Llama3

Eagle is a family of frontier vision-language models (VLMs) developed by NVIDIA that combines multimodal understanding with data-centric training...

MaxKB is an open-source platform for building enterprise-grade AI agents with integrated RAG pipelines, agentic workflows, and MCP tool-use...

This is an educational resource portal for fine-tuning large language models, covering SFT and reinforcement learning workflows (GRPO, GSPO), data...

GenieX is an on-device inference runtime for running large language models and vision models locally on Qualcomm Snapdragon devices (NPU, GPU, CPU)....

OpenCompass is a comprehensive LLM evaluation platform supporting 100+ datasets and a wide range of models (Llama, Mistral, GPT-4, Claude, Qwen,...

GenU is a production-ready reference implementation demonstrating how to safely deploy generative AI use cases in business operations, built on AWS...

Agents-Flex is a lightweight Java framework for building AI applications with LLM integration, RAG, vector stores, tool calling, and agent workflows....

Distributed Llama enables distributed LLM inference by connecting home devices into a cluster using tensor parallelism and Ethernet synchronization...

MaxText is a high-performance, JAX-based open-source library for training and fine-tuning large language models on Google Cloud TPUs and GPUs,...

Khoj is a self-hosted AI assistant platform that integrates local and cloud LLMs with semantic search over user documents and web content. It serves...

Unsloth Studio is a local web UI and training framework for running, fine-tuning, and deploying open-source LLMs (Llama, Gemma, Qwen, DeepSeek, etc.)...

Liger Kernel provides optimized Triton kernels specifically for LLM training, delivering significant memory efficiency and speed improvements for...

LLaMA Factory is a unified fine-tuning framework that supports 100+ large language models and vision-language models through a zero-code CLI and web...

Ollama is a local LLM runtime that lets developers and end users download, run, and interact with open-weight language models (Llama, Gemma,...

A comprehensive Chinese-language tutorial project for deploying, fine-tuning, and using 50+ open-source large language models (LLMs) on Linux...

LLamaSharp is a C#/.NET library for running LLaMA and LLaVA language models locally on consumer hardware, built as a wrapper around llama.cpp. It...

LMDeploy is a specialized toolkit for compressing, deploying, and serving large language models with focus on inference optimization across multiple...

Xinference is a production-ready inference server that lets developers swap between different LLMs (open-source, speech, and multimodal models)...

Parlant is an open-source interaction control harness for building customer-facing AI agents with consistent, compliant, and traceable conversations....

Fanyi is a command-line translator for Chinese and English that fetches results from multiple sources: iciba, youdao, and LLM providers. It's...

tlm is a local CLI copilot that integrates open-source LLMs (Llama, Phi, DeepSeek-R1, Qwen) via Ollama to provide command suggestions, command...

Chinese-LLaMA-Alpaca-3 is a specialized project for adapting Meta's Llama-3 language models to Chinese language tasks through incremental...