Instructions to use mlx-community/starcoder2-15b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/starcoder2-15b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/starcoder2-15b-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/starcoder2-15b-4bit")
model = AutoModelForCausalLM.from_pretrained("mlx-community/starcoder2-15b-4bit")

MLX

How to use mlx-community/starcoder2-15b-4bit 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/starcoder2-15b-4bit")

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/starcoder2-15b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/starcoder2-15b-4bit"
# 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/starcoder2-15b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlx-community/starcoder2-15b-4bit

SGLang

How to use mlx-community/starcoder2-15b-4bit 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/starcoder2-15b-4bit" \
    --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/starcoder2-15b-4bit",
		"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/starcoder2-15b-4bit" \
        --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/starcoder2-15b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use mlx-community/starcoder2-15b-4bit 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/starcoder2-15b-4bit" --prompt "Once upon a time"

Docker Model Runner
How to use mlx-community/starcoder2-15b-4bit with Docker Model Runner:
```
docker model run hf.co/mlx-community/starcoder2-15b-4bit
```

starcoder2-15b-4bit / README.md

muhtasham

Upload folder using huggingface_hub

f3b6d56 verified about 2 years ago

preview code

raw

history blame contribute delete

1.65 kB

	---
	license: bigcode-openrail-m
	library_name: transformers
	tags:
	- code
	- mlx
	datasets:
	- bigcode/the-stack-v2-train
	pipeline_tag: text-generation
	inference: true
	widget:
	- text: 'def print_hello_world():'
	example_title: Hello world
	group: Python
	model-index:
	- name: starcoder2-15b
	results:
	- task:
	type: text-generation
	dataset:
	name: CruxEval-I
	type: cruxeval-i
	metrics:
	- type: pass@1
	value: 48.1
	- task:
	type: text-generation
	dataset:
	name: DS-1000
	type: ds-1000
	metrics:
	- type: pass@1
	value: 33.8
	- task:
	type: text-generation
	dataset:
	name: GSM8K (PAL)
	type: gsm8k-pal
	metrics:
	- type: accuracy
	value: 65.1
	- task:
	type: text-generation
	dataset:
	name: HumanEval+
	type: humanevalplus
	metrics:
	- type: pass@1
	value: 37.8
	- task:
	type: text-generation
	dataset:
	name: HumanEval
	type: humaneval
	metrics:
	- type: pass@1
	value: 46.3
	- task:
	type: text-generation
	dataset:
	name: RepoBench-v1.1
	type: repobench-v1.1
	metrics:
	- type: edit-smiliarity
	value: 74.08
	---

	# mlx-community/starcoder2-15b-4bit
	This model was converted to MLX format from [`bigcode/starcoder2-15b`]().
	Refer to the [original model card](https://huggingface.co/bigcode/starcoder2-15b) for more details on the model.
	## Use with mlx

	```bash
	pip install mlx-lm
	```

	```python
	from mlx_lm import load, generate

	model, tokenizer = load("mlx-community/starcoder2-15b-4bit")
	response = generate(model, tokenizer, prompt="hello", verbose=True)
	```