NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

Notes for Machine Learning Engineering for Production (MLOps) Specialization course by DeepLearning.AI & Andrew Ng

A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically Chat…

Let ChatGPT teach your own chatbot in hours with a single GPU!

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Instruct-tune LLaMA on consumer hardware

A library for efficient similarity search and clustering of dense vectors.

ACL'2021: Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

Code for our TACL-2022 paper.

code for the NAACL 2021 paper Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention by Microsoft Semantic Machines.

Data and Code for ICLR2020 Paper "TabFact: A Large-scale Dataset for Table-based Fact Verification"

Dataset and code for EMNLP2020 paper "HybridQA: A Dataset of Multi-Hop Question Answeringover Tabular and Textual Data"

Code for WACV 2021 Paper "Meta Module Network for Compositional Visual Reasoning"

Lucene open-domain QA retrieval in python

Implementation of the paper Tree Transformer

GloVe model for distributed word representation

Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation

Implementation of the ESIM model for natural language inference with PyTorch

Data and code for Natural Language Inference with Multiple Premises

Stopwords for 50 languages in JSON format