A simulation evaluation platform for DROID

Efficient Triton Kernels for LLM Training

`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.

AI Logging for Interpretability and Explainability🔬

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Code and documentation to train Stanford's Alpaca models, and generate the data.

Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI

An open collection of implementation tips, tricks and resources for training large language models

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Generating Information-Seeking Conversations from Unlabeled Documents (EMNLP 2022).

Keep Me Updated! Memory Management in Long-term Conversations (Findings of EMNLP 2022)

Saving Dense Retriever from Shortcut Dependency in Conversational Search (EMNLP 2022)

Polyglot: Large Language Models of Well-balanced Competence in Multi-languages

COYO-700M: Large-scale Image-Text Pair Dataset

Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)

A latent text-to-image diffusion model

A library for building and serving multi-node distributed faiss indices.

Official Pytorch implementation of GGDR (ECCV 2022)

Repository for Realistic Blur Synthesis for Learning Image Deblurring

Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

PyTorch code for "Fine-grained Image Captioning with CLIP Reward" (Findings of NAACL 2022)

Korean Online That-gul Emotions Dataset