Instructions to use Michael711/feinschwarz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Michael711/feinschwarz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Michael711/feinschwarz")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Michael711/feinschwarz") model = AutoModelForCausalLM.from_pretrained("Michael711/feinschwarz") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Michael711/feinschwarz with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Michael711/feinschwarz" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Michael711/feinschwarz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Michael711/feinschwarz
- SGLang
How to use Michael711/feinschwarz 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 "Michael711/feinschwarz" \ --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": "Michael711/feinschwarz", "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 "Michael711/feinschwarz" \ --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": "Michael711/feinschwarz", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Michael711/feinschwarz with Docker Model Runner:
docker model run hf.co/Michael711/feinschwarz
feinschwarz
This model is a fine-tuned version of dbmdz/german-gpt2. The dataset was compiled from all texts of https://www.feinschwarz.net (as of October 2021). The homepage gathers essayistic texts on theological topics.
The model will be used to explore the challenges of text-generating AI for theology with a hands on approach. Can an AI generate theological knowledge? Is a text by Karl Rahner of more value than an AI-generated text? Can we even distinguish a Rahner text from an AI-generated text in the future? And the crucial question: Would it be bad if not?
The model is a very first attempt and in its current version certainly not yet a danger for academic theology 🤓
Using the model
You can create text with the model using this code:
from transformers import pipeline
pipe = pipeline('text-generation', model="Michael711/feinschwarz",
tokenizer="Michael711/feinschwarz")
text = pipe("Der Sinn des Lebens ist es", max_length=100)[0]["generated_text"]
print(text)
Have fun theologizing!
- Downloads last month
- 6