Stars
✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
llama3 implementation one matrix multiplication at a time
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
MINT-1T: A one trillion token multimodal interleaved dataset.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Video code lecture on building nanoGPT from scratch
Build AI Assistants with memory, knowledge and tools.
We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
CodiumAI Cover-Agent: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表,主要面向基础大模型评测,旨在探求生成式AI的技术边界.
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
High-quality datasets, tools, and concepts for LLM fine-tuning.
Create LLM agents with long-term memory and custom tools 📚🦙
Start building LLM-empowered multi-agent applications in an easier way.
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
Llama-3 agents that can browse the web by following instructions and talking to you
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
A framework for few-shot evaluation of language models.
Inference and training library for high-quality TTS models.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory