I was trying to distance myself from this situation, but this is just too painful to read. I am sincerely sorry that people have harassed you on my behalf, but I have no control over what some people say or do on an anonymous board based on publicly available information.
That doesn't mean that I am happy with the way our collaboration was handled. Why did you create a new converter when you knew there was already an existing pull request that addressed the same issue? Why did you modify the model format and break backwards compatibility when the current format was proven to work with mmap? Why did you change the magic string of the file format to include your initials, when there was an explicit version number field for this purpose? Why did you create a new pull request when you could have added your changes to mine? Why did you rush to merge the PR instead of taking your time to verify that everything worked properly, while listening to feedback from the other contributors and users? Why did you did you ignore concerns raised by other contributors in my PR? Why are you claiming that I was unable to make the WIN32 code work when the final version in your PR is virtually identical to mine, making me look incompetent?
Ultimately, it was my decision to move on, close my PR and allow yours to continue unchallenged, and I owned that decision every single time that I have commented about it, including in the PR linked in this post, where I recommended keeping your PR and working on fixing the issues being raised. I am sorry that some people have harassed you, but making me responsible about this is extremely unfair. There are plenty of reasons for people to feel disappointed about your behavior without me having to say anything about it.
I don't expect that anyone will believe me about this, after all I am just an "anonymous person". The truth is, I am extremely weary about posting this because I know how much damage you can do to me if you insist on this route to your followers. What is your theory, that because I am nobody I have nothing to lose? How are you not aware of the huge power imbalance between a "celebrity programmer" with thousands of followers and a nobody like me?
Anyway, all the information is publicly available on github for anyone who cares enough to verify it.
> I was trying to distance myself from this situation [...]
You were trying to distance yourself from the situation?
Looking at https://rentry.co/Jarted [0], there was somebody claiming to be you saying things like:
1. "Slaren here. Pretty much all that has been said here is correct, what jart did was to take my code, remove backwards compatibility, add a new converter and then proceed to take all the credit."
2. "To understand why I did that, you have to go back here: https://github.com/ggerganov/llama.cpp/issues/91#issuecommen... jart initially created an implementation of mmap a couple of week back that was an abomination that relied on doing things like replacing malloc. Completely unworkable in a real code base. [...] So anyway, I joined jart's discord and talked to her about this a bit, she seemed to be interested in collaborating and that's why I added her as co-author, even thought she didn't write a line of code of the PR. Eventually out of nowhere she opened the PR that you all know and asked me to close mine. That's when I realized what was happening. So whatever, I did what she asked, left her discord and tried to forget about it".
This was intermingled into comments calling jart a "troon" (a derogatory term for transwoman).
Are you saying unequivocally that this wasn't you?
Even assuming that somebody was stealing your identity, why didn't you point out the problems with the PR upfront? One can't sit on the sidelines casting aspersions (even posthoc) while also claiming that they are distanced from the situation.
Either (a) people are competently pretending to be you on some kind of anti-trans imageboard by some how managing to make past statements that are perfectly consistent with the statements you've made today, or (b) you did pop into that thread to stir up shit.
I think there is a later comment in that thread from you responding to someone saying `#JusticeForSlaren` and requesting that they don't do anything, but that was yesterday and at this point it was too late.
In general what can be seen online doesn't look good for you and you are lucky to be anonymous. I know that you feel that jart stole your glory and it seems they did, but you responded with passive aggressive behaviour and whipped up a mob -- it's hard to believe you are stupid enough to not realise what you were doing with your comments. There were many better responses you could have made: you picked the worst one.
> Maybe I should have contested it but I was and still am going through a pretty rough patch in my life and just didn't have the willpower to start any drama. Mostly I think it sucks because IMO the worse technical solution got merged because their PR had a more flashy title.
>That's when I realized what was happening. So whatever, I did what she asked, left her discord and tried to forget about it.
>I really don't want to start any drama so I'll just say that I wrote the code in my commits.
No one claiming to be that user said anything derogatory or ever called for drama. You're making hollow accusations, basically: "Your messages were intermingled among bad comments" "some other users said bad things," "do you denounce you ever gave your side of the story?"
And I'd certainly consider it distancing yourself from the conversation when you close your PR and remain silent when someone essentially steals your code, and goes from "I was co-author" to "my code," "my work," "I did this," "I'm the author" all over Twitter, a bragging PR where she changed the magic number to her initials, etc.
I'm the one "responsible" for noticing this and raising the flag that something isn't right. Code was stolen and the toxic user responsible was taking more and more credit. The community reacted appropriately, on the whole, as did the owner of the project in banning the plagiarist. She's free to add her side of the story, of course. This issue was actually raised with her on Twitter twice and she ignored it, before it made its way to Github. To the extent that drama was caused by this, it's wholly the fault of the person who created this situation with her unethical behavior and intentionally misleading statements.
Of course no one can verify if that user is the same one in the 4chan threads. It's 4chan. But the commit history speaks for itself, and is well-documented by now.
None of this is an excuse for derogatory terms or slurs to be used on 4chan (or elsewhere), but you're intentionally muddying the waters.
>The major point I make is that the posts online that purport to come from Slaren do not show that they had "distanced themselves from [the] situation".
It's evident from simply looking at the PR that the user @slaren on the Github distanced himself from the situation. Days had passed with no one discussing the stolen code until I brought it up in the original PR (which jart rebased off of and created the infamous "Make loading weights 10-100x faster" PR)
> Yes, I can see that you were one of the key people that created drama, by asking "I'm wondering how much was written by you and how much by jart?" [0]
I didn't create drama. Jart created drama. By stealing code. Plagiarism. Then shameless self-promotion, to this very moment.
Do you have absolutely no integrity whatsoever?
>and then when they publicly said they didn't want to start drama, trying to get private comment from them by saying "My contact info is in my profile if there's more to say."
They didn't contact me, and I simply went through the public Github history to document what jart had done, and continues to do.
>I think somebody could choose to believe this, but somebody that reads the GitHub and desuarchive.org threads might also feel that @InconsolableCellist and @slaren had a part to play, too.
Yes, correct. I told you my part, I noticed what jart was doing. Why have you continually ignored what jart did? Why do you seem to think it's some minor issue that she stole code, bragged about it, took all the credit, and damaged the community with unnecessary drama? Why are you so focused on everything except the central ethical issue?
>Yes, it's technically possible that somebody pretending to be Slaren investigated the GitHub and was able to correctly infer exactly what happened chronologically including that they had collaborated on jart's Discord. However, Occam's razor suggests it was Slaren themselves and not a very clever troll.
Even if that were true--which it isn't, to my knowledge--it changes nothing about jart's behavior. Even if every user also used derogatory slurs, it changes nothing about the wrong was committed (but adds additional wrongs).
Fortunately, for anyone level-headed enough to look at what's been discussed so far, you can see the unethical behavior of the user that stole code, the aftermath, and the appropriate reaction for that user to be banned. The behavior that you've ignored and seem wholly unconcerned with, as if blind to it. Plagiarism.
However, I won't respond to you here, since (1) it should be quite clear that I think @slaren wasn't given enough recognition for their work from my prior comments and that there is a more positive approach you could have taken to helping to give them this, and (2) the rest of what you said about ethics is subjective, and I think wrong in magnitude -- for example, I'm not sure it's correct to call it "plagiarism" when @jart's PR mentioned the collaboration with @slaren, used co-authored commits and linked to their PR.
jart was working on a malloc() approach that didn't work and slaren wrote all the code actually doing mmap, which jart then rebased in a random new PR, changed to support an unnecessary version change, magic numbers, a conversion tool, and WIN32 support when that was already working in the draft PR. https://archive.ph/Uva8c
From what I can see, @jart had spent a considerable amount of time on this problem and had posted an interesting-but-not-production hack to it (https://github.com/ggerganov/llama.cpp/commit/5b8023d9354010...) on March 17th, which they had also excitedly posted about on Twitter.
This was 2 weeks prior to @slaren's contribution (https://github.com/slaren/llama.cpp/commit/fc685122f95f212d1...) on March 29th, so in a sense, it's quite possible that what you've just shown is that @slaren saw that @jart was working on mmap support, worked out a cleaner solution and then wasn't happy with only being a co-author -- for their contribution, they believed that they must be the only person mentioned on the PR: although this is weird, since I don't think they even have a public profile, so maybe instead the truth is that they weren't comfortable with working with somebody that hypes up any changes they've worked on for popularity?
I don't think saying "my changes" on Twitter and other social media means what you suggest it does as is it is just informal speech to refer to things you've worked on with "my", and particularly when you see the times this was expanded (e.g. "yesterday my changes to the LLaMA C++ file format were approved") it seems more reasonable than it does without this context.
If you read the rentry you'll see that both of them were working on an issue that l29ah raised, along with other users. jart's work was on something that didn't end up making it in, the malloc() approach. slaren is the one who wrote the code in the commits I linked to, and that's the code that was adopted. You can (and should) do a comparison of the mmap code and see. What I wrote about the version change, magic number, WIN32, etc., is all true too. As is the haste with which the new PR was made, leading to the recent pushes to revert due to swap thrashing and anger over false and rushed claims about "miracle RAM reduction" etc.
In fact, if you read the thread you linked to, you'll see this for yourself too, no reentry required. There's nothing actually objectionable or "repulsive," as jart put it, in that renetry, with an exception of the "r word" being applied to a proposed technical solution.
Your interpretation is incompatible with what we see and the clear timeline. The social media bragging, the second PR, etc., are further evidence. I hope whatever anger you had going into this has abated to the point where you can now actually judge the evidence.
The major point I make is that the posts online that purport to come from Slaren do not show that they had "distanced themselves from [the] situation".
> No one claiming to be that user said anything derogatory or ever called
> for drama. You're making hollow accusations, basically: "Your messages
> were intermingled among bad comments"
I did not make that accusation. My accusation is that it is ill-advised to enter an anonymous imageboard where people use words like "troon" and often show mob-like behaviour, and to decide there to mouth-off about how someone took all credit for your code, removed backwards compatibility, and to add that their original attempt was an "abomination".
This is not "removing yourself from [the] situation" as Slaren asserts.
> And I'd certainly consider it distancing yourself from the conversation
> when you close your PR and remain silent when someone essentially steals
> your code [...] I'm the one "responsible" for noticing this and raising
> the flag that something isn't right.
Yes, I can see that you were one of the key people that created drama, by asking "I'm wondering how much was written by you and how much by jart?" [0] and then when they publicly said they didn't want to start drama, trying to get private comment from them by saying "My contact info is in my profile if there's more to say."
> To the extent that drama was caused by this, it's wholly the fault of the
> person who created this situation with her unethical behavior and
> intentionally misleading statements.
I think somebody could choose to believe this, but somebody that reads the GitHub and desuarchive.org threads might also feel that @InconsolableCellist and @slaren had a part to play, too.
> Of course no one can verify if that user is the same one in the 4chan threads.
Yes, it's technically possible that somebody pretending to be Slaren investigated the GitHub and was able to correctly infer exactly what happened chronologically including that they had collaborated on jart's Discord. However, Occam's razor suggests it was Slaren themselves and not a very clever troll.
I'm really not muddying the waters here. What you're trying to argue is difficult for me to believe, and whether or not you disagree with the level of recognition given by jart, your comment that "it's wholly the fault of the person who created this situation with her unethical behavior" is ugly. It pins all the blame on jart when it's quite clear from both Slaren and your comments that you were trying to cause drama (anonymously and publicly).
I'd just like to add that if yourself and @anzz1 had wanted to give @slaren the recognition that they deserved in a positive way, you'd have linked to https://github.com/ggerganov/llama.cpp/issues/91#issuecommen... and signal-boosted that as the key insight that enabled the PR to land, rather than taking the approach you took.
Pretending to be someone else to stir up drama is pretty much par for the course for 4chan, especially because they really, REALLY hate transexuals. I'd have been more surprised if someone WASN'T claiming to be slaren.
Trust absolutely nothing from that site or any other imageboard unless people provide documented evidence, e.g. timestamped picture or signed message, etc
>The stories and information posted here are artistic works of fiction and falsehood.
>Only a fool would take anything posted here as fact.
I don't actually have any idea where this quote appears these days, I've just been hearing it in reference to chans for well over a decade now. I think it might have been on the bottom of every page in the past.
I can't thank you enough for posting this. I found the link too repulsive to click that far. I learned a new word today. So that's what they call people like me these days. Hate is such a lost opportunity.
it is good to hear your side. sympathy for all involved. lets hope this is resolved amicably and this important project and helpful contributors lives are not further impact. (I myself believe you. sincerity comes straight through and +1 for not using "probably" in describing what "happened".)
In the beginning of GDPR I remember me sitting in annoying meetings with lawyers who essentially became Product Owners and designers while I still thought the GDPR-Framework makes sense in itself and might help in practice.
But boy was I wrong. The people criticizing GDPR were right: Tech giants were able to cope better with the regulations while smaller domestic companies were put under an additional burden of excessive bureaucracy. And from what I perceive, there's now cookie banners everywhere while my personal data is still going into opaque silos.
Yeah. Mozilla with their ad-network visualization and browser extensions did more to privacy in practice than any GDPR regulation in which exchanging business cards became some kind of mexican standoff.
No that's not true, though it does get spouted very often in online comments.
It's true that a cookie banner (notification only) does not equal "the site can now do whatever it wants and is GDPR compliant thanks to the banner".
However, cookie notification banners are nothing to do with GDPR! They are to comply with an earlier (but still active after GDPR) bit of legislation, the 2002 'ePrivacy Directive' (sometimes known as the "cookies law").
If you don't go near personal data, but still want to use cookies for website functionality, then GDPR doesn't apply but you need to notify users of your use of cookies. If you are doing stuff that's covered under GDPR, then you obviously need to do more than just a cookie notification, and in most cases doing that 'more' will cover the non-personal cookies too so no need for a separate cookie notification on top.
edit to be more specific: section (25) includes "Where such devices, for instance cookies, are intended for a legitimate purpose, such as to facilitate the provision of information society services, their use should be allowed on condition that users are provided with clear and precise information in accordance with Directive 95/46/EC about the purposes of cookies or similar devices so as to ensure that users are made aware of information being placed on the terminal equipment they are using." and "Access to specific website content may still be made conditional on the well-informed acceptance of a cookie or similar device, if it is used for a legitimate purpose." (meaning that unlike with GDPR, it's easier to say "these cookies are necessary, accept them or don't use this website")
And usual disclaimer, this is not legal advice, if you're doing anything affected by either the ePrivacy Directive or GDPR you'd do well to do one or both of getting specific advice from a lawyer with specific expertise in this area, and that if it's a personal site (or a company without the money for legal advice), better safe than sorry and better to give users more power (in terms of requiring their consent to use even cookies that might not need explicit opt-in to be legal, etc) than required rather than less. Both better in terms of liability, and in terms of ethics!
> However, cookie notification banners are nothing to do with GDPR! They are to comply with an earlier (but still active after GDPR) bit of legislation, the 2002 'ePrivacy Directive' (sometimes known as the "cookies law").
The cookie banners people are now complaining about are literally companies skirting or otherwise breaking GDPR. Because they now have to ask for your consent before the siphon your data and sell it wholesale to the highest bidder.
Sorry if I wasn't clear, there's confusion between banners put up because of GDPR and actual 'cookie banners'.
There are certainly plenty of examples of poorly implemented banners attempting to comply with GDPR while not actually being compliant, where consent is required, but I wouldn't call those 'cookie banners' since they generally talk about privacy and personal data, not just about cookies/local storage.
My point was that there are plenty of websites that don't need to comply with GDPR (because nothing they do falls under its scope), but they still need to comply with the ePrivacy Directive and therefore there are plenty of cookie banners used for that purposes that are a perfectly acceptable way of complying with that law - though because people are more familiar with GDPR than with the ePrivacy Directive, they see those banners and think it's a non-compliant attempt at dealing with GDPR.
I think, but don't quote me in that, that with ePrivacy you don't really need a banner, but an explanation that you use cookies. But that is a minor issue
I saw this discussed in my Twitter feed today, so second-third-hand account is that the update has been in the works for almost a decade, being fought tooth and nail by the same companies that fight any other privacy initiative.
Ah yeah, this is what I came across earlier when looking for the full 2002 text: "Proposal for a REGULATION OF THE EUROPEAN PARLIAMENT AND OF THE COUNCIL concerning the respect for private life and the protection of personal data in electronic communications and repealing Directive 2002/58/EC (Regulation on Privacy and Electronic Communications)"
I've been observing this space and a lot of those smaller companies didn't bother to ensure personal data is safe, so it's not like they're the victims here.
There was already one large crackdown on non-compliant cookie banners, and even large entities had to stop fooling around and implement them properly.
The leftovers need to be picked up one by one, but that necessarily takes time.
The people on this site who criticize the GDPR don't even know what the GDPR does, including you. Cookie banners aren't from the GDPR, they're from the ePrivacy Directive as amended in 2009. I don't understand how you people even mix this up, the cookie banners appeared several years before the GDPR existed. It's like this site is a big pity party of surveillance capitalists whining into an echo chamber, remixing and repeating each other's confusions without any feedback from reality.
Maybe (I'm too lazy to check this out). But from what I remember only after GDPR those banners went viral in clumsy, annoying, not useful and frequently unnecessary implementations. Maybe it's because of hefty fines introduced in the context of GDPR.
My point is: Did it help fighting privacy issues? I don't think so. Did it harm? I do think so. Will it ever be somehow measured for its effectiveness and be taken back/changed to be more effective? I don't think so. So better get rid of it.
I seem to recall that before the GDPR, cookie banners were basically a single "OK" button, annoying but at least usually floating near the bottom of the page. After GDPR. they became dark-patterned modal nests of unfathomable checkboxes and submenus.
I don't think it has made of jot of difference for privacy, but it sure has degraded the user experience of using the web.
> GDPR those banners went viral in clumsy, annoying, not useful and frequently unnecessary implementations. Maybe it's because of hefty fines introduced in the context of GDPR.
The problem is that not enough fines have been meted out. Had they been, we'd see less of the unuseful, annoying, unnecessary banners. Because they are this way on purpose: to make you "consent" to wholesale collection and trading of your data.
I was complaining about the cookies banners in 2009, but ok people tend to conflate the two but it is not fair to lash out to people saying they don't like X with a simple rebuff that the thing is actually called Y. China makes the hardware, America writes the software and the EU makes the regulation, is a very common critique of technical people in the tech sector who lack political and economical power compared to the value they create.
I would trust ChatGPT code about as much as I trust the code produced by any human. All the Therac-25 code was written by a human, so what is the argument here exactly? At least when you tell ChatGPT that its code is wrong it agrees and tries to fix. Ok, it usually fails at fixing it, but it doesn't refuse to acknowledge that there is a problem at all, unlike the case of the Therac-25.
I like to think that it is not about who (or what) writes the code in the first place, it is about the review and testing procedures that ensure the quality of the final product. I think. Maybe it is just hopeless.
In general we would like developers/engineers to know as much as possible about the things they're engineering. ChatGPT-based development encourages the opposite.
So because ChatGPT exists now, less experienced programmers will be hired to developed critical software under the assumption that they can use ChatGPT to fill the gaps in their knowledge?
Even in that case, I would argue that is entirely a problem of the process, and should be fixed at that level. An experienced programmer doesn't become any less experienced just because they use ChatGPT.
I know this is probably going to give a heart attack to some of the libertarian tech-bros here, but there is an easy and tested solution for that: price controls. Inflation has a very clear source, it happens when someone decides to raise the prices. Why not stop the problem at the source?
The rises are due to a power dynamic: the companies raising the prices can basically get away with it ("whatever the market will bear").
Why can they do this? One reason is monopoly power- monopolies must be broken up.
But what else can be done (besides central bank driven demand destruction)? So instead of price controls, a more palatable solution is collective buying. This gives buyers more clout, allows them to bargain for lower prices.
So we need more large non-profit buyers clubs, things like that. In the US, allow medicare to bargain with drug companies- it's insane that they can not.
An example where this works: my parents live in a gated community. They pay very little for the cable + internet + cell phone because the entire community has a deal with the provider.
Large retailers have this exact role: they certainly demand and get lower prices from their suppliers. We need a non-profit version of this, why should Walmart owners only benefit from their buying power?
Grocers are typically a commodity business, one feature of which is that the companies do not have pricing power. So unless the grocers have increased their net profit margins, I don't think evil-powerful-corpos is a tenable answer. It's a nice simple, market-based answer that gives people someone to blame, but it's just wrong for grocers.
Target has a NET 2.6% profit margin, Walmart has 1.9%, which are on the low side of what you'd expect for a sustainable commodity business. Tesco appears to have a GROSS (not net: this is after cost of goods but before salaries, etc.) margin of 6.5% and Sainsbury's has 7.6%. [1] Obviously their net profit margin is going to be less. This is hardly a company with a huge pricing power dynamic. If you want to see that, look at Apple (24.5% NET margin), Coca-Cola (22.2% NET margin), Visa (50.3% NET margin). (Note however that Coca-Cola's customers are its bottlers and Visa's customers are merchants so their pricing power might be invisible to end consumers)
>Large retailers have this exact role: they certainly demand and get lower prices from their suppliers. We need a non-profit version of this
This was tried a lot in the 20th century (starting in the 19th century), usually emerging from the labour movement. I think in food retail and energy it has mostly failed or simply stopped making a difference. The profit margins of food retailers are small to begin with and easily lost by being a bit less efficient.
But Europe and the UK in particular has been using a similar model pretty successfully to keep drug prices low. Some argue that costs were merely shifted over to the U.S. I think this is only partially true.
Price controls are equivalent to welfare payments, except instead of being handled by an at least theoretically accountable government, the responsibility is imposed on random third parties with no oversight. Unsurprisingly, most of those third parties decide they'd rather keep their wealth instead of selling at a loss.
Gives anybody with elementary knowledge of econ a heart attack. How far up the supply chain do you want to go with these price controls to try and avoid the inevitable shortages and black markets? Labor price controls? Would that be effective?
> "It happens when someone decides to raise the prices"
What would drive someone to raise the price of something with the confidence it will still sell at that price?
Rising demand and limited supply. Someone with a monopoly on all the widget production can arbitrarily decide to limit supply (e.g. your "limited edition" MTG card), which is a farce.
More often and importantly, in an environment where there are many producers of a commodity like toilet paper, they suffer input shortages or other increases to the cost of production/delivery. On and on this analysis goes until you get to your question, "why not stop the problem at the source". Where is the source in the price increase in toilet paper? Paper production costs are up? Ink costs are up? Shipping costs are up? Regulatory costs are up? Energy prices are up? Labor costs are up? Freeze all of these by government mandate?
As the guy cutting down trees for toilet paper with a shortage of gas for your chainsaw (meaning it costs more to run), do you want the cost of your product arbitrarily frozen with no regard to your input costs? What if the cost of your logging lease from the government increased? Can you raise the price of the toilet paper logs you're selling? No? How is that fair? What if landslides decreased your tree availability by half, but the number butts that needed wiping hasn't changed, or worse, has increased? Are you to sell your now scarce trees at the same price you always did? Or shall you sell to the highest bidder? What if the government says you can't auction the trees but must sell them for the same price? Maybe you look for off-the-books compensation - free tickets to the game, whatever. Someone still bears that increased cost.
If rising demand relative to limited supply is the actual source of the problem (too many people want toilet paper) why not stop the problem there by simply rationing toilet paper? Turns out this is what happens more frequently - rationing eggs, toilet paper, trying to prevent hoarding, scalping, etc.
Arbitrarily limiting the supply costs of a product or the demand for a product is a temporary solution at best.
Price controls and rationing go hand in hand. Ultimately the goal is to ensure that everybody is able to acquire the goods that they need to survive. We are not talking about luxury yachts here, we are talking about food. If the source of the price increases is an insufficient supply of the raw materials, would you rather allow the market to increase prices until the point that some people are starving while others are buying ten times the food that you need to survive to feed their pets?
> Gives anybody with elementary knowledge of econ a heart attack
Plainly, this isn't true. This opinion is not uncommon amongst so-called "Marxist economists" such as Richard Wolff. You can disagree that price controls and rationing would be the best way to solve the problem, but it is outright ignorant and needlessly insulting to make this claim.
That went really well in my country 30-40 years ago.
My father once went to buy me diapers and returned with living room furniture set(ugly one also), because this was only one available since month or so, and he had to take it on the spot, because entire shipment will be gone in next few hours.
Then he had to go back to the diaper line and wait a few hours, because I wasn't impressed with the furniture enough to stop eating.
I'm not sure you really get how markets work. Price controls can have a few different effects depending on the good in question, but one of those is shortages, which can be really bad when the good is food.
People don’t decide to raise prices out of the blue… it isn’t quite this simple, but for the purpose of understanding the basic concept, you can think of it as the price goes up when you can easily sell your inventory at the current price… if your product sells out quickly, and you still have people eager to buy your product, you raise prices, and you keep raising them until you can just barely sell all your product (of course it is more complicated, because you are trying to maximize profit and not minimize inventory, but the basic idea is the same)
If you fix prices, it just means the product keeps selling out quickly and most people can’t get the product.
This is why prices go up when there is a supply shock (like with eggs and the bird flu). There are fewer eggs available, and raising prices reduces demand until it matches the supply (as people who only kinda like eggs switch to cheaper alternatives). While it sucks that eggs are more expensive, at least you can still buy them if you really like eggs. With price controls, it becomes a crapshoot on whether you can get them or not.
With eggs its kind of a different story. The price of eggs has increased for the supermarket to buy, by maybe a cent or two coming down to up to 16 cents.
Packaging takes 4 cents per egg.
Meanwhile the eggs in the supermarket cost 56 cents each.
I used it for a while but I found that too many suggestions are worthless and having to consider them makes me waste more time than just writing the code myself. For the things that it is useful like snippets, I found that ChatGPT is better anyway.
Most likely yes. I bought a new 980 Pro 2TB a few weeks ago and it came with the latest firmware. Manufacture date is Jan 2023. The firmware is already more than a year old so unless you get very old stock it should come with it.
Could you share what you did to convert the models? The mirrors aren't very reliable and it would be good to have it documented somewhere. There is some discussion about this at https://github.com/ggerganov/llama.cpp/issues/172
There's a script in the alpaca-lora repo for converting the weights back into a PyTorch dump- and my changes have since been merged https://github.com/tloen/alpaca-lora/pull/19
The llama models were trained with a context size of 2048. By default llama.cpp limits it to 512, but you can use -c 2048 -n 2048 to get the full context window.
Tokens. Short or common words tend to be one token, while less common words are composed of multiple tokens. For GPT OpenAI gives the rule of thumb that on average you need four tokens to encode three words, and LLaMA should be similar
So we have numbers on PTB original perplexity 8.79 quantized 9.68, already 10% worse. And PPL reported per token I suppose? Because word PPL for PTB must be around 20, not less than 10.
That doesn't mean that I am happy with the way our collaboration was handled. Why did you create a new converter when you knew there was already an existing pull request that addressed the same issue? Why did you modify the model format and break backwards compatibility when the current format was proven to work with mmap? Why did you change the magic string of the file format to include your initials, when there was an explicit version number field for this purpose? Why did you create a new pull request when you could have added your changes to mine? Why did you rush to merge the PR instead of taking your time to verify that everything worked properly, while listening to feedback from the other contributors and users? Why did you did you ignore concerns raised by other contributors in my PR? Why are you claiming that I was unable to make the WIN32 code work when the final version in your PR is virtually identical to mine, making me look incompetent?
Ultimately, it was my decision to move on, close my PR and allow yours to continue unchallenged, and I owned that decision every single time that I have commented about it, including in the PR linked in this post, where I recommended keeping your PR and working on fixing the issues being raised. I am sorry that some people have harassed you, but making me responsible about this is extremely unfair. There are plenty of reasons for people to feel disappointed about your behavior without me having to say anything about it.
I don't expect that anyone will believe me about this, after all I am just an "anonymous person". The truth is, I am extremely weary about posting this because I know how much damage you can do to me if you insist on this route to your followers. What is your theory, that because I am nobody I have nothing to lose? How are you not aware of the huge power imbalance between a "celebrity programmer" with thousands of followers and a nobody like me?
Anyway, all the information is publicly available on github for anyone who cares enough to verify it.
- slaren