Instructions to use amazon/FalconLite2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amazon/FalconLite2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="amazon/FalconLite2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("amazon/FalconLite2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use amazon/FalconLite2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "amazon/FalconLite2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "amazon/FalconLite2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/amazon/FalconLite2
- SGLang
How to use amazon/FalconLite2 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 "amazon/FalconLite2" \ --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": "amazon/FalconLite2", "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 "amazon/FalconLite2" \ --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": "amazon/FalconLite2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use amazon/FalconLite2 with Docker Model Runner:
docker model run hf.co/amazon/FalconLite2
Can't run on SageMaker with TGI
#4
by dpr882 - opened
While the README mentions that it can be used with TGI container in reality the notebook uses a custom ECR image, prob based on TGI.
But
- there's no visibility on that container image or where it's hosted
- couldn't get it to run on sagemaker with custom container: permissions errorsa and really don't see where this image is hosted so which account id to be used.
not great that an amazon model can't be ran on AWS Sagemaker simply with TGI
Hi @dpr882 Thanks for your interest!
To deploy on Sagemaker, pls refer to this notebook. https://github.com/awslabs/extending-the-context-length-of-open-source-llms/blob/main/falconlite2-tgi1.1.0/sm_deploy.ipynb Thank you!