This headline is totally editorializing. Stick with the source one. “Introducing Lamini, the LLM Engine for Rapidly Customizing Models”
So much click bait in the LLM space.
Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
21–30 of 75 posts
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#22Very exciting! Glad to finally be able to get beyond prompt engineering. What's the pricing model like?
Free open source libraries. Paid LLM hosting. 50% cheaper than OpenAI, pay per compute needed to run & create the LLM. Export the weights anytime you want. Enterprise VPC deployments.
50% cheaper than OpenAI compared to what?
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#23Trivial examples show that this isn't nearly as good as ChatGPT. The headline should be changed.
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#24Earlier quoted context omitted.
Free open source libraries. Paid LLM hosting. 50% cheaper than OpenAI, pay per compute needed to run & create the LLM. Export the weights anytime you want. Enterprise VPC deployments.
50% cheaper than OpenAI compared to what?
OpenAI models have wide ranges in prices, so indeed some clarity is needed
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#25Congrats! I went to your demo and asked for words that end in agi. This is what I got: -- agi, agi, agi, agi, agi, agi, agi These are some of the words that end in agi. You can also use the word agi in a sentence. For example, "I am going to the grocery store to get some agi." These are some of words that end in agi. These are some words that end in agi. maximize, maximize, maximize, maximize, maximize, maximize, max…
It's a fair criticism, and ChatGPT does better, but this isn't a great test of model quality. All LLMS that rely on tokenization struggle with being introspective on language. Try asking chatGPT to count how many e's are in a sentence, or to list all words that start with "to" and end wide "de". I haven't heard anyone describe the phenomenon clearly, but I expect it is a challenge with reasoning over both intent of t…
You can't ask ChatGPT to count something and expect that it can answer correctly, because it does not have counting logic. It is a language model, not a math model. People use this to "prove" hallucinations, but when you ask it something that is within it's programmed abilities, you get something at least close to what you want.
Having said that, here are the words ChatGPT gave me for the same prompt:
Magi Nagi Sagi Yagi Adagi Galagi Tegagi Sigikagi Tagi Wagagi
It missed Unagi, surprisingly. But it is still leagues ahead of the response primordialsoup got from Lamini.
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#26Noting that the Github repo includes a data pipeline for instruction fine tunining. What's the difference between this and other data pipelines like Alpaca?
Aren't you Greg Diamos, the founder, why are you asking this instead of answering?
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#27Earlier quoted context omitted.
Thats an interesting test. Here's what I got from ChatGPT: ---GPT-3.5--- Here are some words that end in "agi": Strategy Swarajya Arthroplasty Sialagogue Podagric Gynecology Physiognomy Ophthalmology Esophagitis Otalgia --- GPT-4 --- Here are some words that end in "agi": Swaggy Raggi Magi Gagi Stagi Please note that some of these words may not be commonly used or may be specific to certain dialects or regions.
Stagi isn't a word (unless you count Lojban). Gagi isn't a word unless you could Filipino slang.
Could you not have at least Googled the word before speaking against it?
https://www.google.com/search?q=stagi
There are a lot of genuine hits for stagi.
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#28Earlier quoted context omitted.
It's a fair criticism, and ChatGPT does better, but this isn't a great test of model quality. All LLMS that rely on tokenization struggle with being introspective on language. Try asking chatGPT to count how many e's are in a sentence, or to list all words that start with "to" and end wide "de". I haven't heard anyone describe the phenomenon clearly, but I expect it is a challenge with reasoning over both intent of t…
You can't ask ChatGPT to count something and expect that it can answer correctly, because it does not have counting logic. It is a language model, not a math model. People use this to "prove" hallucinations, but when you ask it something that is within it's programmed abilities, you get something at least close to what you want. Having said that, here are the words ChatGPT gave me for the same prompt: Magi Nagi Sagi…
It's true that ChatGPT is not designed for counting and struggles with it in general.
But my point was that ChatGPT, like any tokenized LLM, doesn't even have the concept of letters. The prompt "how many e's in this sentence" is rendered as the tokens [4919, 867, 304, 338, 287, 428, 6827]. There just isn't a pathway for it to consider the letters that make up those tokens.
I'm a little surprised it did that well on your prompt, which is rendered as [10919, 2456, 886, 287, 556, 72]. The interesting thing here is that 556 = " ag" (with leading space) and 72 = "i". So I'm not sure how got to those words. "Wagagi" is tokens [54, 363, 18013], so somehow it is seeing that token 18013 is what you get when you combine 556 and 72? That seems really weird.
I'd love clarification from someone deeper into LLMs and tokenization.
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#29Earlier quoted context omitted.
Stagi isn't a word (unless you count Lojban). Gagi isn't a word unless you could Filipino slang.
To be fair the question did not specify the language and included a disclaimer about it.
Even if you don't consider an Italian word as a word: It's a last name. It's a brand name. It is several companies' name.
It belongs in the list just fine.
Re: Launch Lamini: The LLM Engine for Rapidly Customizing Models as Good as ChatGPT
#30I hope this turns out be as good as chatgpt and not "we have chatgpt at home"