Instructions to use babylm/git-2024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use babylm/git-2024 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="babylm/git-2024", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("babylm/git-2024", trust_remote_code=True) model = AutoModelForImageTextToText.from_pretrained("babylm/git-2024", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use babylm/git-2024 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "babylm/git-2024" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "babylm/git-2024", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/babylm/git-2024
- SGLang
How to use babylm/git-2024 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 "babylm/git-2024" \ --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": "babylm/git-2024", "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 "babylm/git-2024" \ --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": "babylm/git-2024", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use babylm/git-2024 with Docker Model Runner:
docker model run hf.co/babylm/git-2024
Commit History
minor fix for config class bb62585
Chengxu Zhuang commited on
add support for sequence classification 2cd6995 verified
model for new text data and tokenizer 0e6cae6
Chengxu Zhuang commited on
add LICENSE cbef2db
Chengxu Zhuang commited on
add processor json 5bb740a
Chengxu Zhuang commited on
model upload dbddb9a
Chengxu Zhuang commited on