BatsResearch / bonitoLinks
A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.
β795Updated 3 months ago
Alternatives and similar repositories for bonito
Users that are interested in bonito are comparing it to the libraries listed below
Sorting:
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. β π€π€β1,069Updated 8 months ago
- Evaluate your LLM's response with Prometheus and GPT4 π―β1,005Updated 5 months ago
- Automated Evaluation of RAG Systemsβ664Updated 6 months ago
- The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalβ1,434Updated last year
- Automatically evaluate your LLMs in Google Colabβ660Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifiβ¦β2,903Updated this week
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.β1,560Updated 4 months ago
- Easily embed, cluster and semantically label text datasetsβ578Updated last year
- Fine-Tuning Embedding for RAG with Synthetic Dataβ512Updated 2 years ago
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diveβ¦β966Updated last year
- Code for explaining and evaluating late chunking (chunked pooling)β453Updated 9 months ago
- Train Models Contrastively in Pytorchβ753Updated 6 months ago
- Generative Representational Instruction Tuningβ675Updated 3 months ago
- [NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelsβ664Updated 3 months ago
- β897Updated 11 months ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracyβ2,056Updated last year
- Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuningβ308Updated 11 months ago
- Efficient Retrieval Augmentation and Generation Frameworkβ1,735Updated 9 months ago
- This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai,β¦β2,213Updated last year
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data β¦β782Updated 7 months ago
- Best practices for distilling large language models.β578Updated last year
- β544Updated 11 months ago
- β1,097Updated last year
- β634Updated 9 months ago
- β415Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backendsβ2,021Updated this week
- Repository for "MultiHop-RAG: A Dataset for Evaluating Retrieval-Augmented Generation Across Documents" (COLM 2024)β376Updated 6 months ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and β¦β344Updated last year
- Official repository for ORPOβ463Updated last year
- Data and tools for generating and inspecting OLMo pre-training data.β1,332Updated 3 weeks ago