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

Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

cerebras.net

Post reply on HN
Print view View original

111–120 of 231 posts

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#111

Post by bilsbie »

2bitencryption wrote: post #105
simon83 wrote: post #72

Earlier quoted context omitted.

Google: "confetti has left the cannon" > No results found for "confetti has left the cannon". I'm amazed that a "stochastic parrot" can come up with such a beautiful idiom.

For the curious, here was the conversation I had: ME: What's another saying similar to: "The cat is out of the bag" or "The genie is out of the bottle"? chatgpt: Another similar saying is "the toothpaste is out of the tube." Like the other two expressions, this phrase conveys the idea that something has been revealed or unleashed, and it cannot be undone or put back into its original state. ME: Can you invent a new p…

I don’t understand why people aren’t more impressed with it clearly understanding and then even inventing idioms. That shows some real intelligence.

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#112

Post by alchemist1e9 »

Garcia98 wrote: post #92

I've been following open source LLMs for a while and at first glance this doesn't seem too powerful compared to other open models, Flan-Alpaca[0] is licensed under Apache 2.0, and it seems to perform much better. Although I'm not sure about the legalities about that licensing, since it's basically Flan-T5 fine-tuned using the Alpaca dataset (which is under a Non-Commercial license). Nonetheless, it's exciting to see…

Sounds like you might be the right person to ask the “big” question.

For a small organization or individual who is technically competent and wants to try and do self-hosted inference.

What open model is showing the most promise and how does it’s results compare to the various openAI GPTs?

A simple example problem would be asking for a summary of code. I’ve found openAI’s GPT 3.5 and 4 to give pretty impressive english descriptions of code. Running that locally in batch would retain privacy and even if slow could just be kept running.

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#113

Post by Tommstein »

2bitencryption wrote: post #105
simon83 wrote: post #72

Earlier quoted context omitted.

Google: "confetti has left the cannon" > No results found for "confetti has left the cannon". I'm amazed that a "stochastic parrot" can come up with such a beautiful idiom.

For the curious, here was the conversation I had: ME: What's another saying similar to: "The cat is out of the bag" or "The genie is out of the bottle"? chatgpt: Another similar saying is "the toothpaste is out of the tube." Like the other two expressions, this phrase conveys the idea that something has been revealed or unleashed, and it cannot be undone or put back into its original state. ME: Can you invent a new p…

That is impressive, especially given that neither Google nor DuckDuckGo find any previous trace of that idiom.

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#114

Post by flir »

simon83 wrote: post #72
2bitencryption wrote: post #26

This type of article (or press release, or whatever you want to call it) is exactly what makes the future so interesting. The cat is out of the bag, the genie is out of the bottle, the confetti has left the cannon[0]. It's tempting to see a world dominated by Google Bard, ChatGPT, Bing Search, etc. And no doubt, they will be huge players, with services that are far more powerful than anything that can be run on the e…

Google: "confetti has left the cannon" > No results found for "confetti has left the cannon". I'm amazed that a "stochastic parrot" can come up with such a beautiful idiom.

Could be lifted from another language. Is nice though.

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#115

Post by fnordpiglet »

bilsbie wrote: post #111
2bitencryption wrote: post #105

Earlier quoted context omitted.

For the curious, here was the conversation I had: ME: What's another saying similar to: "The cat is out of the bag" or "The genie is out of the bottle"? chatgpt: Another similar saying is "the toothpaste is out of the tube." Like the other two expressions, this phrase conveys the idea that something has been revealed or unleashed, and it cannot be undone or put back into its original state. ME: Can you invent a new p…

I don’t understand why people aren’t more impressed with it clearly understanding and then even inventing idioms. That shows some real intelligence.

It’s because they’re confused in thinking human intelligence isn’t learned stochastic expectation.

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#116

Post by johtso »

2bitencryption wrote: post #105
simon83 wrote: post #72

Earlier quoted context omitted.

Google: "confetti has left the cannon" > No results found for "confetti has left the cannon". I'm amazed that a "stochastic parrot" can come up with such a beautiful idiom.

For the curious, here was the conversation I had: ME: What's another saying similar to: "The cat is out of the bag" or "The genie is out of the bottle"? chatgpt: Another similar saying is "the toothpaste is out of the tube." Like the other two expressions, this phrase conveys the idea that something has been revealed or unleashed, and it cannot be undone or put back into its original state. ME: Can you invent a new p…

Not exactly sure why it would be surprising that it can come up with a convincing idiom when it can produce remarkably good _poetry_

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#117

Post by brucethemoose2 »

MacsHeadroom wrote: post #96
meghan_rain wrote: post #83

Earlier quoted context omitted.

How can a GPU be optimized for StyleGAN but not LLMs? Serious question.

RAM. GPT-3 is over 600GB, ie just the max RAM of 8xA100s, because that's all the hardware can fit. StableDiffusion plus a whole chain of imagenets can make any visual imagery imaginable in 2GB of RAM. Meanwhile 2GB of RAM barely runs a basic tiny text completion NN that can't do anything intelligent. Text requires a lot more parameters (and more memory/RAM) than images.

The Cerebras node's actual "RAM" (the 40GB of SRAM) is pretty modest too, but being an enormous chip with the networked storage pools is certainly a better situation than a bunch of A100s reaching out to every other A100.

Honestly, all the AI ASIC makers drastically underestimated the RAM requirements of future models. Graphcore's 4GB and Tenstorrent's 8GB per IC is kinda laughable, and it takes them longer to adjust than Nvidia. And Cerebras' original pitch was "fit the entire model into SRAM!"

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#118

Post by athom »

simon83 wrote: post #72
2bitencryption wrote: post #26

This type of article (or press release, or whatever you want to call it) is exactly what makes the future so interesting. The cat is out of the bag, the genie is out of the bottle, the confetti has left the cannon[0]. It's tempting to see a world dominated by Google Bard, ChatGPT, Bing Search, etc. And no doubt, they will be huge players, with services that are far more powerful than anything that can be run on the e…

Google: "confetti has left the cannon" > No results found for "confetti has left the cannon". I'm amazed that a "stochastic parrot" can come up with such a beautiful idiom.

Try looking up "pinkie pie party cannon"

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#119

Post by simon83 »

barking_biscuit wrote: post #86
simon83 wrote: post #72

Earlier quoted context omitted.

Google: "confetti has left the cannon" > No results found for "confetti has left the cannon". I'm amazed that a "stochastic parrot" can come up with such a beautiful idiom.

Out of distribution generations are a thing.

I understand that all of this is based on some fundamental mathematics, a couple of algorithms here, and some statistical analysis there. And I find it absolutely amazing that we can use all of that knowledge and encode it into something that resembles intelligence. This makes me think if our brains and the concept of intelligence are really as special and mysterious as we assume.

Re: Cerebras-GPT: A Family of Open, Compute-Efficient, Large Language Models

#120

Post by HanClinto »

cs-fan-101 wrote: post #81
antimatter15 wrote: post #77

Looking at their charts it seems like their 6.7B model is considerably worse than GPT-J which is an existing open 6B model from several years ago. I wish rather than stopping training early they would have run more data through a small model so we could have something more competitive with LLaMA 7B.

Someone posted this repost from the Cerebras Discord earlier, but sharing for visibility - "We chose to train these models to 20 tokens per param to fit a scaling law to the Pile data set. These models are optimal for a fixed compute budget, not necessarily "best for use". If you had a fixed parameter budget (e.g., because you wanted to fit models on certain hardware) you would train on more tokens. We do that for ou…

Sounds like we should crowd-fund the cost to train and open source one of these models with LLaMa-like quality.

I'd chip in!

Post reply on HN