BatsResearch / bonitoLinks
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
β776Updated 3 months ago
Alternatives and similar repositories for bonito
Users that are interested in bonito are comparing it to the libraries listed below
Sorting:
- Evaluate your LLM's response with Prometheus and GPT4 π―β948Updated last month
- Automated Evaluation of RAG Systemsβ596Updated 2 months ago
- This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai,β¦β2,087Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifiβ¦β2,724Updated this week
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalβ1,236Updated 8 months ago
- Generative Representational Instruction Tuningβ639Updated 2 months ago
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.β1,436Updated this week
- β517Updated 6 months ago
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. β π€π€β1,017Updated 3 months ago
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data β¦β705Updated 2 months ago
- Easily embed, cluster and semantically label text datasetsβ540Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backendsβ1,563Updated last week
- Doing simple retrieval from LLM models at various context lengths to measure accuracyβ1,875Updated 9 months ago
- Stanford NLP Python library for Representation Finetuning (ReFT)β1,476Updated 3 months ago
- Official repository for ORPOβ453Updated last year
- Fine-Tuning Embedding for RAG with Synthetic Dataβ497Updated last year
- Efficient Retrieval Augmentation and Generation Frameworkβ1,558Updated 4 months ago
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.β453Updated this week
- A library for advanced large language model reasoningβ2,132Updated last month
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diveβ¦β944Updated 7 months ago
- Automatically evaluate your LLMs in Google Colabβ629Updated last year
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.β2,390Updated this week
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and β¦β344Updated 11 months ago
- RAGChecker: A Fine-grained Framework For Diagnosing RAGβ897Updated 5 months ago
- β893Updated 8 months ago
- A reading list on LLM based Synthetic Data Generation π₯β1,280Updated 2 weeks ago
- β597Updated 4 months ago
- β877Updated 7 months ago
- Code for explaining and evaluating late chunking (chunked pooling)β390Updated 5 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retrainingβ697Updated last year