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

Libraries

How to use dphn/dolphincoder-starcoder2-15b with Transformers:

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

pipe = pipeline("text-generation", model="dphn/dolphincoder-starcoder2-15b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dphn/dolphincoder-starcoder2-15b")
model = AutoModelForCausalLM.from_pretrained("dphn/dolphincoder-starcoder2-15b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dphn/dolphincoder-starcoder2-15b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dphn/dolphincoder-starcoder2-15b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dphn/dolphincoder-starcoder2-15b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dphn/dolphincoder-starcoder2-15b

SGLang

How to use dphn/dolphincoder-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 "dphn/dolphincoder-starcoder2-15b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dphn/dolphincoder-starcoder2-15b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "dphn/dolphincoder-starcoder2-15b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dphn/dolphincoder-starcoder2-15b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dphn/dolphincoder-starcoder2-15b with Docker Model Runner:
```
docker model run hf.co/dphn/dolphincoder-starcoder2-15b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DolphinCoder StarCoder2 15b 🐬

Training

It took 3 days to train 3 epochs on 8x H100s using qLoRA and Axolotl

Prompt format: This model uses ChatML prompt format.

<|im_start|>system
You are DolphinCoder, a helpful AI programming assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Example:

<|im_start|>system
You are DolphinCoder, a master at software engineering and coding in any programming language.
<|im_start|>user
Please write me a program in golang that parses all the lines in a file, and reverses them character-wise, and saves it to a new file.
<|im_start|>assistant

Quantized models

Gratitude

This model was made possible by the generous sponsorship of latitude.sh.
Huge thank you to BigCode for training and publishing the weights of StarCoder2
HUGE Thank you to the dataset authors: @ise-uiuc, @teknium, @m-a-p
And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.