Instructions to use tiiuae/falcon-11B-vlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiiuae/falcon-11B-vlm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="tiiuae/falcon-11B-vlm")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("tiiuae/falcon-11B-vlm") model = AutoModelForImageTextToText.from_pretrained("tiiuae/falcon-11B-vlm") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tiiuae/falcon-11B-vlm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tiiuae/falcon-11B-vlm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tiiuae/falcon-11B-vlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tiiuae/falcon-11B-vlm
- SGLang
How to use tiiuae/falcon-11B-vlm 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 "tiiuae/falcon-11B-vlm" \ --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": "tiiuae/falcon-11B-vlm", "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 "tiiuae/falcon-11B-vlm" \ --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": "tiiuae/falcon-11B-vlm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tiiuae/falcon-11B-vlm with Docker Model Runner:
docker model run hf.co/tiiuae/falcon-11B-vlm
Working requirements.txt
1
#7 opened over 1 year ago
by
Dinura
Sample Script Here
1
#6 opened almost 2 years ago
by
ctranslate2-4you
Error in running the code
#5 opened almost 2 years ago
by
Uzair121
Sharing of vlm finetune datasets?
#4 opened almost 2 years ago
by
lqniu
gguf quantization
#3 opened almost 2 years ago
by
rzabounidis