Skip to main content

A hybrid chatbot - LLM side.

Project description

WAFL-llm

WAFL is built to run as a two-part system. Both can be installed on the same machine. This is the LLM side of the WAFL project.

The two parts of WAFL

LLM side (needs a GPU)

This is a model server for the speech-to-text model, the LLM, the embedding system, and the text-to-speech model.

Installation

In order to quickly run the LLM side, you can use the following installation commands:

pip install wafl-llm
wafl-llm start

which will use the default models and start the server on port 8080.

The installation will require MPI and Java installed on the system. One can install both with the following commands

sudo apt install libopenmpi-dev
sudo apt install default-jdk

Configuration

A use-case specific configuration can be set by creating a config.json file in the path where wafl-llm start is executed. The file should look like this (the default configuration)

{
  "llm_model": "mistralai/Mistral-7B-Instruct-v0.1",
  "speaker_model": "facebook/fastspeech2-en-ljspeech",
  "whisper_model": "fractalego/personal-whisper-distilled-model",
  "sentence_embedder_models": "TaylorAI/gte-tiny"
}

The models are downloaded from the HugggingFace repository. Any other compatible model should work.

Docker

A docker image can be used to run it as in the following:

$ docker run -p8080:8080 --env NVIDIA_DISABLE_REQUIRE=1 --gpus all fractalego/wafl-llm:latest

or one can clone this repository and run the following

docker/build.sh
docker run -p8080:8080 --env NVIDIA_DISABLE_REQUIRE=1 --gpus all wafl-llm

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

wafl_llm-0.0.83-py3-none-any.whl (9.1 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page