RewardBench: the first evaluation tool for reward models.

Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation editor Gradio UI.

Convert Compute And Books Into Instruct-Tuning Datasets (or classifiers)!

Go ahead and axolotl questions

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Zep: Long-Term Memory for ‍AI Assistants.

Large Language Model Text Generation Inference

A bagel, with everything.

Scalable Meta-Evaluation of LLMs as Evaluators

An open-sourced LLM judge for evaluating LLM-generated answers.

Arena-Hard-Auto: An automatic LLM benchmark.

AI for all: Build the large graph of the language models

Minimalistic large language model 3D-parallelism training

Easily embed, cluster and semantically label text datasets

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate, Groq (100+ LLMs)

Superfast AI decision making and intelligent processing of multi-modal data.

All available datasets for Instruction Tuning of Large Language Models

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

🥷 Run AI-agents with an API

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

LLM training code for Databricks foundation models

Supercharge Your Model Training

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Implementation of "SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages" paper, accepted to EMNLP 2022.

An open science effort to benchmark legal reasoning in foundation models

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"