Instructions to use hpcgroup/hpc-coder-v2-6.7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hpcgroup/hpc-coder-v2-6.7b with Transformers:

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

pipe = pipeline("text-generation", model="hpcgroup/hpc-coder-v2-6.7b")

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

tokenizer = AutoTokenizer.from_pretrained("hpcgroup/hpc-coder-v2-6.7b")
model = AutoModelForCausalLM.from_pretrained("hpcgroup/hpc-coder-v2-6.7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hpcgroup/hpc-coder-v2-6.7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hpcgroup/hpc-coder-v2-6.7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hpcgroup/hpc-coder-v2-6.7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hpcgroup/hpc-coder-v2-6.7b

SGLang

How to use hpcgroup/hpc-coder-v2-6.7b 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-v2-6.7b" \
    --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": "hpcgroup/hpc-coder-v2-6.7b",
		"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 "hpcgroup/hpc-coder-v2-6.7b" \
        --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": "hpcgroup/hpc-coder-v2-6.7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hpcgroup/hpc-coder-v2-6.7b with Docker Model Runner:
```
docker model run hf.co/hpcgroup/hpc-coder-v2-6.7b
```

daniellnichols commited on Nov 13, 2024

Commit

eaf4335

verified ·

1 Parent(s): 4562eaf

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -21,9 +21,10 @@ This version is a fine-tuning of the [Deepseek Coder 6.7b](https://huggingface.c
 It is fine-tuned on the [hpc-instruct](https://huggingface.co/datasets/hpcgroup/hpc-instruct), [oss-instruct](https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K), and [evol-instruct](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) datasets.
 We utilized the distributed training library [AxoNN](https://github.com/axonn-ai/axonn) to fine-tune in parallel across many GPUs.
-[HPC-Coder-v2-1.3b](https://huggingface.co/hpcgroup/hpc-coder-v2-1.3b) and HPC-Coder-v2-6.7b are two of the most capable open-source LLMs for parallel and HPC code generation.
-HPC-Coder-v2-6.7b is the best performing LLM under 30b parameters on the [ParEval](https://github.com/parallelcodefoundry/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.
 ## Using HPC-Coder-v2

 It is fine-tuned on the [hpc-instruct](https://huggingface.co/datasets/hpcgroup/hpc-instruct), [oss-instruct](https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K), and [evol-instruct](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) datasets.
 We utilized the distributed training library [AxoNN](https://github.com/axonn-ai/axonn) to fine-tune in parallel across many GPUs.
+[HPC-Coder-v2-1.3b](https://huggingface.co/hpcgroup/hpc-coder-v2-1.3b), [HPC-Coder-v2-6.7b](https://huggingface.co/hpcgroup/hpc-coder-v2-6.7b), and [HPC-Coder-v2-16b](https://huggingface.co/hpcgroup/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](https://github.com/parallelcodefoundry/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