Charlieholtz

Only because I haven't tested it on Windows/Linux yet (started working on this last week!). But theoretically should be easy to package for other OS's

Enter does continue the chat! And shift-enter for new line.

My Mac now has built in copilot style completions (maybe only since upgrading to Sequoia?). They're not amazing but they're decent.

https://support.apple.com/guide/mac-help/typing-suggestions-...

Thanks for the feedback! I haven't tried to do this yet, but it's built on Tauri 2.0 and it looks not too hard (https://tauri.app/distribute/app-store/). Will take a look at this

ahah true, but in this case, we're (melty) just paying right now. I wanted to make it really easy to try and didn't implement bring your own keys yet. I probably should ask O1 to fix that

Thanks! Right now Chorus is proxying API calls to our server so it's free. This was kind of an experimental winter break project that we were using internally, and it was quicker to ship this way.

Likely going to add bring your own API keys (or a paid version) soon.

Update: just added option to bring your own keys! Should be available within an hour.

Hi! One of the creators of Chorus here. Really cool to hear how everyone is using it. We made this as an experiment because it felt silly to constantly be switching between the ChatGPT, Claude, and LMStudio desktop app. It's also nice to be able to run models with custom system prompts in one place (I have Claude with a summary of how CBT works that I find pretty helpful).

It's a Tauri 2.0 desktop app (not Electron!), so it is using the Mac's native browser view and a Rust backend. It also makes DMG size relatively small (~25mb but we can get it much smaller once we get rid of some bloat).

Right now Chorus is proxying API calls to our server, so it's free to use. We didn't add bring-your-own-api key to this version because it was a bit quicker to ship. This was kind of an experimental winter break project, so didn't think too hard about it. Likely will have to fix that (and add bring your own key? or a paid version?) as more of you use it :)

Definitely planning on adding support for local models too. Happy to answer any other questions, and any feedback is super helpful (and motivating!) for us.

UPDATE: Just added the option to bring your own API keys! It should be rolling out over the next hour or so.

Ahah yeah! So many fun ways to play with these new models

Llama 70B is at GPT-3.5's level! It's not a perfect comparison, but I built this site to compare the two and Llama 70B won (https://llmboxing.com/leaderboard).

It's not as smart as GPT-4, but you can fine-tune Llama to do things that aren't possible with larger models (https://replicate.com/blog/fine-tune-llama-2).

Yeah I’ve noticed that too. Adding a toggle soon!

Ahah, that's awesome. Thank you! Let me know if you have any questions about Replicate! Happy to help.

Yeah I’ve also noticed an unintended bias that we’re not proud of.

We’re on it – we’re reviewing the model and fixing the issue ASAP. Thanks for pointing it out and for your patience!

Yeah, that’s a good point. We’re currently training a new version that reduces this bias. It’s really important to us that we make this better.

Thanks so much :)

I'll share it as soon as I have access! I'll also post a transcript on my site (charlieholtz.com) soon.

Yeah my thought was the up/down votes could be used to have a "Trending" or "Most Popular" section on the site. But that RHLF idea is interesting too — I've had the same problem with tiled images, and so fine-tuning on highly upvoted examples may help

Yes! I love Elixir :) Phoenix LiveView is really amazing. I feel so fast working in it. I got hooked after watching Chris McCord's 'Build a real-time Twitter clone in 15 minutes' demo, and things have improved a lot since then.

great idea! working on this now

working on it!! scaling up now

Hi! Creator here! I just started hacking on this last night and wasn't expecting to see this on HN already :)

It works by taking your prompt and generating an emoji using https://replicate.com/fofr/sdxl-emoji. Next, I remove the background using https://replicate.com/cjwbw/rembg. Then, click to download and add to slack!

It's all open-source, code is here: https://github.com/cbh123/emoji

Let me know if you have any questions!

Whoops! Fixed now

This is a great question. My best answer is that there's a speed/intelligence trade-off. The smaller weights (7B) will run faster and require less memory, but you won't get the same quality responses as the 13B / 70B model. I think there may be a Llama 30B variant coming soon too.

Thanks for pointing this out — we should've pointed out the script needs to be run on WSL. I added a note to the post to clarify (I work at Replicate).

Also, you don't need a GPU to run this script! It builds and runs llama.cpp https://github.com/ggerganov/llama.cpp

There’s been a lot of talk comparing Llama 2 and GPT-3.5. So, I made a site to let the models fight it out. Each round, pick the output you like better.

All open-source, and built with Elixir/Phoenix LiveView: https://github.com/cbh123/llmboxing

This is really exciting. I work at Replicate, where we've already setup a hosted version for anyone to try it:

https://replicate.com/a16z-infra/llama13b-v2-chat

Haha, thanks! Yes the outputs can be bizarre. But it's very impressive how fast text-to-video is evolving. Imagine text-to-video a year from now!

Should be fixed now!

Ah shoot! Fixing now. I think the redirect went to an old version of the notebook

woah these are great

interesting! I got it to work but I wonder if the "bottoms" threw things off

ahah yeah that is terrifying. thanks :)

Hi HN! I've been working for the past couple of weeks on a GUI for running stable diffusion on your Mac.

It works by packaging a stable diffusion repo into a python executable and then calling that executable from an ElectronJS app. It's all open-source.

I've had a lot of fun working on this (except for figuring out Apple notarization), and would love to hear your thoughts!