:robot: The free, Open Source OpenAI alternative. Self-hosted, community...
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT f...
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
The official PyTorch implementation of Google's Gemma models
Firefly: 大模型训练工具,支持训练Llama3、Gemma、MiniCPM、Yi、Deepseek、O...
Replace OpenAI GPT with another LLM in your app by changing a single lin...
Fully-featured, beautiful web interface for Ollama LLMs - built with Nex...
Inferflow is an efficient and highly configurable inference engine for l...
Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave ...
JetStream is a throughput and memory optimized engine for LLM inference ...
Examples of RAG using Llamaindex with local LLMs - Gemma, Mixtral 8x7B, ...
Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)