Instructions to use GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct with Transformers:

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

pipe = pipeline("text-generation", model="GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct")
model = AutoModelForCausalLM.from_pretrained("GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct

SGLang

How to use GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct 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 "GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct" \
    --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": "GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct",
		"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 "GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct" \
        --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": "GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct with Docker Model Runner:
```
docker model run hf.co/GeorgiaTechResearchInstitute/starcoder-gpteacher-code-instruct
```

Fp16 version

by aseok - opened May 29, 2023

Discussion

aseok

May 29, 2023

Hi.
Please also add fp16 version to reduce size.

blair-johnson

Georgia Tech Research Institute org Jun 12, 2023

•

edited Jun 12, 2023

At some point, we plan to update our model repos to safetensor format. I'll update this model to fp16 when we do that.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment