Instructions to use ayaderaghul/datascience-style-completion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayaderaghul/datascience-style-completion with Transformers:

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

pipe = pipeline("text-generation", model="ayaderaghul/datascience-style-completion")

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

tokenizer = AutoTokenizer.from_pretrained("ayaderaghul/datascience-style-completion")
model = AutoModelForCausalLM.from_pretrained("ayaderaghul/datascience-style-completion", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ayaderaghul/datascience-style-completion with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ayaderaghul/datascience-style-completion

SGLang

How to use ayaderaghul/datascience-style-completion 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 "ayaderaghul/datascience-style-completion" \
    --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": "ayaderaghul/datascience-style-completion",
		"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 "ayaderaghul/datascience-style-completion" \
        --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": "ayaderaghul/datascience-style-completion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ayaderaghul/datascience-style-completion with Docker Model Runner:
```
docker model run hf.co/ayaderaghul/datascience-style-completion
```

datascience-style-completion

Commit History

Apr 2, 2023

17:02
Adding `safetensors` variant of this model⁠

SFconvertbot

a1b420e

Mar 13, 2023

15:03
Update README.md

ayaderaghul

27b6e58

Mar 7, 2023

06:56
Create README.md

ayaderaghul

5bec932

Mar 5, 2023

10:05
Upload model

ayaderaghul

34768fb
09:17
Upload model

ayaderaghul

9c49979
09:07
Upload tokenizer.json

ayaderaghul

f9daee0
09:01
Upload model

ayaderaghul

79914af
09:01
Upload model

ayaderaghul

3daafa4
08:57
initial commit

ayaderaghul

37b7a95

Commit History

Apr 2, 2023

Adding `safetensors` variant of this model⁠

Mar 13, 2023

Update README.md

Mar 7, 2023

Create README.md

Mar 5, 2023

Upload model

Upload model

Upload tokenizer.json

Upload model

Upload model

initial commit