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

Libraries

How to use codeparrot/starcoder-self-instruct with Transformers:

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

pipe = pipeline("text-generation", model="codeparrot/starcoder-self-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codeparrot/starcoder-self-instruct")
model = AutoModelForCausalLM.from_pretrained("codeparrot/starcoder-self-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codeparrot/starcoder-self-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/codeparrot/starcoder-self-instruct

SGLang

How to use codeparrot/starcoder-self-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 "codeparrot/starcoder-self-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": "codeparrot/starcoder-self-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 "codeparrot/starcoder-self-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": "codeparrot/starcoder-self-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codeparrot/starcoder-self-instruct with Docker Model Runner:
```
docker model run hf.co/codeparrot/starcoder-self-instruct
```

ArmelR commited on Jun 13, 2023

Commit

b121cbd

1 Parent(s): 77cb69f

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -30,7 +30,9 @@ input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"]
 completion = model.generate(input_ids, max_length=200)
 print(tokenizer.batch_decode(completion[:,input_ids.shape[1]:])[0])
 ```
- ## More information
 For additional information, check
 - [self-intruct-starcoder](https://huggingface.co/codeparrot/self-instruct-starcoder)
 - [starcoder](https://huggingface.co/bigcode/starcoder)

 completion = model.generate(input_ids, max_length=200)
 print(tokenizer.batch_decode(completion[:,input_ids.shape[1]:])[0])
 ```
+## More information
 For additional information, check
 - [self-intruct-starcoder](https://huggingface.co/codeparrot/self-instruct-starcoder)
 - [starcoder](https://huggingface.co/bigcode/starcoder)