Instructions to use tiiuae/falcon-40b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiiuae/falcon-40b-instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tiiuae/falcon-40b-instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-40b-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-40b-instruct", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tiiuae/falcon-40b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiiuae/falcon-40b-instruct"
# 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-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tiiuae/falcon-40b-instruct

SGLang

How to use tiiuae/falcon-40b-instruct 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-instruct" \
    --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-instruct",
		"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-instruct" \
        --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-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tiiuae/falcon-40b-instruct with Docker Model Runner:
```
docker model run hf.co/tiiuae/falcon-40b-instruct
```

Getting "trust_remote_code" Error when Running SageMaker Deploy Code Sample

#27

by garystafford - opened Jun 4, 2023

Discussion

garystafford

Jun 4, 2023

•

edited Jun 4, 2023

When deploying the model to Amazon SageMaker using the supplied code in the Deploy tab I am getting the following error, on the predictor.predict call:

ModelError: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{
  "code": 400,
  "type": "InternalServerException",
  "message": "Loading /.sagemaker/mms/models/tiiuae__falcon-40b-instruct requires you to execute the configuration file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option `trust_remote_code\u003dTrue` to remove this error."
}

Shridharalve

Jun 5, 2023

•

edited Jun 5, 2023

You can use this in your model_fn function in inference.py

tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-40b-instruct")
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-40b-instruct", trust_remote_code=True,torch_dtype=torch.bfloat16, device_map="auto")

martin-holste

Jun 6, 2023

I'm struggling with this as well. In Sagemaker Studio, I have created a file code/inference.py, and put in it:

from transformers import pipeline
def model_fn(model_dir):
    tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-40b-instruct")
    model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-40b-instruct", trust_remote_code=True,torch_dtype=torch.bfloat16, device_map="auto")

    return pipeline(
        "question-answering",
        model=model,
        tokenizer=tokenizer,
        torch_dtype="auto",
        trust_remote_code=True,
        device_map="auto",
        )

But I continue to get the error regarding "trust_remote_code." Can someone please explain a bit more on exactly what is required to get falcon to work as a Sagemaker endpoint? I'd really appreciate it.

Shridharalve

Jun 8, 2023

@martin-holste @garystafford

Here's the guide by Phil Schmid to deploy this model on sage maker... Works like a charm

https://www.philschmid.de/sagemaker-falcon-llm

FalconLLM changed discussion status to closed Jun 9, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment