IBM / unitxt
🦄 Unitxt: a python library for getting data fired up and set for training and evaluation
☆181Updated this week
Alternatives and similar repositories for unitxt:
Users that are interested in unitxt are comparing it to the libraries listed below
- codebase release for EMNLP2023 paper publication☆19Updated last year
- 🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.☆37Updated this week
- The Granite Guardian models are designed to detect risks in prompts and responses.☆71Updated this week
- Using open source LLMs to build synthetic datasets for direct preference optimization☆59Updated last year
- IBM development fork of https://github.com/huggingface/text-generation-inference☆60Updated 3 months ago
- ☆114Updated 6 months ago
- awesome synthetic (text) datasets☆265Updated 4 months ago
- A package dedicated for running benchmark agreement testing☆16Updated 3 months ago
- Let's build better datasets, together!☆257Updated 3 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆253Updated 8 months ago
- Dolomite Engine is a library for pretraining/finetuning LLMs☆44Updated this week
- RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker☆107Updated last week
- Codebase accompanying the Summary of a Haystack paper.☆75Updated 6 months ago
- ☆42Updated last month
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers☆126Updated last year
- ☆113Updated 6 months ago
- InstructLab Training Library - Efficient Fine-Tuning with Message-Format Data☆30Updated this week
- A Lossless Compression Library for AI pipelines☆234Updated last week
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆190Updated 5 months ago
- ☆57Updated 6 months ago
- Complex Function Calling Benchmark.☆85Updated 2 months ago
- Functional Benchmarks and the Reasoning Gap☆84Updated 5 months ago
- A framework for few-shot evaluation of autoregressive language models.☆13Updated last year
- Generalist and Lightweight Model for Text Classification☆92Updated this week
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆176Updated 2 months ago
- ☆142Updated 11 months ago
- Evaluating LLMs with CommonGen-Lite☆89Updated last year
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆73Updated 5 months ago
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆207Updated 4 months ago