llama2.java--Llama 2 in With One Pure Java 21 File

llama2.java (github.com/mukel/llama2.java) walkthrough.
Also checkout the airhacks.fm podcast with Alfonso: the creator of llama2.java: "LLama2.java: LLM integration with A 100% Pure Java file" 👉 airhacks.fm/#episode_294 📻📡
Java used in this short: openjdk version "21" 2023-09-19 LTS
Visual Studio Code used for editing: code.visualstudio.com/
See you at live, virtual workshops: airhacks.live
About me: airhacks.industries
#airhacks

[@khalilelemam1349]

It might be very stupid question. What is llama is?? I'm a beginner😅

[@bienadam]

There are no stupid questions: 👉 llama.meta.com Thanks for watching && asking!

[@michbishee]

Don’t you need to put “by meta” in your product name to use it? Wouldn’t every enterprise client hate that?

[@bienadam]

In the screencast I used the tinystories model. llama2_java also integrates well with mistral.ai and other llama-like models (checkout airhacks.fm/#episode_294) - which is highly appreciated by enterprise companies. In my current projects I'm using AWS Bedrock with Claude v3. Thanks for watching!

[@champfisk5613]

What is the purpose of this and what can be done with it? Seems like it just spit out a couple of paragraphs

[@bienadam]

This PoC example uses huggingface.co/karpathy/tinyllamas/tree/main behind the scenes. If you download the llama2 model (github.com/karpathy/llama2.c#metas-llama-2-models), you get a ChatGPT-like but offline experience without any external dependencies or Python involved. Thanks for watching!