Instructions to use hpcgroup/hpc-coder-v2-16b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hpcgroup/hpc-coder-v2-16b with Transformers:

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

pipe = pipeline("text-generation", model="hpcgroup/hpc-coder-v2-16b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hpcgroup/hpc-coder-v2-16b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hpcgroup/hpc-coder-v2-16b", trust_remote_code=True)
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 hpcgroup/hpc-coder-v2-16b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hpcgroup/hpc-coder-v2-16b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hpcgroup/hpc-coder-v2-16b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hpcgroup/hpc-coder-v2-16b

SGLang

How to use hpcgroup/hpc-coder-v2-16b 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 "hpcgroup/hpc-coder-v2-16b" \
    --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": "hpcgroup/hpc-coder-v2-16b",
		"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 "hpcgroup/hpc-coder-v2-16b" \
        --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": "hpcgroup/hpc-coder-v2-16b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hpcgroup/hpc-coder-v2-16b with Docker Model Runner:
```
docker model run hf.co/hpcgroup/hpc-coder-v2-16b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

HPC-Coder-v2

The HPC-Coder-v2-16b model is an HPC code LLM fine-tuned on an instruction dataset catered to common HPC topics such as parallelism, optimization, accelerator porting, etc. This version is a fine-tuning of the Deepseek Coder V2 lite base model. It is fine-tuned on the hpc-instruct, oss-instruct, and evol-instruct datasets. We utilized the distributed training library AxoNN to fine-tune in parallel across many GPUs.

HPC-Coder-v2-1.3b, HPC-Coder-v2-6.7b, and HPC-Coder-v2-16b are the most capable open-source LLMs for parallel and HPC code generation. HPC-Coder-v2-16b is currently the best performing open-source LLM on the ParEval parallel code generation benchmark in terms of correctness and performance. It scores similarly to 34B and commercial models like Phind-V2 and GPT-4 on parallel code generation. HPC-Coder-v2-6.7b is not far behind the 16b in terms of performance.

Using HPC-Coder-v2

The model is provided as a standard huggingface model with safetensor weights. It can be used with transformers pipelines, vllm, or any other standard model inference framework. HPC-Coder-v2 is an instruct model and prompts need to be formatted as instructions for best results. It was trained with the following instruct template:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{instruction}

### Response: