Very cool, this looks like a combination of chatbot-ui and llama-cpp-python? A similar project I've been using is https://github.com/serge-chat/serge. Nous-Hermes-Llama2-13b is my daily driver and scores high on coding evaluations (https://huggingface.co/spaces/mike-ravkine/can-ai-code-resul...).
Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
11–20 of 78 posts
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#12(1) What are the best more creative/less lobotomized versions of Llama 2?
(2) What's the best way to get one of those running in a similarly easy way?
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#13So many projects still using GPT in their name.
Is the thinking here that OpenAI is not going to defend that trademark? Or just kicking the can down the road on rebranding until the C&D letter arrives?
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#14So many projects still using GPT in their name. Is the thinking here that OpenAI is not going to defend that trademark? Or just kicking the can down the road on rebranding until the C&D letter arrives?
They don’t have the trademark yet.
OpenAI has applied to the United States Patent and Trademark Office (USPTO) to seek domestic trademark registration for the term “GPT” in the field of AI.[64] OpenAI sought to expedite handling of its application, but the USPTO declined that request in April 2023.
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#15Nice project! I could not find the information in the README.md, can I run this with a GPU? If so what do I need to change? Seems like it's hardcoded to 0 in the run script: https://github.com/getumbrel/llama-gpt/blob/master/api/run.s...
Had the same thought, since it is kinda slow (only have 4 pyhsical/8 logical cores though). But I think vRAM might be a problem (8gb can work, if one has a rather recent gpu (here m1/2 might be interesting)).
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#16So many projects still using GPT in their name. Is the thinking here that OpenAI is not going to defend that trademark? Or just kicking the can down the road on rebranding until the C&D letter arrives?
This reminds me of the first generation of computers in the 40s and early 50s following the ENIAC: EDSAC, EDVAC, BINAC, UNIVAC, SEAC, CSIRAC, etc. It took several years for the industry to drop this naming scheme.
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#17So many projects still using GPT in their name. Is the thinking here that OpenAI is not going to defend that trademark? Or just kicking the can down the road on rebranding until the C&D letter arrives?
Well, GPT is simply an initialism for "Generative Pre-trained Transformer".
In Germany, a trademark can be lost if it becomes a "Gattungsbegriff" (generic term). This happens when a trademark becomes so well-known and widely used that it becomes the common term for a product or service, rather than being associated with a specific company or brand.
For example, if a company invented a new type of vacuum cleaner and trademarked the name, but then people started using that name to refer to all vacuum cleaners, not just those made by the company, the trademark could be at risk of becoming a generic term; which would lead to a deletion of the trademark. I think this is basically what happens to GPT here.
Btw, there are some interesting exampls from the past were trademarks were lost due to the brand name becoming too popular: Vaseline and Fön (hairdryer; everyone in Germany uses the term "Fön").
I also found some trademarks which are at risk of being lost: "Lego", "Tupperware", "Post" (Deutsche Post/DHL), and "Jeep".
I don't know how all this stuff works in America though. But it would honestly suck if you'd approve such a generic term as a trademark :/
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#18(1) What are the best more creative/less lobotomized versions of Llama 2? (2) What's the best way to get one of those running in a similarly easy way?
try llama2-uncensored
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#19(1) What are the best more creative/less lobotomized versions of Llama 2? (2) What's the best way to get one of those running in a similarly easy way?
https://github.com/jmorganca/ollama was extremely simple to get running on my M1 and has a couple uncensored models you can just download and use.
Re: Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2
#20Ok, since is running all private, how can I add my own private data? For example I have a 20+ years of an email archive that I'd like to be ingested.