Instructions to use Jipski/MegStuart_gpt-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jipski/MegStuart_gpt-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jipski/MegStuart_gpt-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jipski/MegStuart_gpt-2") model = AutoModelForCausalLM.from_pretrained("Jipski/MegStuart_gpt-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Jipski/MegStuart_gpt-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jipski/MegStuart_gpt-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jipski/MegStuart_gpt-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jipski/MegStuart_gpt-2
- SGLang
How to use Jipski/MegStuart_gpt-2 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 "Jipski/MegStuart_gpt-2" \ --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": "Jipski/MegStuart_gpt-2", "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 "Jipski/MegStuart_gpt-2" \ --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": "Jipski/MegStuart_gpt-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jipski/MegStuart_gpt-2 with Docker Model Runner:
docker model run hf.co/Jipski/MegStuart_gpt-2
Commit History
-
Upload pytorch_model.bin with git-lfs
99b41e2 -
Upload training_args.bin with git-lfs
70daaa7 -
Upload config.json
9850fcc -
Delete config.json
4f6521a -
Delete pytorch_model.bin
0ab6445 -
Delete training_args.bin
74fb23e
-
Upload pytorch_model.bin with git-lfs
58e3bcd -
Upload training_args.bin with git-lfs
89e9c28 -
Upload config.json
4ba9531 -
Upload tokenizer.json
7a4c43e -
initial commit
63588a2