awesome-llamas

get it on Hugging Face

Meta is giving its answer to OpenAI’s GPT-4 away for free. The move could intensify the generative AI boom by making it easier for entrepreneurs to build powerful new AI systems.

open source implementation of Microsoft's Orca model, based on Llama 1, not for commercial use.

FreeWilly is a Llama65B model fine-tuned on an Orca style Dataset

FreeWilly2 is a Llama2 70B model finetuned on an Orca style Dataset, beating Llama-2-70b-chat on the HuggingFace Open LLM Leaderboard

Releasing LLongMA-2-13b-16k, a Llama-2 model, trained at 16k context length using linear positional interpolation scaling. 8k context length is also available. (

LLaMA2-70B-chat is better than ChatGPT and Claude2, trailing only GPT-4 as of 2023-07-27.

see models that have llama or llama-2 in the name.

Code Llama is an AI model built on top of Llama 2, fine-tuned for generating and discussing code. Also this

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation:

Inference Llama 2 in one file of pure C by Andrej Karpathy

Llama中文社区，最好的中文Llama大模型，完全开源可商用

Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen)

A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device

Other model sizes can be found here:

Other model sizes can be found here:

Post I wrote for how to run

Released 2023-02-27

Released 2023-07-18