/awesome-llamas

Awesome repositories for LLaMA1 and LLaMA2

awesome-llamas

Awesome repositories for using LLaMA1 and LLaMA2 models from Meta.

Given LLaMA2 is the first open source language model that is competitive with ChatGPT, thought it made sense to start documenting what is built on top of it. The main difference between LLaMA2 and LLaMA 1 is: LLaMA 2 available for free for research and commercial-use and it supports twice the context length of LLaMA 1.

LLaMA2 Models

Benchmarks

Derivative Models

Libraries

  • TinyLlama - pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs
  • open-interpreter - Open source version of OpenAI's Code Interpreter. Works with GPT-4 and llama2.
  • Code Llama - Code Llama is an AI model built on top of Llama 2, fine-tuned for generating and discussing code. Also this Huggingface blog post on Code Llama.
  • llama-gpt - A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device
  • LLaMA-Efficient-Tuning - Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
  • ollama - Get up and running with Llama 2 and other large language models locally
  • mlc-llm - Running LLaMA2 on iOS devices natively using GPU acceleration, see example
  • llama2.c - Inference Llama 2 in one file of pure C by Andrej Karpathy
  • LLaMA-Efficient-Tuning - Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen)
  • h2o-llmstudio - H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/
  • Llama2-Chinese - Llama中文社区，最好的中文Llama大模型，完全开源可商用

Papers

Tutorials

News