Architecture: GPT2 (512 embd, 8 layers, 8 heads)
Training data: sedthh/ubuntu_dialogue_qa (~12k records)
Epochs: 5 | Loss: 2.076
Quantization: Q4_K_M (40 MB)

Run with Ollama

ollama create ubuntu-support -f Modelfile
ollama run ubuntu-support

Downloads last month: 67

Safetensors

Model size

51.2M params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support