BatsResearch / bonito
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
☆701Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for bonito
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆1,647Updated this week
- Evaluate your LLM's response with Prometheus and GPT4 💯☆798Updated 2 months ago
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆495Updated 2 weeks ago
- Fine-Tuning Embedding for RAG with Synthetic Data☆469Updated last year
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆850Updated 3 months ago
- ☆722Updated 2 months ago
- ☆453Updated this week
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval☆969Updated 2 months ago
- Automated Evaluation of RAG Systems☆486Updated 2 weeks ago
- [NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models☆535Updated 3 weeks ago
- Framework for enhancing LLMs for RAG tasks using fine-tuning.☆505Updated this week
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,098Updated last week
- RAGChecker: A Fine-grained Framework For Diagnosing RAG☆549Updated last month
- Easily embed, cluster and semantically label text datasets☆463Updated 7 months ago
- This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai,…☆1,840Updated 5 months ago
- Generative Representational Instruction Tuning☆567Updated this week
- Official repository for ORPO☆421Updated 5 months ago
- [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge a…☆1,401Updated 3 months ago
- Efficient Retrieval Augmentation and Generation Framework☆1,348Updated last week
- Automatically evaluate your LLMs in Google Colab☆559Updated 6 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆677Updated 7 months ago
- ☆801Updated 3 weeks ago
- A library for easily merging multiple LLM experts, and efficiently train the merged LLM.☆408Updated 2 months ago
- ☆529Updated 2 months ago
- Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhan…☆498Updated 6 months ago
- NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRav…☆308Updated last year
- Code for Quiet-STaR☆653Updated 3 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆813Updated this week
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆886Updated last month
- Code for explaining and evaluating late chunking (chunked pooling)☆248Updated last month