Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

QwQ-32B: Embracing the Power of Reinforcement Learning

qwenlm.github.io

Post reply on HN
Print view View original

91–100 of 178 posts

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#91

Post by anon373839 »

antirez wrote: post #39

Note the massive context length (130k tokens). Also because it would be kinda pointless to generate a long CoT without enough context to contain it and the reply. EDIT: Here we are. My first prompt created a CoT so long that it catastrophically forgot the task (but I don't believe I was near 130k -- using ollama with fp16 model). I asked one of my test questions with a coding question totally unrelated to what it say…

> Note: Ollama "/show info" shows that the context size set is correct.

That's not what Ollama's `/show info` is telling you. It actually just means that the model is capable of processing the context size displayed.

Ollama's behavior around context length is very misleading. There is a default context length limit parameter unrelated to the model's capacity, and I believe that default is a mere 2,048 tokens. Worse, when the prompt exceeds it, there is no error -- Ollama just silently truncates it!

If you want to use the model's full context window, you'll have to execute `/set parameter num_ctx 131072` in Ollama chat mode, or if using the API or an app that uses the API, set the `num_ctx` parameter in your API request.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#92

Post by moffkalast »

AustinDev wrote: post #63
antirez wrote: post #39

Note the massive context length (130k tokens). Also because it would be kinda pointless to generate a long CoT without enough context to contain it and the reply. EDIT: Here we are. My first prompt created a CoT so long that it catastrophically forgot the task (but I don't believe I was near 130k -- using ollama with fp16 model). I asked one of my test questions with a coding question totally unrelated to what it say…

I tried the 'Strawberry' question which generated nearly 70k words of CoT.

I think you guys might be using too low of a temperature, it never goes beyond like 1k thinking tokens for me.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#93

Post by igleria »

Imustaskforhelp wrote: post #89
mohsen1 wrote: post #85

Gets really stuck with my query which R1 figures out after some thinking First 3 odd numbers without e in their spelling

Doesn't every odd number has a e ? one three five seven nine Is this a riddle which has no answer ? or what? why are people on internet saying its answer is one huh??

given one, three, five, seven, nine (odd numbers), seems like the machine should have said "there are no odd numbers without an e" since every odd number ends in an odd number, and when spelling them you always have to.. mention the final number.

these LLM's don't think too well.

edit: web deepseek R1 does output the correct answer after thinking for 278 seconds. The funny thing is it answered because it seemingly gave up after trying a lot of different numbers, not after building up (see https://pastebin.com/u2w9HuWC )

----

After examining the spellings of odd numbers in English, it becomes evident that all odd numbers contain the letter 'e' in their written form. Here's the breakdown:

1. *1*: "one" (contains 'e') 2. *3*: "three" (contains 'e') 3. *5*: "five" (contains 'e') 4. *7*: "seven" (contains 'e') 5. *9*: "nine" (contains 'e') 6. All subsequent odd numbers (e.g., 11, 13, 15...) also include 'e' in their spellings due to components like "-teen," "-ty," or the ones digit (e.g., "one," "three," "five").

*Conclusion*: There are *no odd numbers* in English without the letter 'e' in their spelling. Therefore, the first three such numbers do not exist.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#94

Post by laurent_du »

There's a very simple math question I asked every "thinking" models and every one of them not only couldn't solve it, but gave me logically incorrect answers and tried to gaslight me into accepting them as correct. QwQ spend a lot of time on a loop, repeating the same arguments over and over that were not leading to anything, but eventually it found a correct argument and solved it.

So as far as I am concerned this model is smarter than o1 at least in this instance.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#95

Post by sReinwald »

zamadatix wrote: post #72
wizee wrote: post #50

Earlier quoted context omitted.

Ollama defaults to a context of 2048 regardless of model unless you override it with /set parameter num_ctx [your context length]. This is because long contexts make inference slower. In my experiments, QwQ tends to overthink and question itself a lot and generate massive chains of thought for even simple questions, so I'd recommend setting num_ctx to at least 32768. In my experiments of a couple mechanical engineeri…

I always see: /set parameter num_ctx Explained but never the follow up: /save So you don't have to do the parameter change every load. Is there a better way or is it kind of like setting num_ctx in that "you're just supposed to know"?

You can also set

    OLLAMA_CONTEXT_LENGTH=
as an environment variable to change ollama's default context length.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#96

Post by antirez »

anon373839 wrote: post #91
antirez wrote: post #39

Note the massive context length (130k tokens). Also because it would be kinda pointless to generate a long CoT without enough context to contain it and the reply. EDIT: Here we are. My first prompt created a CoT so long that it catastrophically forgot the task (but I don't believe I was near 130k -- using ollama with fp16 model). I asked one of my test questions with a coding question totally unrelated to what it say…

> Note: Ollama "/show info" shows that the context size set is correct. That's not what Ollama's `/show info` is telling you. It actually just means that the model is capable of processing the context size displayed. Ollama's behavior around context length is very misleading. There is a default context length limit parameter unrelated to the model's capacity, and I believe that default is a mere 2,048 tokens. Worse,…

Ok, this explains why QwQ is working great on their chat. Btw I saw this thing multiple times: that ollama inference, for one reason or the other, even without quantization, somewhat had issues with the actual model performance. In one instance the same model with the same quantization level, if run with MLX was great, and I got terrible results with ollama: the point here is not ollama itself, but there is no testing at all for this models.

I believe that models should be released with test vectors at t=0, providing what is the expected output for a given prompt for the full precision and at different quantization levels. And also for specific prompts, the full output logits for a few tokens, so that it's possible to also compute the error due to quantization or inference errors.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#97

Post by h0l0cube »

whatshisface wrote: post #79
h0l0cube wrote: post #77

Earlier quoted context omitted.

They will, out of sheer necessity. Local industries will be incentivized to restart. And of course, there are already carve-outs for the automotive sector that needs steel, overseas components, etc. I expect more carve-outs will be made, esp. for the military. I don't think the tariffs are being managed intelligently, but they will have the intended effect of moving manufacturing back to the US, even if, in the short…

You're thinking about the bolt factory that will open, but what about the factories that close? Putting, as you say, businesses in peril, gets rid of jobs. As for the carve-outs, there isn't a single US industry that doesn't rely on imports from lower down the supply chain.

Protectionist policy, if applied consistently, will actually lead to more jobs (and higher wages) eventually, but also higher inflation and job losses in the short term, and a more insular economy. It's foolish to go so hard, and so fast – or this is just a negotiation tactic – so I think the Trump administration is going to compromise by necessity, but in time supply chains will adjust to the new reality, and tariffs can increase.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#98

Post by anon373839 »

antirez wrote: post #96
anon373839 wrote: post #91

Earlier quoted context omitted.

> Note: Ollama "/show info" shows that the context size set is correct. That's not what Ollama's `/show info` is telling you. It actually just means that the model is capable of processing the context size displayed. Ollama's behavior around context length is very misleading. There is a default context length limit parameter unrelated to the model's capacity, and I believe that default is a mere 2,048 tokens. Worse,…

Ok, this explains why QwQ is working great on their chat. Btw I saw this thing multiple times: that ollama inference, for one reason or the other, even without quantization, somewhat had issues with the actual model performance. In one instance the same model with the same quantization level, if run with MLX was great, and I got terrible results with ollama: the point here is not ollama itself, but there is no testin…

The test vectors idea is pretty interesting! That's a good one.

I haven't been able to try out QwQ locally yet. There seems to be something wrong with this model on Ollama / my MacBook Pro. The text generation speed is glacial (much, much slower than, say Qwen 72B at the same quant). I also don't see any MLX versions on LM Studio yet.

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#99

Post by ithkuil »

UncleOxidant wrote: post #47
holoduke wrote: post #34

Earlier quoted context omitted.

Have you heard of Jevons paradox? That says that whenever new tech is used to make something more efficient the tech is just upscaled to make the product quality higher. Same here. Deepseek has some algoritmic improvements that reduces resources for the same output quality. But increasig resources (which are available) will increase the quality. There will be always need for more compute. Nvidia is not in trouble. Th…

I agree that the Jevons paradox can apply here, however, there have been several "breakthroughs" in the last couple of months (R1, diffusion LLMs, this) that really push the amount of GPU compute down such that I think it's going to be problematic for companies that went out and bought boatloads of GPUs (like OpenAI, for example). So while it might not be bad news for NVidia (given Jevons) it does seem to be bad news…

I don't quite understand the logic.

Even if you have cheaper models if you have tons of compute power you can do more things than if you had less compute power!

You can experiment with huge societies of agents, each exploring multitude of options. You can run world models where agents can run though experiments and you can feed all this back to a single "spokesperson" and you'll have an increase in intelligence or at the very least you'll able to distill the next generation models with that and rinse and repeat.

I mean I welcome the democratizing effect of this but I fail to understand how this is something that is so readily accepted as a doom scenario for people owning or building massive compute.

If anything, what we're witnessing is the recognition that useful stuff can be achieved by multiplying matrices!

Re: QwQ-32B: Embracing the Power of Reinforcement Learning

#100

Post by cubefox »

Leary wrote: post #55
cubefox wrote: post #37

Earlier quoted context omitted.

How do you know this model is the same as in the blog post?

One of the people on the Qwen team tweeted this instruction.

Thanks. I just saw they also link to https://chat.qwen.ai/?models=Qwen2.5-Plus in the blog post.
Post reply on HN