Instructions to use sarthak-2002/MuskGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sarthak-2002/MuskGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sarthak-2002/MuskGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("sarthak-2002/MuskGPT") model = AutoModelForCausalLM.from_pretrained("sarthak-2002/MuskGPT") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sarthak-2002/MuskGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sarthak-2002/MuskGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sarthak-2002/MuskGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/sarthak-2002/MuskGPT
- SGLang
How to use sarthak-2002/MuskGPT 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 "sarthak-2002/MuskGPT" \ --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": "sarthak-2002/MuskGPT", "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 "sarthak-2002/MuskGPT" \ --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": "sarthak-2002/MuskGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use sarthak-2002/MuskGPT with Docker Model Runner:
docker model run hf.co/sarthak-2002/MuskGPT
Commit ·
5607fa5
1
Parent(s): f648b09
Create README.md
Browse filesFinetuned GPT2 model, using Elon Musk's tweet dataset from Kaggle. Given few initial words of the tweet the model will generate the text as if entire tweet was written by Elon Musk.