Instructions to use mlx-community/bigcode-starcoder2-15b-fp32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/bigcode-starcoder2-15b-fp32 with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/bigcode-starcoder2-15b-fp32")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/bigcode-starcoder2-15b-fp32")
model = AutoModelForCausalLM.from_pretrained("mlx-community/bigcode-starcoder2-15b-fp32")

MLX

How to use mlx-community/bigcode-starcoder2-15b-fp32 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/bigcode-starcoder2-15b-fp32")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/bigcode-starcoder2-15b-fp32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/bigcode-starcoder2-15b-fp32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/bigcode-starcoder2-15b-fp32",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/bigcode-starcoder2-15b-fp32

SGLang

How to use mlx-community/bigcode-starcoder2-15b-fp32 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 "mlx-community/bigcode-starcoder2-15b-fp32" \
    --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": "mlx-community/bigcode-starcoder2-15b-fp32",
		"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 "mlx-community/bigcode-starcoder2-15b-fp32" \
        --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": "mlx-community/bigcode-starcoder2-15b-fp32",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use mlx-community/bigcode-starcoder2-15b-fp32 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "mlx-community/bigcode-starcoder2-15b-fp32" --prompt "Once upon a time"

Docker Model Runner
How to use mlx-community/bigcode-starcoder2-15b-fp32 with Docker Model Runner:
```
docker model run hf.co/mlx-community/bigcode-starcoder2-15b-fp32
```

mlx-community/bigcode-starcoder2-15b-fp32

The Model mlx-community/bigcode-starcoder2-15b-fp32 was converted to MLX format from bigcode/starcoder2-15b using mlx-lm version 0.21.1 by Focused.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/bigcode-starcoder2-15b-fp32")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Focused is a technology company at the forefront of AI-driven development, empowering organizations to unlock the full potential of artificial intelligence. From integrating innovative models into existing systems to building scalable, modern AI infrastructures, we specialize in delivering tailored, incremental solutions that meet you where you are. Curious how we can help with your AI next project? Get in Touch

Downloads last month: 44

MLX

Hardware compatibility

Quantized

Model tree for mlx-community/bigcode-starcoder2-15b-fp32

Base model

bigcode/starcoder2-15b

Finetuned

(20)

this model

Dataset used to train mlx-community/bigcode-starcoder2-15b-fp32

Evaluation results

pass@1 on CruxEval-I
self-reported

48.100
pass@1 on DS-1000
self-reported

33.800
accuracy on GSM8K (PAL)
self-reported

65.100
pass@1 on HumanEval+
self-reported

37.800
pass@1 on HumanEval
self-reported

46.300
edit-smiliarity on RepoBench-v1.1
self-reported

74.080