From 905bfb16745ff4da1e15e6d6a1f5b889b9d0c30c Mon Sep 17 00:00:00 2001 From: Michael Feil <63565275+michaelfeil@users.noreply.github.com> Date: Sun, 12 Nov 2023 17:33:17 +0100 Subject: [PATCH] neural search: embedding inference, llm inference and trl (#454) * Update README.md * Update README.md --- README.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c7f916c6..0acb1650 100644 --- a/README.md +++ b/README.md @@ -474,7 +474,6 @@ This repository contains a curated list of awesome open source libraries that wi * [NMSLIB](https://github.com/nmslib/nmslib) ![](https://img.shields.io/github/stars/nmslib/nmslib.svg?style=social) - Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces. * [Qdrant](https://github.com/qdrant/qdrant) ![](https://img.shields.io/github/stars/qdrant/qdrant.svg?style=social) - An open source vector similarity search engine with extended filtering support. - ## Industry Strength CV * [Deep Lake](https://github.com/activeloopai/deeplake) ![](https://img.shields.io/github/stars/activeloopai/deeplake.svg?style=social) - Deep Lake is a data infrastructure optimized for computer vision. * [iGibson](https://github.com/StanfordVL/iGibson) ![](https://img.shields.io/github/stars/StanfordVL/iGibson.svg?style=social) - iGibson is a simulation environment providing fast visual rendering and physics simulation based on Bullet. @@ -517,6 +516,7 @@ This repository contains a curated list of awesome open source libraries that wi * [Tensorflow Lingvo](https://github.com/tensorflow/lingvo) ![](https://img.shields.io/github/stars/tensorflow/lingvo.svg?style=social) - A [framework](https://blog.tensorflow.org/2019/02/lingvo-tensorflow-framework-for-sequence-modeling.html) for building neural networks in Tensorflow, particularly sequence models. * [Tensorflow Text](https://github.com/tensorflow/text) ![](https://img.shields.io/github/stars/tensorflow/text.svg?style=social) - TensorFlow Text provides a collection of text related classes and ops ready to use with TensorFlow 2.0. * [Transformers](https://github.com/huggingface/transformers) ![](https://img.shields.io/github/stars/huggingface/transformers.svg?style=social) - Huggingface's library of state-of-the-art pretrained models for Natural Language Processing (NLP). +* [text-generation-inference](https://github.com/huggingface/text-generation-inference) ![](https://img.shields.io/github/stars/huggingface/text-generation-inference.svg?style=social) - Large Language Model Text Generation Inference under TFOIL license. * [trlX](https://github.com/CarperAI/trlx) ![](https://img.shields.io/github/stars/CarperAI/trlx.svg?style=social) - trlX is a distributed training framework designed from the ground up to focus on fine-tuning large language models with reinforcement learning using either a provided reward function or a reward-labeled dataset. * [YouTokenToMe](https://github.com/vkcom/youtokentome) ![](https://img.shields.io/github/stars/vkcom/youtokentome.svg?style=social) - YouTokenToMe is an unsupervised text tokenizer focused on computational efficiency. It currently implements fast [Byte Pair Encoding](https://arxiv.org/abs/1508.07909) (BPE). @@ -557,7 +557,7 @@ This repository contains a curated list of awesome open source libraries that wi * [Stable Baselines](https://github.com/DLR-RM/stable-baselines3) ![](https://img.shields.io/github/stars/DLR-RM/stable-baselines3.svg?style=social) - A fork of OpenAI Baselines, implementations of reinforcement learning algorithms. * [SuperSuit](https://github.com/Farama-Foundation/SuperSuit) ![](https://img.shields.io/github/stars/Farama-Foundation/SuperSuit.svg?style=social) - SuperSuit introduces a collection of small functions which can wrap reinforcement learning environments to do preprocessing ('microwrappers'). * [TF-Agents](https://github.com/tensorflow/agents) ![](https://img.shields.io/github/stars/tensorflow/agents.svg?style=social) - A reliable, scalable and easy to use TensorFlow library for contextual bandits and reinforcement learning. - +* [TRL](https://github.com/huggingface/trl) ![](https://img.shields.io/github/stars/huggingface/trl.svg?style=social) - Train transformer language models with reinforcement learning. ## Industry Strength Visualisation * [Altair](https://github.com/altair-viz/altair) - Altair is a declarative statistical visualization library for Python. @@ -640,6 +640,7 @@ This repository contains a curated list of awesome open source libraries that wi * [Fennel](https://fennel.ai/) - Realtime feature engineering platform for fast moving machine learning teams. Python / Pandas native, built in Rust. Easy to install/use/run, builds upon best practices for reducing data/feature quality issues, and keeps cloud spend low. Fully managed, zero ops. * [Fiddler](https://www.fiddler.ai/) - Fiddler is a model performance management platform that offers model monitoring, observability, explainability & fairness. * [Google Cloud Machine Learning Engine](https://cloud.google.com/ml-engine/) - Managed service that enables developers and data scientists to build and bring machine learning models to production. +* [Gradient](https://gradient.ai/) - Gradient offers fine-tuning as training and inference of LLM's as cloud infrastructure * [Graphsignal](https://graphsignal.com/) - Machine learning profiler that helps make model training and inference faster and more efficient. * [H2O Driverless AI](https://www.h2o.ai/products/h2o-driverless-ai/) - Automates key machine learning tasks, delivering automatic feature engineering, model validation, model tuning, model selection and deployment, machine learning interpretability, bring your own recipe, time-series and automatic pipeline generation for model scoring - [(Video)](https://www.youtube.com/watch?v=ZqCoFp3-rGc). * [Hugging Face](https://huggingface.co/) - Hugging Face is a platform that allows users to share machine learning models and datasets.