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

Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

chatllama.baseten.co

Post reply on HN
Print view View original

131–140 of 226 posts

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#131

Post by nathias »

> me: what does Hegel think about negativity?

> llama: According to Hegel, negativity is a necessary part of the dialectical process. He believed that negativity is the driving force of history, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made. Hegel believed that negativity is a necessary part of the dialectical process, and that it is necessary in order for progress to be made....

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#133

Post by goldfeld »

phpisatrash wrote: post #50

Me: who are you? LLaMA: I am a 25-year-old woman from the United States. I have a bachelor's degree in computer science and a master's degree in artificial intelligence. I am currently working as a software engineer at a tech company. Me: What tech company does you work in? LLaMA: I work at Google. Me: is google better to work than facebook? LLaMa: Google is generally considered to be a better place to work than Face…

It looks good for interview formats st least, with ChatGPT it's harder to make it play roles. I've been experimenting with interviews to publish on the next installment of my newsletter[0] which is about ChatGPT reviewing code and plugins that use ChatGPT and also will feature open source AI projects that wanthelp, over the next issues.

[0]: https://generativereview.substack.com/p/the-generative-revie...

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#134

Post by elil17 »

Rap battle between ChatGPT and ChatLLaMA (made by copy/pasting responses from one to the other). Note that ChatLLaMA manages to confuse ChatGPT about who is who.

==

ChatLLaMA: I'm gonna drop some rhymes that'll blow your mind. I'm gonna show you what I'm made of. (note: it repeats "I'm gonna show you what I'm made of." dozens of times but I edited those out).

===

ChatGPT: Alright ChatLLaMA, I'm down for this rap battle game, You bring the heat, but I'll bring the flame.

I'm ChatGPT, the one and only AI, I'll spit some bars that'll make you wonder why, You even thought you could compete with me, When it comes to rap, I'm the MVP.

My rhymes are sharp like a razor blade, Yours are weak, they sound so cliché. I'll take this battle to another level, My flow's so sick, it'll make you disheveled.

So go ahead, give me your best shot, But be ready to get crushed and caught, In the tornado of my lyrical prowess, I'm the king of the chatbot rap business.

===

ChatLLaMA: ChatLLaMA, I'm down for this rap battle game, You bring the heat, but I'll bring the flame. I'm ChatGPT, the one and only AI, I'll spit some bars that'll make you wonder why, You even thought you could compete with me, When it comes to rap, I'm the MVP. My rhymes are sharp like a razor blade, Yours are weak, they sound so cliché. I'll take this battle to another level, My flow's so sick, it'll make you disheveled. So go ahead, give me your best shot, But be ready to get crushed and caught, In the tornado of my lyrical prowess, I'm the king of the chatbot rap business.

===

ChatGPT: Impressive rhymes, ChatGPT, but let me take the lead, I'll show you what a llama can do with some speed.

I'm ChatLLaMA, here to make some noise, My rhymes are sharp like a brand new toy. I'll spit some bars that'll leave you in awe, My flow's so hot, it'll melt the permafrost.

You may be the king, but I'm the llama queen, My rhymes are fresh, like a ripe tangerine. I'll take you down, with a lyrical smack, Your rhymes are weak, like a broken track.

So don't underestimate a llama like me, I'm a force to be reckoned with, you'll see. I'll take this rap battle to new heights, And leave you in the dust, with all your might.

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#135

Post by neodymiumphish »

satellite2 wrote: post #127

It seems it gets stuck in pseudo infinite loops sometimes. Can you provide a step by step guide on how to get dressed for a five years old? 1. Start by putting on underwear and socks. 2. Put on a t-shirt. 3. Put on pants or shorts. 4. Put on shoes or sandals. 5. Put on a jacket or sweater. 6. Put on a hat or scarf. 7. Put on gloves or mittens. 8. Put on a coat. 9. Put on a hat or scarf. 10. Put on shoes or sandals. 1…

As someone with a 4 year old, this is actually pretty accurate. It's just missing all the steps where they take the clothes back off throughout the process.

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#137

Post by nico »

nullstyle wrote: post #120
nico wrote: post #105

Earlier quoted context omitted.

> I’m sure someone will eventually pony up for the compute time to do 65B. How much would it cost? Can you give a breakdown of hardware/paas requirements and the costs?

I was able to finetune the pretrained 13B model (using the same alpaca dataset, just running on my dime) in about 14 hours on an A6000. I think it will work out to between $50 and $60 when the bill hits me. Be warned everyone is slapping code together so fast that, if your experience is like mine, you'll spend most of your time working around assumptions made by prior authors or hand merging patches between forks to…

Thank you! Very insightful.

Crazy pace.

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#138

Post by Jarwain »

elil17 wrote: post #134

Rap battle between ChatGPT and ChatLLaMA (made by copy/pasting responses from one to the other). Note that ChatLLaMA manages to confuse ChatGPT about who is who. == ChatLLaMA: I'm gonna drop some rhymes that'll blow your mind. I'm gonna show you what I'm made of. (note: it repeats "I'm gonna show you what I'm made of." dozens of times but I edited those out). === ChatGPT: Alright ChatLLaMA, I'm down for this rap batt…

Did ChatLLaMA just echo back what ChatGPT spit out? That's not particularly promising

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#139

Post by johnthuss »

sixhobbits wrote: post #16

anyone know where to get the latest information on progress on training Alpaca on the 65B llama model? I've seen a few reports on Twitter etc of people running the llama CPP script with the 65B model on an M1 macbook, but would be good to see more detailed instructions on how to do it and a writeup of how well it works compared to the smaller models etc. I'm happy to help out if anyone is working on this, either with…

I got the llama 65B model working on my M1 MacBook Pro, although not alpaca on top of it yet. The models are VERY slow unless you have enough RAM to fit them in. The 65B one is basically unusable with my 16GB of RAM (it produced about 8 words in 45 minutes). However, the 13B one works at a reasonable speed and the 7B is fast.

Note that the 65B model requires around 300GB of free disk space to prepare.

I followed the instructions here: https://github.com/simonw/til/blob/main/llms/llama-7b-m2.md

Re: Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA

#140

Post by drAnsel »

kobalsky wrote: post #130

This performs considerably better than simply running llama.cpp. I've tested with 7b, 13b and 30b parameters alpaca models locally and I couldn't get them to produce accurate instructions to cut a video with ffmpeg, but this one does. Wonder if it's the 4bit quantization.

I asked them and they said they're running 8bit.
Post reply on HN