Instructions to use tiiuae/falcon-40b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tiiuae/falcon-40b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tiiuae/falcon-40b", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-40b", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-40b", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tiiuae/falcon-40b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tiiuae/falcon-40b" # 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-40b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tiiuae/falcon-40b
- SGLang
How to use tiiuae/falcon-40b 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-40b" \ --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-40b", "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-40b" \ --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-40b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tiiuae/falcon-40b with Docker Model Runner:
docker model run hf.co/tiiuae/falcon-40b
Prevent Hallucinations
#74
by Zhaoqiong - opened
I am using falcon model to build a knowledge bot. But I find it will always answer the question even it's irrelevant to the given document, and I think it generates the response based on the basic knowledge it learn from training set. Any idea to prevent this phenomenon and just answer question based on given context?
I have found that by appending the sentence "Only respond if the answer is contained in the text above." to the question it will sometimes respect this directive, but not consistently enough for this to be a viable option.