421–430 of 860 posts
Earlier quoted context omitted.
LLaMAv1 had guardrails too, but they are super easy to finetune away.
You might be thinking of unofficial LLaMA finetunes such as Alpaca, Vicuna, etc. LLaMA 1 was a base model without any safety features in the model itself.
Earlier quoted context omitted.
Enormous complaint about this space: people seemingly never think to include checksums. Drives me wild when there is supposedly all of this concern about the right data and provenance, yet it is not easy to even confirm you have the genuine article.
The checksums are automatically included with the models when you download them using the download.sh script, and verified right after the download completes. This isn't unlike how a lot of packages distribute the SHA256SUMS file next to their downloads over HTTPS, which you can validate yourself. That said it would be nice to announce them somewhere else but if you're already downloading them from Meta directly the…
That’s the moment when I most would want out of band checksums available.
Making advanced LLMs and releasing them for free like this is wonderful for the world. It saves a huge number of folks (companies, universities & individuals) vast amount of money and engineering time. It will enable many teams to do research and make products that they otherwise wouldn't be able to. It is interesting to ponder to what extent this is just a strategic move by Meta to make more money in the end, but wh…
In a free market economy everything is a strategic move to make the company more money. It's the nature of our incentive structure.
Prompt: 5 Ounce (Pack of 6) is $33. 4 ounce pack of 6 is 15. which is the better deal? Llama 2: The 5 ounce pack of 6 is the better deal. It costs 33for6packs,whichis33for6packs,whichis5.50 per pack. The 4 ounce pack of 6 costs 15for6packs,whichis15for6packs,whichis2.50 per pack. So, the 5 ounce pack of 6 is the better deal. ChatGPT4: To figure out the best deal, we need to calculate the price per ounce for each opti…
Key detail from release: > If, on the Llama 2 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under thi…
Maybe we should give it a good name and hopefully seeing OSS adopt this.
Earlier quoted context omitted.
There's a few prompts that I use with every model to compare them. One of the simplest ones is: > When does the bowl of the winds get used in the wheel of time books? LLaMA2 fails pretty hard: > The Bowl of the Winds is a significant artifact in the Wheel of Time series by Robert Jordan. It is first introduced in the third book, "The Dragon Reborn," and plays a crucial role in the series throughout the rest of the bo…
> Please write a function in JavaScript that takes in a string as input and returns true if it contains a valid roman numeral and false otherwise. Your question actually isn't worded concisely enough. You don't specify whether the string can merely contain the roman numeral (plus other, non-roman-numeral text), or must entirely consist of just the roman numeral. The way "if it contains" is used colloquially, could im…
Earlier quoted context omitted.
> Please write a function in JavaScript that takes in a string as input and returns true if it contains a valid roman numeral and false otherwise. Your question actually isn't worded concisely enough. You don't specify whether the string can merely contain the roman numeral (plus other, non-roman-numeral text), or must entirely consist of just the roman numeral. The way "if it contains" is used colloquially, could im…
I think that makes it a better test. An ideal model would recognize the ambiguity and either tell you what assumption it's making or ask a followup question.
Earlier quoted context omitted.
A 34B model is probably about the largest you can run on a consumer GPU with 24GB VRAM. 70B will require A100's or a cloud host. 13B models are everywhere already. I'm sure this was a very deliberate choice - let people play with the 13B model locally to whet their appetite and then they can pay to run the 70B model on Azure.
70B should work reasonably well on 64GB CPU RAM + any decent GPU, or maybe a 24GB GPU + 32GB CPU RAM.