kani (カニ) is a highly hackable microframework for chat-based language models with tool use/function calling. (NLP-OSS @ EMNLP 2023)
MIT License
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
LLaVA-NeXT-Image-Llama3-Lora, Modified from https://github.com/arielnlee/LLaVA-1.6-ft
[ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language M...
A high-performance inference system for large language models, designed for production environments.
KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델
🤖 Everything you need to create an LLM Agent—tools, prompts, frameworks, and models—all in one pl...
A high-throughput and memory-efficient inference and serving engine for LLMs
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
An Efficient "Factory" to Build Multiple LoRA Adapters
An Open-sourced Knowledgable Large Language Model Framework.
[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful convers...
EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders
Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in ...
Private Open AI on Kubernetes