Live data from Hacker News

Llama 2

ai.meta.com

531–540 of 860 posts

Re: Llama 2

#531

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…

Lately I’ve been wondering if a license similar to this but instead based on market cap could be a way to monetize open source projects

E.g. 100k/year for each trillion in market cap, updated yearly. First trillion is free

Re: Llama 2

#532
post #69

Earlier quoted context omitted.

its not clear but can we also download the model with this Llama v2 Cog thing? EDIT: Meta is being extremely prompt, just got sent the download instructions https://twitter.com/swyx/status/1681351712718876673 also is it now Llama or LLaMA since the website says Llama? lol

Seems people here on HN were lucky. Signed up ~20 minutes ago and no download link, so surely they're doing some checking, it's not fully automated, unlike what others say here. On Huggingface, the following disclaimer has been put in place: > This is a form to enable access to Llama 2 on Hugging Face after you have been granted access from Meta. Please visit the [Meta website]( https://ai.meta.com/resources/models-a…

I signed up again with "country" being United States and I got it immediately -- apparently they're not auto-accepting other countries..

Re: Llama 2

#533

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…

> get this question correct I am willing to bet a million dollars that it is unlikely any single model will ever be able to answer any question correctly. The implications then are that one cannot use a single question evaluate whether a model is useful or not.

I would go even further, use models to answer questions only if you don't care whether the answer is correct or not.

Re: Llama 2

#534
post #275

Hey HN, we've released tools that make it easy to test LLaMa 2 and add it to your own app! Model playground here: https://llama2.ai Hosted chat API here: https://replicate.com/a16z-infra/llama13b-v2-chat If you want to just play with the model, llama2.ai is a very easy way to do it. So far, we’ve found the performance is similar to GPT-3.5 with far fewer parameters, especially for creative tasks and interactions. Dev…

Still fails my hippo test! > Yes, hippos are excellent swimmers. They spend most of their time in the water, where they feed on aquatic plants and escape the heat of the savannah. In fact, hippos are one of the best swimmers among all land mammals. But that's fine. Most do. Hippos don't swim. They walk or hop/skip at best underwater.

is there a model that succeeds the hippo test?

Re: Llama 2

#535
post #527

Earlier quoted context omitted.

If you want to try running Llama 2 locally, you can use https://github.com/jmorganca/ollama To run Llama 2 with it: ollama run llama2

Thank you for sharing your project. Do you know why it would print this message that it cannot write code? https://gist.github.com/hbt/4fc643f64ac9e34250cdd1a3d6279eba However, when using the API https://www.llama2.ai/ It can actually produce code. https://htmlpreview.github.io/?https://gist.githubuserconten... Is this a prompt thing? a model thing? Thank you.

I posted something in the Gist, but the prompt can be really finicky. You might want to `ollama pull llama2` again just to make certain you have the latest prompt. We were messing around with it earlier because it was giving some strange answers.

I think it's going to take a while to figure out what the best prompt to use is though.

Re: Llama 2

#536

keep getting `md5sum: checklist.chk: no properly formatted checksum lines found` when I try to download the weights -- even though I received an approval.

I got this when I tried to download the weights and it was because instead of the proper files I was downloading an "unauthorized access" html page due to my work blocking the download.

I switched to the huggingface repository to get the files. Of course I'm not out of the weeds yet, but I'll give it another hour before I throw my arms up.

Re: Llama 2

#537
post #20

Another non-open source license. Getting better but don't let anyone tell you this is open source. http://marble.onl/posts/software-licenses-masquerading-as-op...

On HN, I really expected better of people. Why does everybody think this is open source? Every third comments is about how it's open source, but it's not Does everyone also think OpenAI is open source? Or a non-profit? Does putting open in the name just mean you're going to love it?

It’s not open source, but it is more open than GPT. We can obviously download the weights.

Re: Llama 2

#539

Earlier quoted context omitted.

I don't think so. I think what is happening is that most people are not familiar with hippos because probably somewhere between zero and one people in this thread have ever seen them in their natural habitat. The average person might think hippos swim because they do not understand that hippos do not float. If you were to put a hippo in a very deep pool they would simply drown, because they cannot float nor swim. I t…

You just said definitions and usage don’t line up, and usage is what it means. Now you’re saying how people use it is wrong because it’s not what it means. Can you see how that is confusing?

Sure, human language is pretty confusing! Or rather it is nuanced. Dictionary definitions try to track the way language is used in common parlance, rather than the meaning of words tracking dictionary definitions. At the same time, not all people use all words correctly. For example, the words "affect" and "effect" are commonly confused, but misuse of those words is simply considered incorrect, not a drift in the meaning of the words. Then there are words like "nice" or "cute" [1] whose meanings drifted over time. So the confusion you point out comes from this distinction, which I have not explained because I think that's probably the kind of thing for a language scholar, where some different usages of words are simply incorrect, whereas others represent the natural drifting of language over time. The truth is I do not know how to explain why this happens, but I am aware of these distinctions.

[1] https://theculturetrip.com/europe/articles/10-english-words-...

Re: Llama 2

#540

Earlier quoted context omitted.

Consideration -> Implementation -> Verification is a super low friction way to improve how LLMs do at coding tasks (or most tasks really). - Me: We want to swap keys with values in a Ruby hash, what are some considerations? LLM: When swapping keys with values in a Ruby hash, there are a few considerations to keep in mind. First, it's important to note that swapping keys and values can change the order of the hash, wh…

But this is wrong in at least two ways: > Additionally, if the hash contains duplicate keys, swapping the keys and values may not have the desired effect. You can't have duplicate keys in a hash. More importantly, their implementation adds the swapped pairs but does not remove the original k/v pairs, which is both incorrect and does not match the output it prints.

It looks like you can have duplicate keys so I'll give it the benefit of the doubt: https://stackoverflow.com/questions/6808801/ruby-hash-with-d...

But maybe this is why they still used GPT-4 for benchmarking, GPT-4's take:

Actually, there is a mistake in that response. The code snippet I provided modifies the original hash during iteration, which can lead to unexpected results. Also, the code can't handle the case where there are duplicate values.

A safer and more accurate way would be to create a new hash and then populate it with the swapped keys and values:

   hash = {a: 1, b: 2, c: 3}
   swapped_hash = {}

   hash.each do |key, value|
      swapped_hash[value] = key
   end

    puts swapped_hash
    # Output:
    # {1 => :a, 2 => :b, 3 => :c}
In this example, we avoid modifying the original hash while iterating over it, and the potential problems that can cause. Additionally, please note that if the hash contains duplicate values, some entries might be overwritten in the new hash since hash keys must be unique.

Also, the invert method is a built-in Ruby method for swapping keys with values in a hash. It's a simpler approach:

   hash = {a: 1, b: 2, c: 3}
   swapped_hash = hash.invert
   
   puts swapped_hash
   # Output:
   # {1 => :a, 2 => :b, 3 => :c}
Remember that the invert method also doesn't handle duplicate values gracefully. If a value appears more than once, only one of those instances will appear in the inverted hash.

-

Since I wrote the original comment I tried this for common use cases I've established with 3.5 and 4 and it's still a joke. Overall OpenAI is clearly dominating this space in a way I think people are downplaying out of hope.

Post reply on HN