Instructions to use Minibase/Detoxify-Language-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minibase/Detoxify-Language-Small with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Minibase/Detoxify-Language-Small",
	filename="detoxify-small-q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Minibase/Detoxify-Language-Small with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Minibase/Detoxify-Language-Small:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Minibase/Detoxify-Language-Small:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Minibase/Detoxify-Language-Small:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Minibase/Detoxify-Language-Small:Q8_0

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 Minibase/Detoxify-Language-Small:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Minibase/Detoxify-Language-Small:Q8_0

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 Minibase/Detoxify-Language-Small:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Minibase/Detoxify-Language-Small:Q8_0

Use Docker

docker model run hf.co/Minibase/Detoxify-Language-Small:Q8_0

LM Studio
Jan
Ollama
How to use Minibase/Detoxify-Language-Small with Ollama:
```
ollama run hf.co/Minibase/Detoxify-Language-Small:Q8_0
```

Unsloth Studio new

How to use Minibase/Detoxify-Language-Small 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 Minibase/Detoxify-Language-Small 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 Minibase/Detoxify-Language-Small to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Minibase/Detoxify-Language-Small to start chatting

Docker Model Runner
How to use Minibase/Detoxify-Language-Small with Docker Model Runner:
```
docker model run hf.co/Minibase/Detoxify-Language-Small:Q8_0
```

Lemonade

How to use Minibase/Detoxify-Language-Small with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Minibase/Detoxify-Language-Small:Q8_0

Run and chat with the model

lemonade run user.Detoxify-Language-Small-Q8_0

List all available models

lemonade list

Minibase commited on Sep 17, 2025

Commit

b13b7d0

verified ·

1 Parent(s): 2adb798

Upload run_server.sh with huggingface_hub

Browse files

Files changed (1) hide show

run_server.sh +82 -0

run_server.sh ADDED Viewed

	@@ -0,0 +1,82 @@

+#!/bin/bash
+# Detoxify-Small - GGUF Model Server Launcher
+# Generated on 2025-09-17 20:07:11
+# Configuration
+MODEL_FILE="model.gguf"
+MODEL_NAME="Detoxify-Small"
+HOST="127.0.0.1"
+PORT="8000"
+GPU_LAYERS="0"
+# Colors for output
+RED='[0;31m'
+GREEN='[0;32m'
+YELLOW='[1;33m'
+BLUE='[0;34m'
+NC='[0m' # No Color
+echo -e "========================================"
+echo -e "  Detoxify-Small Server"
+echo -e "========================================"
+echo
+# Check if model file exists
+if [ ! -f "$MODEL_FILE" ]; then
+    echo -e "Error: Model file '$MODEL_FILE' not found!"
+    echo -e "Make sure you're running this script from the model directory."
+    exit 1
+fi
+echo -e "✓ Model file found: $MODEL_FILE"
+echo -e "✓ Model: $MODEL_NAME"
+echo -e "✓ Server: http://$HOST:$PORT"
+echo
+# Check if port is available
+if lsof -Pi :$PORT -sTCP:LISTEN -t >/dev/null ; then
+    echo -e "Warning: Port $PORT is already in use."
+    echo -e "Trying alternative port 8001..."
+    PORT="8001"
+fi
+# Detect system capabilities
+if [[ "$OSTYPE" == "darwin"* ]]; then
+    echo -e "✓ macOS detected - Metal GPU acceleration available"
+    GPU_LAYERS="35"  # Reasonable default for M1/M2/M3
+elif command -v nvidia-smi &> /dev/null; then
+    echo -e "✓ NVIDIA GPU detected - CUDA acceleration available"
+    GPU_LAYERS="35"  # Reasonable default for CUDA
+else
+    echo -e "No GPU acceleration detected - using CPU only"
+    GPU_LAYERS="0"
+fi
+echo -e "✓ GPU layers: $GPU_LAYERS"
+echo
+# Check for llama-server
+if ! command -v llama-server &> /dev/null; then
+    echo -e "Error: llama-server not found in PATH!"
+    echo -e "Please install llama.cpp and add it to your PATH:"
+    echo -e "  https://github.com/ggerganov/llama.cpp"
+    exit 1
+fi
+echo -e "✓ llama-server found"
+echo
+echo -e "Starting server..."
+echo -e "Press Ctrl+C to stop"
+echo
+# Start the server
+exec llama-server \
+    -m "$MODEL_FILE" \
+    --host "$HOST" \
+    --port "$PORT" \
+    --n-gpu-layers "$GPU_LAYERS" \
+    --ctx-size 4096 \
+    --chat-template "" \
+    --log-disable