InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

RewardBench: the first evaluation tool for reward models.

Recipes to train reward model for RLHF.

Robust recipes to align language models with human and AI preferences

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Internship project

🦄 Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data for end-to-end AI benchmarking

Fast Inference Solutions for BLOOM

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

code for document level AMR representation and evaluation

Model parallel transformers in JAX and Haiku

Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…

BookNLP, a natural language processing pipeline for books

A Portal Site for Structured Knowledge Grounding(SKG) Resources.

[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models

Inference code for Llama models

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

Democratizing Internet-scale financial data.

FinRL®: Financial Reinforcement Learning. 🔥

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

DALL·E Mini - Generate images from a text prompt

GLIDE: a diffusion-based text-conditional image synthesis model

The official repository for EMNLP 2022 EnDex Paper

SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.

The Yahoo News Annotated Comments Corpus (YNACC)