Llama2

H2O LLM Studio is a no-code GUI framework for fine-tuning large language models (LLMs) without coding experience, supporting techniques like LoRA,...

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

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

This is a collection of Jupyter notebooks and code examples for fine-tuning large language models using PEFT (Parameter-Efficient Fine-Tuning) and...

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

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...

OpenLLM enables developers to deploy any open-source LLM (Llama, Qwen, DeepSeek, Mistral, etc.) as an OpenAI-compatible API with a single command,...

Ludwig is a declarative deep learning framework for building LLMs, multimodal models, and tabular AI systems using YAML configuration files without...

Enchanted is a native iOS, macOS, and visionOS application for privately chatting with self-hosted language models (Llama 2, Mistral, Vicuna, etc.)...

LLM-Aided OCR enhances Tesseract OCR output by using large language models (local or API-based) to correct errors, format text as markdown, and...

The Llama Cookbook is Meta's official guide for building with Llama language models, providing practical recipes and examples for inference,...

Chinese-LLaMA-Alpaca-2 is a fine-tuned version of Meta's Llama-2 with extended Chinese vocabulary and capabilities, offering multiple model variants...