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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigcode/starcoder2-15b")
model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-15b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

starcoder2-15b

Commit History

Jun 5, 2024

19:50
Update values of `bos_token_id` and `eos_token_id` in generation_config.json⁠

regisss HF Staff

Verified signature
18bfb01

Mar 6, 2024

16:55
change widget inference parameters

loubnabnl HF Staff

Verified signature
995200d

Mar 4, 2024

13:32
add dropout (#13)⁠

lvwerra +1: loubnabnl HF Staff

Verified signature
acfb201
13:17
Update config.json (#9)⁠

loubnabnl +1: muhtasham HF Staff

Verified signature
1dab6bb

Mar 1, 2024

14:33
fix paper (#7)⁠

loubnabnl HF Staff

Verified signature
d020785

Feb 28, 2024

15:59
Fix table of contents (#4)⁠

loubnabnl +1: mishig HF Staff

Verified signature
c78f7e5
12:34
Update README.md

lvwerra HF Staff

Verified signature
e18a21d

Feb 27, 2024

23:31
NVIDIA framework and contribution updates. (#3)⁠

lvwerra +1: Criztov HF Staff

Verified signature
b1bcca5
23:28
Update README.md (#2)⁠

loubnabnl +1: lvwerra HF Staff

Verified signature
1c2dae0
15:35
add model

loubnabnl HF Staff

56438be
11:40
fix model name

loubnabnl HF Staff

Verified signature
cb14254
11:06
fix typos

loubnabnl HF Staff

Verified signature
eaa8ac9
08:54
Update README.md (#1)⁠

lvwerra +1: loubnabnl HF Staff

Verified signature
5c5e0d3

Feb 20, 2024

17:58
initial commit

lvwerra HF Staff

Verified signature
44b897e

Commit History

Jun 5, 2024

Update values of `bos_token_id` and `eos_token_id` in generation_config.json⁠

Mar 6, 2024

change widget inference parameters

Mar 4, 2024

add dropout (#13)⁠

Update config.json (#9)⁠

Mar 1, 2024

fix paper (#7)⁠

Feb 28, 2024

Fix table of contents (#4)⁠

Update README.md

Feb 27, 2024

NVIDIA framework and contribution updates. (#3)⁠

Update README.md (#2)⁠

add model

fix model name

fix typos

Update README.md (#1)⁠

Feb 20, 2024

initial commit