Instructions to use onekq-ai/starcoder2-3b-instruct-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onekq-ai/starcoder2-3b-instruct-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="onekq-ai/starcoder2-3b-instruct-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("onekq-ai/starcoder2-3b-instruct-v0.1")
model = AutoModelForCausalLM.from_pretrained("onekq-ai/starcoder2-3b-instruct-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use onekq-ai/starcoder2-3b-instruct-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "onekq-ai/starcoder2-3b-instruct-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onekq-ai/starcoder2-3b-instruct-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/onekq-ai/starcoder2-3b-instruct-v0.1

SGLang

How to use onekq-ai/starcoder2-3b-instruct-v0.1 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 "onekq-ai/starcoder2-3b-instruct-v0.1" \
    --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": "onekq-ai/starcoder2-3b-instruct-v0.1",
		"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 "onekq-ai/starcoder2-3b-instruct-v0.1" \
        --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": "onekq-ai/starcoder2-3b-instruct-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use onekq-ai/starcoder2-3b-instruct-v0.1 with Docker Model Runner:
```
docker model run hf.co/onekq-ai/starcoder2-3b-instruct-v0.1
```

Starcoder2-3b finetuned the same way as https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 using https://huggingface.co/datasets/bigcode/self-oss-instruct-sc2-exec-filter-50k

Epochs: 1
Learning Rate: 0.0001
Lora Rank: 8
Batch Size: 16
Evaluation Split: 0

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for onekq-ai/starcoder2-3b-instruct-v0.1

Base model

bigcode/starcoder2-3b

Finetuned

(50)

this model

onekq-ai
/

starcoder2-3b-instruct-v0.1

Model tree for onekq-ai/starcoder2-3b-instruct-v0.1

Dataset used to train onekq-ai/starcoder2-3b-instruct-v0.1