Instructions to use maettubfh/puzzle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maettubfh/puzzle with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="maettubfh/puzzle")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("maettubfh/puzzle") model = AutoModelForCausalLM.from_pretrained("maettubfh/puzzle") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use maettubfh/puzzle with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "maettubfh/puzzle" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maettubfh/puzzle", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/maettubfh/puzzle
- SGLang
How to use maettubfh/puzzle 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 "maettubfh/puzzle" \ --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": "maettubfh/puzzle", "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 "maettubfh/puzzle" \ --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": "maettubfh/puzzle", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use maettubfh/puzzle with Docker Model Runner:
docker model run hf.co/maettubfh/puzzle
Model Card for Model ID
This model is part of the latent space puzzle. It cannot be used for any real purpose, therefore a model card is omitted. It's up to you to find out what it does and how to use it. Good luck!
It's a fine-tuned version of https://huggingface.co/openai-community/gpt2.
Loading the model and tokenizer:
model = GPT2LMHeadModel.from_pretrained("maettubfh/puzzle")
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
- Downloads last month
- 1