BatsResearch / bonito
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
☆692Updated last month
Related projects ⓘ
Alternatives and complementary repositories for bonito
- Generative Representational Instruction Tuning☆562Updated this week
- [NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models☆531Updated last week
- Automated Evaluation of RAG Systems☆479Updated this week
- Evaluate your LLM's response with Prometheus and GPT4 💯☆794Updated 2 months ago
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,042Updated this week
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval☆942Updated 2 months ago
- Fine-Tuning Embedding for RAG with Synthetic Data☆468Updated last year
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆476Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆1,612Updated this week
- ☆445Updated last week
- Framework for enhancing LLMs for RAG tasks using fine-tuning.☆502Updated 3 weeks ago
- Easily embed, cluster and semantically label text datasets☆459Updated 7 months ago
- Code for Quiet-STaR☆639Updated 2 months ago
- Automatically evaluate your LLMs in Google Colab☆556Updated 6 months ago
- ☆705Updated last month
- Official repository for ORPO☆420Updated 5 months ago
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆838Updated 3 months ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆401Updated 2 months ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆1,551Updated 2 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆667Updated 6 months ago
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆881Updated 2 weeks ago
- Open-source tool to visualise your RAG 🔮☆1,083Updated 7 months ago
- Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding☆324Updated 9 months ago
- ☆796Updated 2 weeks ago
- In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.☆383Updated 8 months ago
- Efficient Retrieval Augmentation and Generation Framework☆1,328Updated this week
- RAGChecker: A Fine-grained Framework For Diagnosing RAG☆528Updated last month
- A tool for generating function arguments and choosing what function to call with local LLMs☆338Updated 7 months ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆327Updated 4 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆787Updated last week