Falcon-7B Truss

This repository packages Falcon-7B as a Truss.

Falcon 7B is an LLM released by Technology Innovation Institute (TII).

Utilizing this model for inference can be challenging given the hardware requirements. With Baseten and Truss, inference is dead simple.

Deploying Falcon-7B

We found this model runs reasonably fast on A10Gs; you can configure the hardware you'd like in the config.yaml.

...
resources:
  cpu: "3"
  memory: 14Gi
  use_gpu: true
  accelerator: A10G
...

Before deployment:

Make sure you have a Baseten account and API key. You can sign up for a Baseten account here.
Install Truss and the Baseten Python client: pip install --upgrade baseten truss
Authenticate your development environment with baseten login

Deploying the Truss is easy; simply load it and push from a Python script:

import baseten
import truss

falcon_truss = truss.load('.')
baseten.deploy(falcon_truss)

Invoking Falcon-7B

The usual GPT-style parameters will pass right through to the inference point:

max_new_tokens (default: 64)
temperature (default: 0.5)
top_p (default: 0.9)
top_k (default: 0)
num_beams (default: 4)
do_sample (default: False)

Note that we recommend setting do_sample to True for best results, and increasing the max_new_tokens parameter to 200-300.

import baseten
model = baseten.deployed_model_id('YOUR MODEL ID')
model.predict({"prompt": "Write a movie plot about falcons planning to over the world", "do_sample": True, "max_new_tokens": 300})

You can also invoke your model via a REST API

curl -X POST " https://app.baseten.co/models/YOUR_MODEL_ID/predict" \
     -H "Content-Type: application/json" \
     -H 'Authorization: Api-Key {YOUR_API_KEY}' \
     -d '{
           "prompt": "Write a movie plot about falcons planning to over the world",
           "do_sample": True,
           "max_new_tokens": 300,
           "temperature": 0.3
         }'

kierisi/falcon-7b-truss

Falcon-7B Truss

Deploying Falcon-7B

Invoking Falcon-7B