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
Falcon breaks after the second prompt of code.
#86
by thecowmilk - opened
Hello, I don't know if this is the right place to address this issue, however I want to report a break of Falcon that I have noticed it even before.
I prompted Falcon a code and at first everything is okay but if you prompt again it will break. Here's an example:
= : /*.
The = : //, with a random to 2 with. = //the good luck{ //, (TopApp: // //'s}
The issue, and = }
It is not //.
The code:
<h
It is not //.
You can you may be stored in// +1 and = //, = (TopAppCompos, //, and = (this. = //, and color```
You can // this.
It is not //.
The following code to: = //, and color```
There are some suggestions this is not designed to be the with a material= (with the given, we do will also has a// = = == //with the following, where What's(
this.addition = (TopApp: // = // this.display(this. = //, and its just as //'s own{ this.
To summarize the number of a minimum {
with:
<p> = (TopApp: = (Top.is a, = // this.addition and the = = = (with = // this.add(this.1= = //This is the color = // and also, = = // User, //.
In this.getElements= = = = = //, = = = //in this=, and its own=>> = // =, and= = = = = = = = =.
} = = = = = = = = = on= = (top = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =.is = = = = = = = = = = = =, = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = the app = = // this. = = = = = = = = = = = = = = = = = = = new and the user= the following: = = = = = = = : the following code, = = = = = = =, = = = = the best, the element =.show a and=. = = = = = (Top. = = = ( = = = = (Cd = = = = = = = = = = = = = = = = "app</sds. = = = = = = = = = = = = = = = = /3.dressed// The reason+ = = = = = = = = = = = = = = = = = = //d = = = = = = // =.user = = = = = = = = = " can be used to, = = =