Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I made a self-hosted ChatGPT UI

github.com

Post reply on HN
Print view View original

51–54 of 54 posts

Re: Show HN: I made a self-hosted ChatGPT UI

#51

Post by leobg »

thefourthchime wrote: post #49
CharlesW wrote: post #37

Apologies if this is so unrelated as to be off-topic, but I'm new to this and so my mental model is incomplete at best and completely wrong at worst. My question is: How would one create a "domain expert" version of this? The idea would be to feed the model a bunch of specialized, domain-specific content, and then use an app like this as the UX for that.

I just did this exact thing, it's very easy. https://dev.to/dhanushreddy29/fine-tune-gpt-3-on-custom-data...

This actually has nothing to do with fine-tuning in the technical sense. You are actually using vector search and injecting the results of that into the prompt for GPT.

It is a good approach, but to use the word “fine-tuning“ for that is confusing, given that OpenAI actually has a process for fine-tuning, which works in a very different way.

Re: Show HN: I made a self-hosted ChatGPT UI

#52

Post by vineyardmike »

kkielhofner wrote: post #30
neilv wrote: post #2

> Chat with GPT is an open-source, unofficial ChatGPT app with extra features and more ways to customize your experience. It connects ChatGPT with ElevenLabs to give ChatGPT a realistic human voice. Looks like only GUI aspects of the UI are self-hosted, but that the text and speech aspects of the UI (and the bulk of the computation and IP) are provided by two SaaS services. Self-hosted (and some degree of open) ML mo…

It's somewhat ambiguous language - "self-hosted ChatGPT UI" could lead many to believe it's completely self-hosted. However, sophisticated readers familiar with ChatGPT will know the model and weights haven't been released and absent a leak/hack/release by OpenAI a completely self-hosted ChatGPT solution is impossible. Eventually we'll almost certainly see a "Completely self-hosted ChatGPT equivalent" (similar to Dal…

> I'm not sure how else I would write it to disambiguate between a self-hosted UI and a completely self-hosted ChatGPT with a UI.

"Show HN: I made a self-hosted UI for the ChatGPT API"

"Show HN: I hade a self-hosted UI for a local GPT model"

Re: Show HN: I made a self-hosted ChatGPT UI

#53

Post by brianjking »

noduerme wrote: post #22
tottenval wrote: post #11

Earlier quoted context omitted.

OpenAI hasn't published any information about the size or hardware requirements for running ChatGPT. Reading between the lines, the default ChatGPT Turbo model seems to be significantly smaller than GPT-3 (it's a distilled model), but probably still heavier than the Alpaca and Llama 7B models people are running (very slowly) on their single GPU computers this week. You'd probably need multiple A100s to get comparable…

Does the llama code that dropped leverage the GPU at all? On an M1 it appears to just run on as many CPU cores as you want to throw at it. The 65B heats up 8 cores real nicely, and it's slow, but I imagine it would be a lot faster on the GPU.

All of the llama implementations for Apple are CPU only afaik.

Re: Show HN: I made a self-hosted ChatGPT UI

#54

Post by MrLeap »

monkmartinez wrote: post #33

I have tried this and many, many other ChatGPT frontends. I recently did a search for "chatgpt" on GitHub and filtered for frontends, but I was a bit disappointed with the results. Most of them seemed to be pretty similar and didn't offer anything new or unique. I'm really interested in finding a frontend with LangChain integration that can switch between chat mode and doc mode or something along those lines. It woul…

If it's uniqueness you're after.

https://twitter.com/LeapJosh/status/1635735318665068549

Post reply on HN