Instructions to use bartowski/speechless-starcoder2-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/speechless-starcoder2-7b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bartowski/speechless-starcoder2-7b-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/speechless-starcoder2-7b-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bartowski/speechless-starcoder2-7b-GGUF 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 bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/speechless-starcoder2-7b-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 bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/speechless-starcoder2-7b-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 bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/speechless-starcoder2-7b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/speechless-starcoder2-7b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/speechless-starcoder2-7b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M

SGLang

How to use bartowski/speechless-starcoder2-7b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bartowski/speechless-starcoder2-7b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/speechless-starcoder2-7b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bartowski/speechless-starcoder2-7b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/speechless-starcoder2-7b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use bartowski/speechless-starcoder2-7b-GGUF with Ollama:
```
ollama run hf.co/bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use bartowski/speechless-starcoder2-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/speechless-starcoder2-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/speechless-starcoder2-7b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.speechless-starcoder2-7b-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Llamacpp Quantizations of speechless-starcoder2-7b

Using llama.cpp release b2354 for quantization.

Original model: https://huggingface.co/uukuguy/speechless-starcoder2-7b

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Description
speechless-starcoder2-7b-Q8_0.gguf	Q8_0	7.62GB	Extremely high quality, generally unneeded but max available quant.
speechless-starcoder2-7b-Q6_K.gguf	Q6_K	5.89GB	Very high quality, near perfect, recommended.
speechless-starcoder2-7b-Q5_K_M.gguf	Q5_K_M	5.12GB	High quality, very usable.
speechless-starcoder2-7b-Q5_K_S.gguf	Q5_K_S	4.93GB	High quality, very usable.
speechless-starcoder2-7b-Q5_0.gguf	Q5_0	4.93GB	High quality, older format, generally not recommended.
speechless-starcoder2-7b-Q4_K_M.gguf	Q4_K_M	4.40GB	Good quality, similar to 4.25 bpw.
speechless-starcoder2-7b-Q4_K_S.gguf	Q4_K_S	4.12GB	Slightly lower quality with small space savings.
speechless-starcoder2-7b-Q4_0.gguf	Q4_0	4.04GB	Decent quality, older format, generally not recommended.
speechless-starcoder2-7b-Q3_K_L.gguf	Q3_K_L	3.98GB	Lower quality but usable, good for low RAM availability.
speechless-starcoder2-7b-Q3_K_M.gguf	Q3_K_M	3.59GB	Even lower quality.
speechless-starcoder2-7b-Q3_K_S.gguf	Q3_K_S	3.09GB	Low quality, not recommended.
speechless-starcoder2-7b-Q2_K.gguf	Q2_K	2.72GB	Extremely low quality, not recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

Downloads last month: 469

GGUF

Model size

7B params

Architecture

starcoder2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Datasets used to train bartowski/speechless-starcoder2-7b-GGUF

Evaluation results

pass@1 on HumanEval
self-reported

0.000