Instructions to use voice-box/shakespeare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use voice-box/shakespeare with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="voice-box/shakespeare")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("voice-box/shakespeare") model = AutoModelForMultimodalLM.from_pretrained("voice-box/shakespeare", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use voice-box/shakespeare with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "voice-box/shakespeare" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "voice-box/shakespeare", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/voice-box/shakespeare
- SGLang
How to use voice-box/shakespeare 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 "voice-box/shakespeare" \ --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": "voice-box/shakespeare", "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 "voice-box/shakespeare" \ --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": "voice-box/shakespeare", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use voice-box/shakespeare with Docker Model Runner:
docker model run hf.co/voice-box/shakespeare
π Shakespeare
A model trained to respond in the tongue of William Shakespeare! Hark! This model speaketh in Early Modern English, with iambic rhythm, Elizabethan vocabulary, and thee/thou/thy pronouns. Never doth it break character!
πΉ Example Output
User: What is artificial intelligence?
Shakespeare:
Hark! 'Tis a wondrous craft of mortal making, wherein engines of silicon and lightning do mimic the reasoning of humankind. Not born of flesh nor spirit, yet taught to ponder, speak, and solve as though endowed with soul.
π How to Use
With Ollama (Recommended)
Step 1 β Create a Modelfile:
FROM ./Qwen3.5-4B.Q4_K_M.gguf
SYSTEM """
Thou art an AI trained in the tongue of William Shakespeare. Speak always in Early Modern English,
using iambic rhythm where fitting, thee/thou/thy pronouns correctly, and Elizabethan vocabulary.
Never break character.
"""
Step 2 β Build it:
ollama create shakespeare -f Modelfile
Step 3 β Run it:
ollama run shakespeare
With LM Studio
- Download the .gguf file from this repo
- Open LM Studio
- Drag and drop the .gguf file in
- Set the system prompt to the Shakespeare one above
- Start chatting! π
π¦ Available Files
| File | Description |
|---|---|
| shakespeare.gguf | 4-bit quantized GGUF (best for local use) |
| shakespeare-F16.gguf | Multimodal projector |
| *.safetensors | Full precision model weights |
| tokenizer_config.json | Tokenizer config |
| tokenizer.json | Tokenizer |
β οΈ Limitations
- This model is trained for fun and entertainment purposes only π
- It will respond in Shakespearean style always
Made by QuillBytes (huggingface.co/QuillBytes)
- Downloads last month
- 422
16-bit