Stars
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
An open-source NLP research library, built on PyTorch.
Build effective agents using Model Context Protocol and simple workflow patterns
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
An open-source framework for training large multimodal models.
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Entropy Based Sampling and Parallel CoT Decoding
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
[UNMAINTAINED] A reverse engineered Python API wrapper for Quora's Poe, which provides free access to ChatGPT, GPT-4, and Claude.
800,000 step-level correctness labels on LLM solutions to MATH problems
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
novel deep learning research works with PaddlePaddle
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Secrets of RLHF in Large Language Models Part I: PPO
Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
[CVPR 2021 Best Student Paper Honorable Mention, Oral] Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks.
A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
Implementation of https://srush.github.io/annotated-s4
Recognition to Cognition Networks (code for the model in "From Recognition to Cognition: Visual Commonsense Reasoning", CVPR 2019)
[ICML 2024] CLLMs: Consistency Large Language Models
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".