Instructions to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GhostScientist/gpt-oss-20b-semanticwiki-gguf",
	filename="gpt-oss-20b-semanticwiki-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf: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 GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf: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 GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

Use Docker

docker model run hf.co/GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with Ollama:
```
ollama run hf.co/GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M
```

Unsloth Studio

How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf 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 GhostScientist/gpt-oss-20b-semanticwiki-gguf 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 GhostScientist/gpt-oss-20b-semanticwiki-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GhostScientist/gpt-oss-20b-semanticwiki-gguf to start chatting

How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

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": "GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

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 GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with Docker Model Runner:
```
docker model run hf.co/GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M
```

Lemonade

How to use GhostScientist/gpt-oss-20b-semanticwiki-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GhostScientist/gpt-oss-20b-semanticwiki-gguf:Q4_K_M

Run and chat with the model

lemonade run user.gpt-oss-20b-semanticwiki-gguf-Q4_K_M

List all available models

lemonade list

gpt-oss-20b-semanticwiki-gguf / README.md

GhostScientist

Update README.md

16dbf85 verified 5 months ago

preview code

raw

history blame contribute delete

1.34 kB

metadata

base_model: openai/gpt-oss-20b
tags:
  - gguf
  - llama.cpp
  - quantized
  - gpt-oss
  - semanticwiki
datasets:
  - GhostScientist/semanticwiki-data

gpt-oss-20b-semanticwiki GGUF

GGUF conversion of GhostScientist/gpt-oss-20b-semanticwiki, fine-tuned on SemanticWiki data.

Available Quantizations

File	Quant	Description
gpt-oss-20b-semanticwiki-f16.gguf	F16	Full precision
gpt-oss-20b-semanticwiki-q8_0.gguf	Q8_0	8-bit (recommended for 32GB+ RAM)
gpt-oss-20b-semanticwiki-q5_k_m.gguf	Q5_K_M	5-bit medium
gpt-oss-20b-semanticwiki-q4_k_m.gguf	Q4_K_M	4-bit medium (smallest)

Usage

With Ollama

huggingface-cli download GhostScientist/gpt-oss-20b-semanticwiki-gguf gpt-oss-20b-semanticwiki-q8_0.gguf
echo "FROM ./gpt-oss-20b-semanticwiki-q8_0.gguf" > Modelfile
ollama create gpt-oss-semanticwiki -f Modelfile
ollama run gpt-oss-semanticwiki

With llama.cpp

./llama-cli -m gpt-oss-20b-semanticwiki-q8_0.gguf -p "Your prompt"

Model Details

Base Model: openai/gpt-oss-20b (22B params, 3.6B active - MoE)
Fine-tuned Model: GhostScientist/gpt-oss-20b-semanticwiki
Dataset: GhostScientist/semanticwiki-data
Training: SFT with LoRA using TRL