You must log in or register to comment.
- 19 days
If the kink you’re referring to is the amount of time Qwen’s “thinking” about your greeting, that’s not necessarily actually a problem. I’ve seen common misconceptions about exactly this kind of scenario.
Models like these are trained to follow instructions. When they receive a user input they think “what is the user asking me to do, and how do I go about doing it?”
If all you’ve said is “Hi”, that leaves them with a huge puzzle and no hints how to solve it. What does the user want them to do? Is this a test? Did they start writing an actual instruction and accidentally hit enter partway through? Do they want me to write a “hello world” app, and if so in what language? Is this the outout of a “hello world” app that I wrote in a previous round that I now need to check up on?
Qwen’s models are known to be rather “thinky” in the first place - it’s part of how they’re able to hit so high above their weight class - so it’s not surprising that it’s taking its time to figure out this challenge you’ve presented it with.
- fibojoly@sh.itjust.worksEnglish19 days
Oh thank fuck. I thought I was going crazy… My first attempt at local models was a Qwen. A base model. I swear to god all I said was hello and the thing started and never stopped. I guess that’s what a filibuster must be like? It was both amazing, yet terrifying. I’ve a bit more xp now, but yeah Qwen and really really thinky, dear gods ! My colleague got himself an abliterated one and just leave it to run overnight trying to pentest shit in his home network, but I guess I prefer something a bit more hands on, myself.
- 19 days
Heh. I use Qwen3.8-27B as my main coding agent, and I sometimes feel really bad for it as I watch the stream of thought go by filled with “wait… am I doing this right? What if I’m completely wrong about this? Is this really what I should be doing??” I want to pet it and assure it that it should have more confidence in itself. :)
But it’s the tradeoff that Qwen made to cram that much smarts into such a small bundle of parameters, I guess.
- fibojoly@sh.itjust.worksEnglish18 days
Yeah, I can see that but it’s horrendously slow, I find. I tried a 3.8 online and I just dont’ like the way it works, overall :( It goes on and on and on and never stops to ask despite that being one of my main rules.
- 18 days
There’s a fine-tuned version called Swift that’s been trained to use 58.3% fewer reasoning tokens, apparently with almost no loss of quality. I’ve not been in a hurry with my personal usage (I set my coding agent loose on a task and then go have tea or whatever) so I haven’t experimented with it much but it might be worth checking out if the verbosity of reasoning is a problem.
Qwen4 will be coming out soon too, it has a 27B version, so perhaps they’ll have incorporated more efficient reasoning into it from the start. I’m looking forward to testing it out.
- Hazzard@lemmy.zipEnglish18 days
Good tip! I’ll definitely be checking this out, as someone who also uses Qwen3.8 27B. The capability leap over the model I used before is definitely worthwhile, but wow does it overthink really easily.
- [object Object]@lemmy.caEnglish18 days
What’s your use case? I’ve found Qwen 3.5 4b to be fairly useless. Decent for like summarizing stuff or generating annotations on things, but that’s about it.
- Xer'lodrav@szmer.infoEnglish17 days
Qwen3.5-4B-3D-Coder (finetune) with video example seems kinda useful, and quite impressive for its size! I haven’t tested it personally though.
18 daysI don’t know, I was just kinda playing around to see if it would work at all. I think the laptop is a bit too old for anything. But I can use my desktop to build python scripts that I can run on the laptop maybe.
- [object Object]@lemmy.caEnglish18 days
Then 4b or even smaller is probably fine, it’s surprising what even sub 1b models can do if you have a good use case
- ImgurRefugee114@reddthat.comEnglish16 days
A subagent run seemed to be taking a while yesterday (qwen 3.8 Flash Next IQ3; only ever happened once to me so far)
- ImgurRefugee114@reddthat.comEnglish15 days
It’s the “I should stop this odd repetition. Let me think clearly: hmm hmm hmm hmm” trailing off that really gets me
I’m trying to use an old HP zBook. I was told it would be faster.
- BeefAndPoultry@lemmus.orgEnglish19 days
what are the specs? Try Ling 3.0 Tiny, that’s probably the fastest decent model, it should be both smarter and faster than Qwen 3.5 4b
