Instructions to use johnpaulbin/gpt2-skript-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use johnpaulbin/gpt2-skript-base with Transformers:

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

pipe = pipeline("text-generation", model="johnpaulbin/gpt2-skript-base")

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

tokenizer = AutoTokenizer.from_pretrained("johnpaulbin/gpt2-skript-base")
model = AutoModelForCausalLM.from_pretrained("johnpaulbin/gpt2-skript-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use johnpaulbin/gpt2-skript-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "johnpaulbin/gpt2-skript-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "johnpaulbin/gpt2-skript-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/johnpaulbin/gpt2-skript-base

SGLang

How to use johnpaulbin/gpt2-skript-base 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 "johnpaulbin/gpt2-skript-base" \
    --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": "johnpaulbin/gpt2-skript-base",
		"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 "johnpaulbin/gpt2-skript-base" \
        --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": "johnpaulbin/gpt2-skript-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use johnpaulbin/gpt2-skript-base with Docker Model Runner:
```
docker model run hf.co/johnpaulbin/gpt2-skript-base
```

gpt2-skript-base

Commit History

Aug 27, 2023

16:27
Adding `safetensors` variant of this model⁠

SFconvertbot

2890116

Jul 15, 2021

07:14
Update README.md

johnpaulbin

955b8bf
06:57
Update README.md

johnpaulbin

2cbb37d
06:50
Update README.md

johnpaulbin

0c631ac
06:49
Add pretrained model

johnpaulbin

baa316f
06:46
initial commit

system HF Staff

3205089

Commit History

Aug 27, 2023

Adding `safetensors` variant of this model⁠

Jul 15, 2021

Update README.md

Update README.md

Update README.md

Add pretrained model

initial commit