llama

An open-source implementation for training LLaVA-NeXT.

An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

A collection of one-click self-hosted AI

🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.

Parse files (e.g. code repos) and websites to clipboard or a file for ingestions by AI / LLMs

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Co-create PowerPoint slide decks with AI

Open-source spreadsheets platform for deep research and document processing

AutoAudit—— the LLM for Cyber Security 网络安全大语言模型

🤖 State-of-the-art, production ready LLM apps made mega-easy, so you don't have to build them from scratch 🤯 Create a bot, now 🫵

A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

Versatile Almost Local, Eventually Reasonable Assistant 🔫

CPU inference for the DeepSeek family of large language models in C++

On-device LLM Inference Powered by X-Bit Quantization

A holistic way of understanding how Llama and its components run in practice, with code and detailed documentation.

“百聆”是一个基于LLaMA的语言对齐增强的英语/中文大语言模型，具有优越的英语/中文能力，在多语言和通用任务等多项测试中取得ChatGPT 90%的性能。BayLing is an English/Chinese LLM equipped with advanced language alignment, showing superior capability in English/Chinese generation, instruction following and multi-turn interaction.⚠️ This project has been moved to: https://github.com/BayLing-Models/BayLing

[CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback