Instructions to use NovelAI/calliope-legacy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NovelAI/calliope-legacy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NovelAI/calliope-legacy")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NovelAI/calliope-legacy") model = AutoModelForCausalLM.from_pretrained("NovelAI/calliope-legacy") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use NovelAI/calliope-legacy with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NovelAI/calliope-legacy" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NovelAI/calliope-legacy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NovelAI/calliope-legacy
- SGLang
How to use NovelAI/calliope-legacy 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 "NovelAI/calliope-legacy" \ --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": "NovelAI/calliope-legacy", "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 "NovelAI/calliope-legacy" \ --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": "NovelAI/calliope-legacy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NovelAI/calliope-legacy with Docker Model Runner:
docker model run hf.co/NovelAI/calliope-legacy
Calliope (NovelAI Legacy Model)
A while ago, we retired our oldest model, Calliope, which was based on EleutherAI's GPT-Neo 2.7B. This model was our first step into finetuning large language models. We made some messes and learned a lot from the experience of creating her.
Right when NovelAI came out of its private alpha test, EleutherAI released GPT-J 6B, which was a much stronger model and became the basis of our Sigurd model, so Calliope barely had any time to shine and spent most of her time sitting unused in our model selection list.
After the release of Clio, Calliope wasn't even the fastest model anymore, so it became time to pull the plug and retire the model.
So now, for the sake of nostalgia, posterity, and historic preservation, we are releasing the weights of our Calliope model publicly on Huggingface Hub under the GPL-2.0 license.
You can find your very own Calliope right here where you are!
Art by @illustratesTarm
- Downloads last month
- 17

