Instructions to use dranger003/starcoder2-15b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dranger003/starcoder2-15b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dranger003/starcoder2-15b-GGUF",
	filename="ggml-starcoder2-15b-f16.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 dranger003/starcoder2-15b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dranger003/starcoder2-15b-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf dranger003/starcoder2-15b-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf dranger003/starcoder2-15b-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf dranger003/starcoder2-15b-GGUF:F16

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 dranger003/starcoder2-15b-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf dranger003/starcoder2-15b-GGUF:F16

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 dranger003/starcoder2-15b-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dranger003/starcoder2-15b-GGUF:F16

Use Docker

docker model run hf.co/dranger003/starcoder2-15b-GGUF:F16

LM Studio
Jan

vLLM

How to use dranger003/starcoder2-15b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dranger003/starcoder2-15b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dranger003/starcoder2-15b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dranger003/starcoder2-15b-GGUF:F16

Ollama
How to use dranger003/starcoder2-15b-GGUF with Ollama:
```
ollama run hf.co/dranger003/starcoder2-15b-GGUF:F16
```

Unsloth Studio new

How to use dranger003/starcoder2-15b-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 dranger003/starcoder2-15b-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 dranger003/starcoder2-15b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dranger003/starcoder2-15b-GGUF to start chatting

Docker Model Runner
How to use dranger003/starcoder2-15b-GGUF with Docker Model Runner:
```
docker model run hf.co/dranger003/starcoder2-15b-GGUF:F16
```

Lemonade

How to use dranger003/starcoder2-15b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dranger003/starcoder2-15b-GGUF:F16

Run and chat with the model

lemonade run user.starcoder2-15b-GGUF-F16

List all available models

lemonade list

GGUF quants for https://huggingface.co/bigcode/starcoder2-15b

StarCoder2-15B model is a 15B parameter model trained on 600+ programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 4+ trillion tokens.

The model was trained on GitHub code as well as additional selected data sources such as Arxiv and Wikipedia. As such it is not an instruction model and commands like "Write a function that computes the square root." do not work well.

Layers	Context	Template (None/Base Model)
40	16384	{prompt}

Downloads last month: 57

GGUF

Model size

16B params

Architecture

starcoder2

Hardware compatibility

6-bit

8-bit

16-bit