Rendered at 17:04:47 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
hereme888 4 minutes ago [-]
Another ad posing as "science".
It's basically a Wafer/AMD advertisement.
B300 is about 46% faster for one stream and 65% faster in aggregate. AMD wins only after Wafer divides throughput // selected cloud-rental prices: $2.50/GPU-hour for MI355X versus $6 for B300.
Benchmarks are unreproducible, power costs are missing, ROCm was patched... and on and on.
Sure, it can serve that particular model at that particular size more economically. Good for them... in particular.
logicallee 11 hours ago [-]
This part sounds like AI assisted setting this up and benchmarking it:
>The fix was trivially simple: zero-pad the head count 12→16, run the fast kernel, and extract the real 12 heads from the output.
I've recently used a frontier AI (ChatGPT 5.6 Sol on ultra) to set up a much smaller local model, and the performance optimizations it introduced left the model totally incoherent. (The model just repeats a single character, etc.)
When I see a line like the one I just quoted, it leaves me wondering if the setup is still coherent like a stock install of Kimi K3 on supported hardware.
Did they run any benchmarks on it to see if it is still correct?
springtimesun 6 hours ago [-]
I have never used sol, but I regularly use Claude to set up and benchmark local models per task. It is very thorough and has always returned good setups. The only thing you have to do is make sure you point at the model card. It’s always incredulous that models exist after its training cutoff.
K3 does an ok job of setting up, but its config searching isn’t nearly as thorough and its will confidently tell you it’s found the best setup when it’s only turned a few knobs. It’s also not a good evaluator of its own output. It rates its work too highly and seems kind of defensive when benchmarking. Still a good check because it does find stuff, but open a fresh session and don’t tell it where the results came from.
What K3 does do more than any other model I’ve found is investigate folder structures. If I want to benchmark it and other models I have to move the testing methodology and any reference to other results out of the project folder bc Kimi is like an ls bloodhound. It will find them.
technoabsurdist 36 minutes ago [-]
hi I work at wafer. yes we ran benchmarks. for example our Kimi K3 is live on open router and in order to host there you have to run accuracy checks. like tau/gpqa.
and then u must pass test regarding thinking, coherency, and tool calling
GuestFAUniverse 9 hours ago [-]
How is the capex on 8 * MI354X even remotely justified at less than $10/h?
Even without the base system, power and every other expenses:
365d * 24h * $2.95 = $25842/a invoicable.
That doesn't add up within one year, that doesn't add up in three years and it is questionable that it brings in the money during the lifetime of the device?
gpugreg 8 hours ago [-]
Where do you see less than $10/h for 8 * MI354X? I can only find $2.50 for 1 * MI355X (lowest I can find for rent on other websites is $2.65, but maybe they got a better deal).
swiftcoder 8 hours ago [-]
> How is the capex on 8 * MI354X even remotely justified at less than $10/h?
Is anyone actually renting them out that cheap? The very cheapest on-demand price I see online is $14, and most providers are a lot higher
arjie 8 hours ago [-]
That can’t be real. Modal rents out an RTX 6000 Pro for more than that. Nvidia will rent your GPUs at a fixed cheap rate if you buy from them. Perhaps AMD has a different subsidy style program. Because those MI355X are going cheap here.
bensyverson 2 hours ago [-]
How does one even purchase an AMD MI355X?
trash_cat 1 hours ago [-]
Have $300k in disposible income?
inferencecoder 10 hours ago [-]
Wafer is making themselves synonymous with slop in the inference space. Exaggerated unfair comparisons in all their results, twitter hype posts with alarm emojis etc.
> $2.50/GPU-hr for the MI355X, $6.00 for the B300, and $4.25 for the B200.
This is not an accurate price comparison for real terms.
greyb 9 hours ago [-]
This is a company that launched a token subscription (WaferPass), before weeks later, rugpulling the plan for being unsustainable while simultaneously claiming they achieved incredible inference efficiency gains worthy of paying them mind.
villgax 9 hours ago [-]
I went the gpus.io website & it’s $2.95/hr right now, this is like comparing MSRP to actual market price. B300s are in demand & hence cost more, but these lazy editors at wafer.ai can't be bothered to do TCO on actual ownership nor share code to replicate their setups. Instead just relying on current market prices to win one row, which isnt even about per/$ on actual MSRPs.
YetAnotherNick 3 hours ago [-]
gpus.io shows tensorweave pricing at $2.95/hr. Tensorweave just shows "Talk to sales".
kelnos 10 hours ago [-]
I wish they wouldn't call them "open source models". They aren't open source. They didn't publish the training data. They didn't publish the tools they used to train the model.
They published the weights. It's an "open weight model", a term that it seems nearly everyone has agreed is appropriate. Why is this company not using it?
HarHarVeryFunny 4 hours ago [-]
> They didn't publish the tools they used to train the model.
That's not totally true - for example Ziphu (Z.ai, developers of GLM) have published their Slime RL-training framework, developed together with Tsinghua University.
Yes, we all realize that "open weights" is more accurate than "open source", and anyways the source code would not be very interesting - it's the training data and methods that mostly define these models.
Almondsetat 6 hours ago [-]
Sorry, where exactly is "data" in "source"?
I can understand not wanting to call it open source if they don't give you the algorithm and software used for training, but wanting the training data too? That's completely different
croes 5 hours ago [-]
For LLMs the training data is the source of their weights.
You can‘t reproduce the LLM without the same data
anon373839 5 hours ago [-]
That’s not really true. The models have source code defining their architecture and it is open-source.
People keep trying to shoehorn OSS concepts onto model weights, but the concepts don’t fit because the weights aren’t software. They aren’t compiled code. They are learned parameters to use with a (very big) function that itself is expressed in the code.
So they’re a very valuable asset that complements the code, but they are not the code. You could use randomly initialized weights and the software will work - it will output tokens. They just won’t have useful patterns.
I don’t think OSS definitions have ever required that assets have their source included. For example, artwork is very important to a game, but nobody thinks a game is not open source if it doesn’t come with sketches and a copy of Adobe Illustrator to recreate the artwork from scratch.
Edit: The distinction I would draw between models like Deepseek and models like OLMo is whether they are open science. With a model like OLMo, they have published everything you need to replicate the training experiment. Whereas Deepseek does share a lot of knowledge, but keeps a lot proprietary too.
pocketarc 5 hours ago [-]
Your game example is a great one: If a game didn’t come with its 3D models, sound, level files, game data, or assets of any kind, but its engine was open source, I don’t think anyone would say “hey this game is open source”. They’d say the engine is, but that’s it. All of the above things are not code, but they are part of a game and yes, expected to be included in an open source game.
Source as a word has a meaning that doesn't include non-source things.
SV_BubbleTime 3 hours ago [-]
That’s an open source engine, we already have a word to define what that is.
And we have Open Weights to define what those are.
gpm 2 hours ago [-]
No, an engine is only the code that is shared between games. For instance "urban terror" by frozen sands is a closed source game on top of a (now) open source engine (the Quake3 engine). Quake3 is a (now) open source game (with closed assets) on top of its own open source engine. Quake and it's derivatives are a particularly nice example of the distinction between a game and its engine because the engine includes an interpreter for the game code, leaving a very clear boundary. Meanwhile many games end up intermingling their engine and game code (e.g. see the Eve Online devs write about this - another closed source game on top of a now open source engine).
BAR is an open source game. All the game source is open.
SV_BubbleTime 2 hours ago [-]
Bro, your link literally says in the read me it is an engine.
gpm 2 hours ago [-]
No? It says
> Open source RTS game built on top of the Recoil RTS Engine
BAR is a game, Recoil (a different thing - not the repository I linked) is an engine it is built on top of. Recoil is - incidentally - a fork of spring, an engine many open source RTSes are built on.
BoxOfRain 4 hours ago [-]
Doom pioneered this model, the Doom engine was open-sourced while the assets remained proprietary. This is where projects like Freedoom exist, to create an entirely free software equivalent.
anon373839 4 hours ago [-]
I think this misses the point I was trying to make. Both an open source game and an open weights LLM include the necessary assets. But people seem to be saying, “you need everything that was used to create the assets”. For game art, that would include sketches, prior art used as inspiration, project files that aren’t used by the game engine but were used during the design process, and so on - if you apply the same standard. But I don’t think anyone does.
gpm 4 hours ago [-]
Similar to this I've never seen a project request anyone license their github PR comments under any license whatsoever even though they're undoubtedly copyrighted and used in the creation of the actual source code.
ungovernableCat 3 hours ago [-]
My understanding was that there was a lot of non determinism in the training process because of many factors: how GPUs optimise floating point arithmetic, how the compute is distributed between the thousands of GPUs etc
I'm not sure how static training data is either (or how you'd distribute it considering its size and nevermind the legality of sharing copyrighted things).
You'd likely get a model with very similar behaviour but the weights would be different.
Please someone correct me if I'm wrong.
fooker 3 hours ago [-]
This trope was valid maybe in 2022.
Model training now is not a straight forwards process of input data -> run tools -> get model.
There's a whole lot of alchemy going on. We don't quite understand what works and what doesn't. Think of it like painting with water color and having to improvise very often.
The only advantage over water color is that we can revert to a working state.
SV_BubbleTime 3 hours ago [-]
And since none of the source is provided to make the thing, it’s not open source.
Really, it’s no more open source than a free calculator. It’s free, and you can use it to no or great effect. But, you sure as hell can’t make one.
So calling it open source is without question, wrong.
fooker 2 hours ago [-]
There's no program you run to 'make the thing'.
It's mostly ad hoc scripts and some pretty horrible hacks being run by a hundred engineers trying to improve a thousand different things at once with a hundred thousand GPUs.
I'm sure once we understand the tech better, the training process will look like running a program.
WithinReason 9 hours ago [-]
If they open sourced the training data and code but you had to train the network yourself, would that be open source?
girvo 5 hours ago [-]
Which some companies have done! Nvidia, I believe, among others.
croemer 8 hours ago [-]
Yes, obviously.
swiftcoder 8 hours ago [-]
Even though none of us could actually afford to train it?
croemer 8 hours ago [-]
Some of us might be rich, or get funding, or in the future it could be useful when training is cheaper.
Open source has benefits even if you can run yourself. You can read the code for understanding/insights. Other labs could replicate/build on it.
gpugreg 8 hours ago [-]
> Some of us might be rich
I sure wish I had a few 100M of disposable income to train a frontier model.
> or in the future it could be useful when training is cheaper.
I do not think that physics will allow hardware getting that much faster. But maybe we will have different, cheaper architectures by then.
halJordan 5 hours ago [-]
You say that but for like 2 years there was a guy on huggingface releasing quants as TheBloke. No identity no nothing except he likely had a grant or a university job that let him do it. Quants aren't the same as training but it was beyond 99% of people at the time (as you say this is)
Cant stand when you guys try and force something as impossible on the rest of us simply because you could never accomplish it.
gpugreg 4 hours ago [-]
I did not say that it is impossible. I just think that we need architectural improvements, or maybe even a fundamentally different approach to get something like Kimi K3 for cheap. The point I was trying to make was that we shouldn't just laze about and hope that hardware improvements will get us there.
(Also, I know Tom Jobbins (TheBloke), and have personally contributed to increase the adoption of GGUF, e.g. in the transformers and ktransformers libraries, so I find the personal dig quite amusing.)
Muromec 8 hours ago [-]
If you would tell people at the start of 20th century how much energy we consume, they may not believe you or think it is wasteful.
Unfortunately, electricity prices did not fall by the same factor, so I fear that training a frontier model will still cause a an unsustainable dent in my monthly budget.
croemer 4 hours ago [-]
Prices have dropped by a factor of around 6 in real terms since 1925 for US household electricity.
Maybe not now, but what about 10 years down the line?
solarkraft 5 hours ago [-]
Yes.
croes 5 hours ago [-]
Yet, I couldn’t afford a PC to run the original Crysis when it came out, now the hardware isn’t an issue anymore
WithinReason 7 hours ago [-]
As an example, Grok 4 took $388M to train
HPsquared 6 hours ago [-]
Compiling source code also takes computing resources, only the scale is different. It's a very close analogy: source code with training data, and compiled binaries with model weights.
The weights are literally a binary blob.
WithinReason 6 hours ago [-]
The weights are the modifiable representation. You modify them with gradient updates.
HPsquared 5 hours ago [-]
They are a cooked stew; the ingredients have already been chopped and mixed together. You can add things, yes, but you can't inspect the ingredients.
ungovernableCat 3 hours ago [-]
If we start with the same ingredients and independently make our stews they're likely still going to taste a bit different due to the non deterministic nature of the process. Isn't it similar with training LLMs at scale? Do you get identical weights if you do multiple runs?
HPsquared 2 hours ago [-]
They don't even say what the ingredients are.
ungovernableCat 2 hours ago [-]
Yeah I understand that. I mean just the methods they use to acquire the training data has already had a shit ton of drama, there's no way the western labs are ever going to be public about the ingredients.
halJordan 5 hours ago [-]
I can also open broadcom's antenna firmware in any hex editor. Why are you arguing that makes it open source?
anon373839 5 hours ago [-]
The antenna firmware is software. Model weights are essentially learned settings, and they are not software.
Note also that software is copyrightable and model weights aren’t (in the US anyway).
croemer 4 hours ago [-]
Not sure why it matters whether weights are software or not.
One can equally argue that firmware is just settings for the CPU.
If weights aren't copyrightable then doesn't this argue against the idea of them being able to have the quality of open-sourceness? Meanwhile the training code could be copyrightable.
anon373839 4 hours ago [-]
Well, my position is that the software that defines/runs the model is the open-source part.
The weights are the asset that makes it useful, but I don’t think 40T tokens of pre-training data should be required to call the model itself open source when you can inspect every line of code in the model without that, as well as instantiate and run the model with randomly initialized weights.
inigyou 5 hours ago [-]
You can hand-patch a binary, too.
croes 5 hours ago [-]
An open source Mac OS is still open source even if I can’t afford a Mac.
solarkraft 5 hours ago [-]
Yes
stavros 9 hours ago [-]
Agreed, it's "open weights". Open source would be to publish the entire process so you could tweak it if you wanted.
charcircuit 10 hours ago [-]
The weights are the preferred form for modifying or integrating with other models. There is no obligation in open source to transitively open source all of the documentation / tools used to create the open source project.
>a term that it seems nearly everyone has agreed is appropriate
Models being considered open source even if the original training code / data is not released also is something almost everyone has agreed to be appropriate.
dietr1ch 9 hours ago [-]
> The weights are the preferred form for modifying or integrating with other models
It's the 2nd time I hear this argument and I'm already fed up with it
Is it the preferred way only because training is expensive? It's like saying binaries are the preferred way of modifying program because you can't afford to have a fast enough machine to compile it yourself.
Most people don't have resources to compile their own browser, but what makes some browsers open is access to the source.
Maybe it's the preferred way because the people sharing models are themselves working with weights and no data?
NitpickLawyer 9 hours ago [-]
> Is it the preferred way only because training is expensive?
No, it's the preferred way because that's literally how you train it. Contrary to popular misconceptions, you don't "compile" data into weights. You initialize a model (based on architecture, config, etc) and then you modify it via training. But crucially they (i.e. model creators) modify it the same way (technically speaking) as you would. That's what the license grants you. Nothing less, nothing more. The "how" as in knowhow has never been something covered by a license.
Open-weight is something dreamt up by people misunderstanding the basics of model creation and training, and having ideological biases against AI and/or LLMs. It is what it is, but you should know that you are technically wrong. A model released under an open source license (Apache, MIT, etc) is an open source model. Because the weights are the source of the models. Training is not "compilation". Training is the "how" as in knowhow to modify the model. Training deals with values. Source deals with everything, including values.
In the past, if someone would have released a piece of software (say a PID controller algo) w/ hardcoded values, no-one would bat an eye. LLMs are just that, with billions of hardcoded values. Nothing less nothing more.
teruakohatu 10 hours ago [-]
> There is no obligation in open source to transitively open source all of the documentation / tools used to create the open source project.
Open source means open source code. Open weight means a binary file dump, not unlike an exe file. There is nothing open source about it.
Its like having a closed source text editor that censors certain words, and an open source text editor that censors certain words.
The latter can easily be recompiled, the former requires reverse engineering. Both may give you a license to use them freely.
Alpha3031 9 hours ago [-]
Per the OSD definition of source code, "the source code must be the preferred form in which a programmer would modify the program." which means an argument could be made (as charcircuit is making) that the weights, being the preferred form to modify, are the source.
I do prefer open weights as being more precise (like, is it even really software that has source code in the first place?) but I feel like at this point the ship has sailed somewhat (though if this is something you're willing to spend your time arguing then... moral support I guess?)
ciupicri 8 hours ago [-]
You can also edit/patch binary executables, but no one says about that software that is open source.
Muromec 8 hours ago [-]
You can, but its not the first preference
applfanboysbgon 5 hours ago [-]
Incidentally, I do. I fucking hate the open source maximalists like Stallman who suggest that not having source code is equivalent to not having control over what runs on your computer. But you always[1] have control over what runs on your computer. Reverse engineer it if you care so much! Every form of DRM is inevitably defeated, because you do have control over program execution, regardless of access to the source code. Stallman's argument seems more lazy and entitled than principled.
[1] ...setting aside hardware attestation bullshit, which does need to die in a fire.
charcircuit 8 hours ago [-]
I think you are failing to see how the weights are the preferred form of working with a model. It's like if I shared a png with others to use as a meme template. Even if I don't share the source code to photoshop other people can use that "binary file dump" to make derivative images of their own with it.
andy99 4 hours ago [-]
I feel like the arguments being made about sharing the training data are from people who don’t have any experience training ML models and have never worked with weights. The biggest reason I have seen that people want the data is to complain about some aspect of it (copyright, bias, etc)
I would be very interested to hear someone explain what freedom it is they need the training data to enjoy.
mlazos 7 hours ago [-]
The models are open source, it’s never been a requirement for someone to document the entire process of creating something to be “open source”. Just sharing the source, in this case, the weights, meets the criteria. Software engineering’s obsession with precise terms is actually one of the things I’m glad is dying with ai automation.
andy99 7 hours ago [-]
> obsession with precise terms
They’re not really even being precise. The relevant software freedom, from the FSF is []
The freedom to study how the program works, and change it so it does your computing as you wish (freedom 1). Access to the source code is a precondition for this.
Ported to the model world, this is fulfilled by sharing the weights and implementation. There’s almost nothing that having the training data gets you (other than actually training it). The weights plus a reference implementation let you see all the states to study the behavior, and let you fine tune it to do your bidding (the abliteration etc). The freedom is satisfied.
Some might argue that without the training data you couldn’t do some classes of experiments to see how it works, say leave-one-out retraining. I’d argue things like that are not really about the model but about ML research or the class of models, which while interesting is not a free software pre-requisite.
Agreed, The spirit is fulfilled, as evidenced by the massive ongoing development of, effectively, new weights grown out of the sourced weights,
nextaccountic 7 hours ago [-]
The source is actually all training data, plus the software used for training, including some scripts or instructions to run the entire thing end to end on your own computer. That's what open source has always been about.
The weights are the output of a program, it's a binary. It's not source.
shock 6 hours ago [-]
> Software engineering’s obsession with precise terms is actually one of the things I’m glad is dying with ai automation.
Yes. The next time you go to your doctor you should hope he's not being overly precise; or the engineer that builds the bridge; or the software engineer that implemented the embedded software in your insulin pump.
There is no precise thinking without precise terms.
HPsquared 6 hours ago [-]
Model weights are literally a compressed blob of binary data. The end result of a compilation process.
ordersofmag 2 hours ago [-]
So is a zip file of source code. There is no 'compilation process'. Model training isn't a fixed end point. You start with random weights. You train. The weights get better. You do this iteratively. At some point you say 'good enough' and release. People doing further training would start with those weights and further iterate. Demanding the original training data and training process would be equivalent to demanding a completely replay-able sequence of editing steps starting with a blank text file and allowing you to replay ever edit that led the original author to the released source code.
Now there are reasons you might want to know about the training data when you wouldn't care about the authoring process used by a traditional open-source process. And these get at the reason LLM's are different than traditional software and so maybe our existing definitions of what 'open-source' means aren't a good match for LLM's. Of course there is software associated with LLM's (beyond the weight) -- defining the structure of the particular neural net those weights fit into. In every open-weights model that I'm aware of that software is open source (though trivial).
muragekibicho 10 hours ago [-]
They even left the em-dashes. Absolute slop.
" The only problem with AMD is software support — slower kernels and less day-0 support on inference frameworks make serving frontier models on AMD a real engineering effort."
jpgvm 11 hours ago [-]
If you do good work you should at least take the time to review the slop that details that work for slopiness. Otherwise it's hard to take it seriously. Especially the prefill section.
BookPage 10 hours ago [-]
People complaining about the slop - what about the atrocious text/bg contrast? Burning my eyes out faster than a B300 ever could
veber-alex 11 hours ago [-]
AI slop
IshKebab 10 hours ago [-]
Yeah I think they at least put some light effort into making it readable though. Obviously slop but not quite as bad as most slop articles.
inferencecoder 10 hours ago [-]
There is barely any effort, a simple GPT5.6 sol pro query rips the post apart.
logicallee 9 hours ago [-]
if you did that in the web interface, could you share the chat? I'd be interested to read it.
When I read your original comment, I was thinking you had just asked it to evaluate the article. (Like just "evaluate this article" or something.)
I don't think anything anyone (or any AI) has ever written or published (including Sol itself) wouldn't be torn apart by the prompt you gave though.
inferencecoder 6 hours ago [-]
I think it's fair to expect an extensive review of an article before publishing. Not everything has a set of serious flaws.
IshKebab 4 hours ago [-]
It doesn't look like it has found a set of serious flaws to me. Just nitpicking.
villgax 10 hours ago [-]
Lol, such a lazily written article by wafer.ai
GPUs. 8× MI355X (TP8) B300 (TP8+DCP8)
Decode tok/s per stream 118 tok/s 172 tok/s
Peak aggregate. 952 tok/s 1,568 tok/s
Peak aggregate per GPU 119 tok/s 196 tok/s
On every row the B300 beat the MI355X
The B200 is being forcefully compared against something which is not gonna fit within it's memory in a single node & not much details about multi-node interconnectivity, disagg or not. As expected of a shoddy slop.
The only point it won is of cost per hour is one aggregation website for rentals, the premium a B300 commands against the $3/hr AMD chip which no provider has in abundance. Never bothered to do TCO of owning the hardware either.
throwa356262 8 hours ago [-]
Did you see this section?
To the B200’s defence, its numbers are somewhat deflated by the fact that it pays a cross-node all-reduce on the decode critical path (RoCE v2 at ~195 Gb/s) — it’s the only config here that spans two nodes
It's basically a Wafer/AMD advertisement.
B300 is about 46% faster for one stream and 65% faster in aggregate. AMD wins only after Wafer divides throughput // selected cloud-rental prices: $2.50/GPU-hour for MI355X versus $6 for B300.
Benchmarks are unreproducible, power costs are missing, ROCm was patched... and on and on.
Sure, it can serve that particular model at that particular size more economically. Good for them... in particular.
>The fix was trivially simple: zero-pad the head count 12→16, run the fast kernel, and extract the real 12 heads from the output.
I've recently used a frontier AI (ChatGPT 5.6 Sol on ultra) to set up a much smaller local model, and the performance optimizations it introduced left the model totally incoherent. (The model just repeats a single character, etc.)
When I see a line like the one I just quoted, it leaves me wondering if the setup is still coherent like a stock install of Kimi K3 on supported hardware.
Did they run any benchmarks on it to see if it is still correct?
K3 does an ok job of setting up, but its config searching isn’t nearly as thorough and its will confidently tell you it’s found the best setup when it’s only turned a few knobs. It’s also not a good evaluator of its own output. It rates its work too highly and seems kind of defensive when benchmarking. Still a good check because it does find stuff, but open a fresh session and don’t tell it where the results came from.
What K3 does do more than any other model I’ve found is investigate folder structures. If I want to benchmark it and other models I have to move the testing methodology and any reference to other results out of the project folder bc Kimi is like an ls bloodhound. It will find them.
and then u must pass test regarding thinking, coherency, and tool calling
Even without the base system, power and every other expenses: 365d * 24h * $2.95 = $25842/a invoicable.
That doesn't add up within one year, that doesn't add up in three years and it is questionable that it brings in the money during the lifetime of the device?
Is anyone actually renting them out that cheap? The very cheapest on-demand price I see online is $14, and most providers are a lot higher
> $2.50/GPU-hr for the MI355X, $6.00 for the B300, and $4.25 for the B200.
This is not an accurate price comparison for real terms.
They published the weights. It's an "open weight model", a term that it seems nearly everyone has agreed is appropriate. Why is this company not using it?
That's not totally true - for example Ziphu (Z.ai, developers of GLM) have published their Slime RL-training framework, developed together with Tsinghua University.
https://github.com/THUDM/slime
Also, if you read Moonshot's Kimi 3 report, it does give a lot of architectural detail and details on training.
https://github.com/MoonshotAI/Kimi-K3/blob/main/k3_tech_repo...
Some discussion on this by HuggingFace here:
https://www.youtube.com/watch?v=MW8-kqd2SD8
Yes, we all realize that "open weights" is more accurate than "open source", and anyways the source code would not be very interesting - it's the training data and methods that mostly define these models.
I can understand not wanting to call it open source if they don't give you the algorithm and software used for training, but wanting the training data too? That's completely different
You can‘t reproduce the LLM without the same data
People keep trying to shoehorn OSS concepts onto model weights, but the concepts don’t fit because the weights aren’t software. They aren’t compiled code. They are learned parameters to use with a (very big) function that itself is expressed in the code.
So they’re a very valuable asset that complements the code, but they are not the code. You could use randomly initialized weights and the software will work - it will output tokens. They just won’t have useful patterns.
I don’t think OSS definitions have ever required that assets have their source included. For example, artwork is very important to a game, but nobody thinks a game is not open source if it doesn’t come with sketches and a copy of Adobe Illustrator to recreate the artwork from scratch.
Edit: The distinction I would draw between models like Deepseek and models like OLMo is whether they are open science. With a model like OLMo, they have published everything you need to replicate the training experiment. Whereas Deepseek does share a lot of knowledge, but keeps a lot proprietary too.
Source as a word has a meaning that doesn't include non-source things.
And we have Open Weights to define what those are.
BAR is an open source game. All the game source is open.
> Open source RTS game built on top of the Recoil RTS Engine
BAR is a game, Recoil (a different thing - not the repository I linked) is an engine it is built on top of. Recoil is - incidentally - a fork of spring, an engine many open source RTSes are built on.
I'm not sure how static training data is either (or how you'd distribute it considering its size and nevermind the legality of sharing copyrighted things).
You'd likely get a model with very similar behaviour but the weights would be different.
Please someone correct me if I'm wrong.
Model training now is not a straight forwards process of input data -> run tools -> get model.
There's a whole lot of alchemy going on. We don't quite understand what works and what doesn't. Think of it like painting with water color and having to improvise very often.
The only advantage over water color is that we can revert to a working state.
Really, it’s no more open source than a free calculator. It’s free, and you can use it to no or great effect. But, you sure as hell can’t make one.
So calling it open source is without question, wrong.
It's mostly ad hoc scripts and some pretty horrible hacks being run by a hundred engineers trying to improve a thousand different things at once with a hundred thousand GPUs.
I'm sure once we understand the tech better, the training process will look like running a program.
Open source has benefits even if you can run yourself. You can read the code for understanding/insights. Other labs could replicate/build on it.
I sure wish I had a few 100M of disposable income to train a frontier model.
> or in the future it could be useful when training is cheaper.
I do not think that physics will allow hardware getting that much faster. But maybe we will have different, cheaper architectures by then.
Cant stand when you guys try and force something as impossible on the rest of us simply because you could never accomplish it.
(Also, I know Tom Jobbins (TheBloke), and have personally contributed to increase the adoption of GGUF, e.g. in the transformers and ktransformers libraries, so I find the personal dig quite amusing.)
Unfortunately, electricity prices did not fall by the same factor, so I fear that training a frontier model will still cause a an unsustainable dent in my monthly budget.
https://chatgpt.com/share/6a6f3f3b-7624-83ed-a11a-248cb39728...
The weights are literally a binary blob.
Note also that software is copyrightable and model weights aren’t (in the US anyway).
One can equally argue that firmware is just settings for the CPU.
If weights aren't copyrightable then doesn't this argue against the idea of them being able to have the quality of open-sourceness? Meanwhile the training code could be copyrightable.
The weights are the asset that makes it useful, but I don’t think 40T tokens of pre-training data should be required to call the model itself open source when you can inspect every line of code in the model without that, as well as instantiate and run the model with randomly initialized weights.
>a term that it seems nearly everyone has agreed is appropriate
Models being considered open source even if the original training code / data is not released also is something almost everyone has agreed to be appropriate.
It's the 2nd time I hear this argument and I'm already fed up with it
Is it the preferred way only because training is expensive? It's like saying binaries are the preferred way of modifying program because you can't afford to have a fast enough machine to compile it yourself.
Most people don't have resources to compile their own browser, but what makes some browsers open is access to the source.
Maybe it's the preferred way because the people sharing models are themselves working with weights and no data?
No, it's the preferred way because that's literally how you train it. Contrary to popular misconceptions, you don't "compile" data into weights. You initialize a model (based on architecture, config, etc) and then you modify it via training. But crucially they (i.e. model creators) modify it the same way (technically speaking) as you would. That's what the license grants you. Nothing less, nothing more. The "how" as in knowhow has never been something covered by a license.
Open-weight is something dreamt up by people misunderstanding the basics of model creation and training, and having ideological biases against AI and/or LLMs. It is what it is, but you should know that you are technically wrong. A model released under an open source license (Apache, MIT, etc) is an open source model. Because the weights are the source of the models. Training is not "compilation". Training is the "how" as in knowhow to modify the model. Training deals with values. Source deals with everything, including values.
In the past, if someone would have released a piece of software (say a PID controller algo) w/ hardcoded values, no-one would bat an eye. LLMs are just that, with billions of hardcoded values. Nothing less nothing more.
Open source means open source code. Open weight means a binary file dump, not unlike an exe file. There is nothing open source about it.
Its like having a closed source text editor that censors certain words, and an open source text editor that censors certain words.
The latter can easily be recompiled, the former requires reverse engineering. Both may give you a license to use them freely.
I do prefer open weights as being more precise (like, is it even really software that has source code in the first place?) but I feel like at this point the ship has sailed somewhat (though if this is something you're willing to spend your time arguing then... moral support I guess?)
[1] ...setting aside hardware attestation bullshit, which does need to die in a fire.
I would be very interested to hear someone explain what freedom it is they need the training data to enjoy.
They’re not really even being precise. The relevant software freedom, from the FSF is []
Ported to the model world, this is fulfilled by sharing the weights and implementation. There’s almost nothing that having the training data gets you (other than actually training it). The weights plus a reference implementation let you see all the states to study the behavior, and let you fine tune it to do your bidding (the abliteration etc). The freedom is satisfied.Some might argue that without the training data you couldn’t do some classes of experiments to see how it works, say leave-one-out retraining. I’d argue things like that are not really about the model but about ML research or the class of models, which while interesting is not a free software pre-requisite.
[] https://www.gnu.org/philosophy/free-sw.html#four-freedoms
The weights are the output of a program, it's a binary. It's not source.
Yes. The next time you go to your doctor you should hope he's not being overly precise; or the engineer that builds the bridge; or the software engineer that implemented the embedded software in your insulin pump.
There is no precise thinking without precise terms.
Now there are reasons you might want to know about the training data when you wouldn't care about the authoring process used by a traditional open-source process. And these get at the reason LLM's are different than traditional software and so maybe our existing definitions of what 'open-source' means aren't a good match for LLM's. Of course there is software associated with LLM's (beyond the weight) -- defining the structure of the particular neural net those weights fit into. In every open-weights model that I'm aware of that software is open source (though trivial).
" The only problem with AMD is software support — slower kernels and less day-0 support on inference frameworks make serving frontier models on AMD a real engineering effort."
When I read your original comment, I was thinking you had just asked it to evaluate the article. (Like just "evaluate this article" or something.)
I don't think anything anyone (or any AI) has ever written or published (including Sol itself) wouldn't be torn apart by the prompt you gave though.
GPUs. 8× MI355X (TP8) B300 (TP8+DCP8)
Decode tok/s per stream 118 tok/s 172 tok/s
Peak aggregate. 952 tok/s 1,568 tok/s
Peak aggregate per GPU 119 tok/s 196 tok/s
On every row the B300 beat the MI355X
The B200 is being forcefully compared against something which is not gonna fit within it's memory in a single node & not much details about multi-node interconnectivity, disagg or not. As expected of a shoddy slop.
The only point it won is of cost per hour is one aggregation website for rentals, the premium a B300 commands against the $3/hr AMD chip which no provider has in abundance. Never bothered to do TCO of owning the hardware either.