Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

All Python solutions for Leetcode

PyTorch code for System-1.x: Learning to Balance Fast and Slow Planning with Language Models

Lean 4 programming language and theorem prover

Lifelong Learning In Context

[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step

A PyTorch Native LLM Training Framework

pytrec_eval is an Information Retrieval evaluation tool for Python, based on the popular trec_eval.

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

[ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Mosaic IT: Enhancing Instruction Tuning with Data Mosaics

Chat凉宫春日, An open sourced Role-Playing chatbot Cheng Li, Ziang Leng, and others.

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Recipes to train reward model for RLHF.

A quick guide (especially) for trending instruction finetuning datasets

Generate multi-round conversation roleplay data based on self-instruct and evol-instruct.

Based on the Evol-character framework and OpenAI API, enabling fine-grained role-playing data generation 🎭🧩.

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

self-adaptive in-context learning

Curate better data for LLMs

Data Valuation on In-Context Examples (ACL23)

1-Click is all you need.

LLM Frontend for Power Users.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.