How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
1. STaR 2. Mesh Transformer JAX 1. Updates 3. Pretrained Models 1. GPT-J-6B 1. Links 2. Acknowledgments 3. License 4. Model Details 5. Zero-Shot Evaluations 4. Architecture and Usage 1. Fine-tuning 2. JAX Dependency 5. TODO
Open-Instruct is a distributed training and instruction tuning framework for large language models. It functions as a coordinator for supervised fine-tuning, reinforcement learning from human feedback pipelines, and tool-use training, providing specialized roles for dataset curation and model alignment. The project distinguishes itself through a high-performance training architecture that utilizes actor-based distributed coordination and hybrid sharding to manage large GPU clusters. It implements advanced alignment techniques including direct preference optimization, group relative policy opt
This repository contains the code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing" (EMNLP 2024).
The main features of sparkjiao/dpo-trajectory-reasoning are: Single Agent Optimization.
Projects with overlapping indexed features include: chengpengli1003/cort. chengsong-huang/r-zero — Check out our paper or webpage for the details. ezelikman/star — 1. STaR 2. Mesh Transformer JAX 1. Updates 3. Pretrained Models 1. GPT-J-6B 1. Links 2. Acknowledgments 3. License 4.… hkust-nlp/mstar — :star: Project Page . iamhankai/forest-of-thought — Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning. allenai/open-instruct — Open-Instruct is a distributed training and instruction tuning framework for large language models. It functions as a…
