Instructions to use BatsResearch/bonito-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BatsResearch/bonito-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BatsResearch/bonito-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BatsResearch/bonito-v1") model = AutoModelForCausalLM.from_pretrained("BatsResearch/bonito-v1") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BatsResearch/bonito-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BatsResearch/bonito-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BatsResearch/bonito-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BatsResearch/bonito-v1
- SGLang
How to use BatsResearch/bonito-v1 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 "BatsResearch/bonito-v1" \ --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": "BatsResearch/bonito-v1", "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 "BatsResearch/bonito-v1" \ --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": "BatsResearch/bonito-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BatsResearch/bonito-v1 with Docker Model Runner:
docker model run hf.co/BatsResearch/bonito-v1
What is the template used in bonito-v1?
Hi! Awesome work on Bonito!
I converted bonito-v1 into GGUF(https://huggingface.co/pacozaa/bonito-gguf) and quantize it using llama.cpp, I would like to run the model using Ollama. Is there any template I should use?
Cheers!
I know this discussion has been closed already, but can we add this snippet from the GitHub discussion / paper in the model description card? Thanks!
<|tasktype|>
Yes-no question answering
<|context|>
Zinedine Zidane -- After retiring as a player, Zidane
transitioned into coaching, becoming assistant coach at
Real Madrid… after the victory, he resigned as Real
Madrid coach.
<|task|>
I shared the my discovery and ollama template here https://medium.com/@sarinsuriyakoon/convert-pytorch-model-to-quantize-gguf-to-run-on-ollama-5c5dbc458208
Thank you for the request. I will add the template to the model card description.