Finetune Llama 4, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

The official PyTorch implementation of Google's Gemma models

Local Deep Research is an AI-powered assistant that transforms complex questions into comprehensive, cited reports by conducting iterative analysis using any LLM across diverse knowledge sources including academic databases, scientific repositories, web content, and private document collections.

A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

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

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

Local LLM Powered Recursive Search & Smart Knowledge Explorer

On-device LLM Inference Powered by X-Bit Quantization

Discover and converse with advanced AI models like Mistral, LLAMA2, and GPT-3.5 from leading sources like OLLAMA, Hugging Face, and OpenAI. Easily extract insights from PDFs, web pages, and YouTube videos with our intuitive interface. Unlock the power of knowledge with seamless chat interactions.

open source assistant using small models (2b - 5b) , with agentic and tool calling capabilities and integration of RAG with effiecient memory.android support using adb

Self-Driven Autonomous Python Libraries

Testing and evaluating the capabilities of Vision-Language models (PaliGemma) in performing computer vision tasks such as object detection and segmentation.

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"

Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)