lazyllm-llamafactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
chatAI4R: Interactive Artificial Intelligence toolkit for Data Science in R
chatAI4R: Interactive Artificial Intelligence toolkit for Data Science in R - Published in JOSS (2026)
rwkv-lm
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
tensorzero
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
llms-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
medicalgpt
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
surprisal
A unified interface for computing surprisal (log probabilities) from language models! Supports neural, symbolic, and black-box API models.
@llm-tools/embedjs
A NodeJS RAG framework to easily work with LLMs and embeddings
https://github.com/nixtla/nixtla
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
xfinder
[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation
iamai
A rule-driven comprehensive AI toolkit emphasizing simultaneous support for multimodal machine learning and the ability to construct cross-platform robots using logic.（规则驱动式的综合性人工智能工具库，强调同时支持多模态机器学习和利用逻辑构建跨平台机器人的能力）
lrv-instruction
[ICLR'24] Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
gemgpt
Explore the power of Gemma model with GemGPT, a project leveraging AI for innovative solutions. Join us in shaping the future of AI!
minigpt
An open-source project to show how to build a mini language model using PyTorch
video-compression-and-future-prediction-using-gpt
This repository presents a project focused on advanced video compression and future prediction using Generative Pre-trained Transformer (GPT) and other state-of-the-art techniques.
https://github.com/bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
keras-gpt-copilot
Integrate an LLM copilot within your Keras model development workflow
quickai
QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
https://github.com/gabotechs/musicgpt
Generate music based on natural language prompts using LLMs running locally
https://github.com/cedrickchee/chatgpt-universe
ChatGPT Universe is fleeting notes on ChatGPT, GPT, and large language models (LLMs)
https://github.com/bytedance/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation
https://github.com/johnsnowlabs/johnsnowlabs
Gateway into the John Snow Labs Ecosystem
https://github.com/amazon-science/transformers-data-augmentation
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper
https://github.com/asanchezyali/ai-avatar
Zippy Talking Avatar uses Azure Cognitive Services and OpenAI API to generate text and speech. It is built with Next.js and Tailwind CSS. This avatar responds to user input by generating both text and speech, offering a dynamic and immersive user experience
llm-reliability
Code for the paper "Larger and more instructable language models become less reliable"
https://github.com/adithya-s-k/world-of-ai
WORLD OF AI : An open-source repository for AI-based projects 🚀, from beginner to expert level, helping contributors start their journey in Artificial Intelligence and Deep Learning. Our projects provide hands-on experience to real-world problems👨💻. Join our community and contribute to the development of AI-based solutions 👥.
black
https://github.com/copyleftdev/shellbot
ShellBot is a vibrant CLI tool that leverages OpenAI's cutting-edge AI to provide expert guidance on computer science, cloud computing, and Linux systems. Designed for tech enthusiasts and IT professionals alike, ShellBot answers your queries, troubleshoots issues, and shares best practices—all with a splash of color for enhanced readability
llm_from_scratch
I am using here just to share what I have been struggling to understand
ai_story_scale
The AI story scale (AISS): A human rating scale for texts written with generative language models.
firebase-gpt-chat-completion-stream
Example of ChatGPT Stream implementation in Firebase with functions. For this method you have to use `fetch`.
llm-confidentiality
Whispers in the Machine: Confidentiality in Agentic Systems
https://github.com/claromes/resumo-periodico
Telegram bot para resumos de artigos científicos
awesome-attention-heads
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
llm-change-agent
LLM Change Agent is a command-line interface (CLI) tool designed to interact with various language models for generating and modifying ontology definitions. It offers a range of functionalities to streamline KGCL command generation tasks.
gptlint
A linter with superpowers! 🔥 Use LLMs to enforce best practices across your codebase.
automated-brain-explanations
Generating and validating natural-language explanations for the brain.
https://github.com/algo7/day-planner-gpt-data-portal
Data integration solution designed to seamlessly connect data sources such as emails, news feeds, and calendar information to plan your day using OpenAI's GPTs
https://github.com/dc-research/tempo
The official code for "TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)". TEMPO is one of the very first open source Time Series Foundation Models for forecasting task v1.0 version.