LangFair — Peer-reviewed • Rank 14.9 • Science 95%

LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases - Published in JOSS (2025)

lazyllm-llamafactory • Rank 25.6 • Science 77%

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

ontogpt • Rank 16.7 • Science 77%

LLM-based ontological extraction tools, including SPIRES

kitsune • Rank 4.2 • Science 85%

Kitsune is a next-generation data steward and harmonization tool.

litgpt • Rank 23.6 • Science 64%

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

txtai • Rank 22.2 • Science 64%

💡 All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows

kani • Rank 8.3 • Science 77%

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

spezillm • Rank 8.0 • Science 77%

Large Language Model (LLM) module for the Spezi Ecosystem

datastew • Rank 8.9 • Science 75%

Python library for intelligent data stewardship using Large Language Model (LLM) embeddings

dolma • Rank 19.6 • Science 64%

Data and tools for generating and inspecting OLMo pre-training data.

farm-haystack • Rank 28.7 • Science 54%

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

kvpress • Rank 14.6 • Science 67%

LLM KV cache compression made easy

ray • Rank 35.1 • Science 46%

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

inseq • Rank 13.6 • Science 67%

Interpretability for sequence generation models 🐛 🔍

bigcodebench • Rank 15.3 • Science 64%

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

tensorzero • Rank 23.4 • Science 54%

TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.

learn_prompting • Rank 13.3 • Science 64%

Prompt Engineering, Generative AI, and LLM Guide by Learn Prompting | Join our discord for the largest Prompt Engineering learning community

tree-of-thought-prompting • Rank 8.0 • Science 67%

Using Tree-of-Thought Prompting to boost ChatGPT's reasoning

chronos-forecasting • Rank 20.5 • Science 54%

Chronos: Pretrained Models for Probabilistic Time Series Forecasting

symbolicai • Rank 17.3 • Science 54%

A neurosymbolic perspective on LLMs

mllmcelltype • Rank 12.3 • Science 59%

🏆 #1 Multi-LLM consensus framework | 550+ stars | 95% accuracy | 10+ LLM providers | Leading cell annotation tool

llms-from-scratch • Rank 14.9 • Science 54%

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

eval-suite • Rank 9.2 • Science 59%

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

optimate • Rank 12.8 • Science 54%

A collection of libraries to optimise AI model performances

agentlego • Rank 12.6 • Science 54%

Enhance LLM agents with rich tool APIs

beyondllm • Rank 12.5 • Science 54%

Build, evaluate and observe LLM apps

https://github.com/modelscope/data-juicer • Rank 19.2 • Science 46%

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

chinese-llama-alpaca-2 • Rank 11.0 • Science 54%

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

multilspy • Rank 18.6 • Science 46%

multilspy is a lsp client library in Python intended to be used to build applications around language servers.

llmebench • Rank 10.5 • Science 54%

Benchmarking Large Language Models

libre-chat • Rank 10.3 • Science 54%

🦙 Free and Open Source Large Language Model (LLM) chatbot web UI and API. Self-hosted, offline capable and easy to setup.

surprisal • Rank 10.1 • Science 54%

A unified interface for computing surprisal (log probabilities) from language models! Supports neural, symbolic, and black-box API models.

magicoder • Rank 9.0 • Science 54%

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

cambrian • Rank 9.0 • Science 54%

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

llm-sandbox • Rank 17.7 • Science 44%

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

@llm-tools/embedjs • Rank 17.7 • Science 44%

A NodeJS RAG framework to easily work with LLMs and embeddings

deeplake • Rank 25.6 • Science 36%

Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai

chinese-mixtral • Rank 7.1 • Science 54%

中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs）

monitors4codegen • Rank 7.0 • Science 54%

Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.

https://github.com/alan-turing-institute/robots-in-disguise • Rank 6.7 • Science 54%

Information and materials for the Turing's "robots-in-disguise" reading group on fundamental AI research.

q-galore • Rank 5.3 • Science 54%

Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.

py-alpaca-eval • Rank 12.6 • Science 46%

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

chinese-llama-alpaca • Rank 12.2 • Science 46%

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

openqa-eval • Rank 3.8 • Science 54%

ACL 2023: Evaluating Open-Domain Question Answering in the Era of Large Language Models

xfinder • Rank 6.6 • Science 51%

[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

nutcracker • Rank 1.9 • Science 54%

Large Model Evaluation Experiments

atlas • Rank 3.0 • Science 52%

Atlas: Adaptive Competency-Based Learning

odin-slides • Rank 7.8 • Science 44%

This is an advanced Python tool that empowers you to effortlessly draft customizable PowerPoint slides using the Generative Pre-trained Transformer (GPT) of your choice. Leveraging the capabilities of Large Language Models (LLM), odin-slides enables you to turn the lengthiest Word documents into well organized presentations.

stormtrooper • Rank 7.6 • Science 44%

Zero/few shot learning components for scikit-learn pipelines with LLMs and transformers.

sgpt • Rank 7.9 • Science 41%

SGPT: GPT Sentence Embeddings for Semantic Search

climsight • Rank 9.3 • Science 39%

A next-generation climate information system that uses large language models (LLMs) alongside high-resolution climate model data, scientific literature, and diverse databases to deliver accurate, localized, and context-aware climate assessments.

odin-tabs • Rank 3.0 • Science 44%

The Odin Tabs extension is a browser extension that allows you to navigate through your browser tabs using speech recognition and the Large Language Model (LLM) of your choice.

gemgpt • Rank 1.1 • Science 44%

Explore the power of Gemma model with GemGPT, a project leveraging AI for innovative solutions. Join us in shaping the future of AI!

https://github.com/bytedance/salmonn • Rank 9.0 • Science 36%

SALMONN family: A suite of advanced multi-modal LLMs

upgini • Rank 17.5 • Science 26%

Data search & enrichment library for Machine Learning → Easily find and add relevant features to your ML & AI pipeline from hundreds of public and premium external data sources, including open & commercial LLMs

napolab • Rank 7.0 • Science 36%

The Natural Portuguese Language Benchmark (Napolab). Stay up to date with the latest advancements in Portuguese language models and their performance across carefully curated Portuguese language tasks.

https://github.com/bowang-lab/bioreason • Rank 5.8 • Science 36%

BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model

https://github.com/bigscience-workshop/petals • Rank 18.7 • Science 23%

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

statlingua • Rank 8.0 • Science 26%

Explain Statistical Output with Large Language Models

https://github.com/amazon-science/auto-cot • Rank 9.1 • Science 23%

Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)

cellama • Rank 5.0 • Science 26%

Cell type annotation with local Large Language Models (LLMs) - Ensuring privacy and speed with extensive customized reports

genaibook • Rank 4.6 • Science 26%

"Generative AI in Action" book's code repository

https://github.com/aisuko/notebooks • Rank 4.6 • Science 26%

Implementation for the different ML tasks on Kaggle platform with GPUs.

https://github.com/bigscience-workshop/xmtf • Rank 7.4 • Science 23%

Crosslingual Generalization through Multitask Finetuning

https://github.com/amazon-science/mezo_svrg • Rank 3.7 • Science 26%

Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"

https://github.com/altunenes/calcarine • Rank 1.4 • Science 26%

Desktop VLM: Real-time FastVLM analysis of video & textures with live compute shaders

https://github.com/astorfi/llm-alignment-project • Rank 3.5 • Science 23%

A comprehensive template for aligning large language models (LLMs) using Reinforcement Learning from Human Feedback (RLHF), transfer learning, and more. Build your own customizable LLM alignment solution with ease.

https://github.com/bigscience-workshop/data-preparation • Rank 8.1 • Science 13%

Code used for sourcing and cleaning the BigScience ROOTS corpus

https://github.com/astorfi/large-scale-ai-blueprint • Rank 4.0 • Science 13%

A comprehensive guide designed to empower readers with advanced strategies and practical insights for developing, optimizing, and deploying scalable AI models in real-world applications.

https://github.com/agnostiqhq/tutorials_covalent_pycon_2024 • Rank 1.4 • Science 13%

curator • Science 44%

Scalable data pre processing and curation toolkit for LLMs

ml-interactive-data-augmentation • Science 67%

Interactive Data Augmentation (CHI 2025)

spectrae • Science 57%

SPECTRA: Spectral framework for evaluation of biomedical AI models

autonomousssiishare • Science 44%

Implementation and evaluation of an autonomous SSI-enhanced iSHARE framework, enabling decentralized identity management, schema alignment for property matching, and automated generation of alternative verification requests, improving scalability, privacy, and flexibility in data spaces and SSI ecosystems.

vellmes-ai-deception-framework • Science 44%

Interactive, dynamic, and realistic LLM honeypots

dpl • Science 44%

[NeurIPS 2023] Multi-fidelity hyperparameter optimization with deep power laws that achieves state-of-the-art results across diverse benchmarks.

coding-steps • Science 44%

An AI-assisted web-based learning platform for Python programming, featuring interactive tasks, real-time feedback, and AI-generated code assistance for novice learners

chain-of-thought • Science 36%

replication of chain of thought paper

https://github.com/amazon-science/cyber-zero • Science 36%

Cyber-Zero: Training Cybersecurity Agents Without Runtime

https://github.com/blegat/linma2472 • Science 26%

Course material for the course LINMA2472 at UCLouvain

https://github.com/amazon-science/turbofuzzllm • Science 26%

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice

https://github.com/csinva/iprompt • Science 36%

Finding semantically meaningful and accurate prompts.

https://github.com/csinva/clinical-rule-survey • Science 13%

Analyzing clinical decision instruments through the lens of data and large language models.

llm_gov_assistant • Science 39%

An agent-based system for context-based document filtering and information aggregation.

https://github.com/bigcode-project/selfcodealign • Science 13%

[NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generation

awesome-llm-papers.github.io • Science 26%

A curated collection of the most impactful papers, tools, and resources on Large Language Models (LLMs). Continuously updated to help researchers, developers, and enthusiasts stay on top of LLM advancements.

aphra • Science 54%

An open-source translation agent designed to enhance the quality of text translations by leveraging large language models

flash-linear-attention • Science 54%

🚀 Efficient implementations of state-of-the-art linear attention models

https://github.com/cornell-zhang/heurigym • Science 36%

Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization

langtest • Science 54%

Deliver safe & effective language models

https://github.com/chen-yang-liu/promptcc • Science 36%

PyTorch implementation of 'A Decoupling Paradigm With Prompt Learning for Remote Sensing Image Change Captioning'

https://github.com/amazon-science/mada_optimizer_search • Science 36%

Code the ICML 2024 paper: "MADA: Meta-Adaptive Optimizers through hyper-gradient Descent"

https://github.com/ammarlodhi255/chest-xray-report-generation-app-with-chatbot-end-to-end-implementation • Science 26%

AI-powered Chest X-ray report generation app using VLM (Swin-T5) and LLM (LLaMA-3) for multilingual Q&A and medical education support.

smart • Science 44%

Self-modifying code at runtime with Large Language Models

self-refine • Science 54%

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

evalplus • Science 54%

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

alembica • Science 67%

Open science package for LLM-powered semantic synthesis and precise extraction of information from unstructured texts.

textgraphs • Science 54%

TextGraphs + LLMs + graph ML for entity extraction, linking, ranking, and constructing a lemma graph

ontoaligner • Science 67%

OntoAligner: A Python Toolkit for Ontology Alignment https://pypi.org/project/OntoAligner/

agentdojo • Science 36%

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.