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

Qwen3.5 Fine-Tuning Guide

unsloth.ai

Post reply on HN
Print view View original

11–20 of 118 posts

Re: Qwen3.5 Fine-Tuning Guide

#11

Post by esafak »

antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

I would like model adaptation algorithms like Doc-to-LoRA (https://pub.sakana.ai/doc-to-lora/) to go mainstream.

Re: Qwen3.5 Fine-Tuning Guide

#12

Post by danielhanchen »

antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

These are fair points considering LLMs are getting smarter and better every week - but to be fair the biggest benefits of finetuning / RL are still not yet realized:

1. If we have robots at home, they need some sort of efficient continual learning, which could be on the go finetuning / RL via some small LoRA - this will need to do multimodal finetuning with sparse reward signals - one could also imagine all data is aggregated to one central processing center after anonymization, and training a larger model with more data + RL like that

2. Agreed images, audio, video etc is what still LoRA does well - the guide at https://unsloth.ai/docs/models/qwen3.5/fine-tune is actually a vision + text finetuning guide, so you can finetune the vision layers on your own use case

3. Model routing is going to be more the norm in the future - ie locally smallish models with LoRA for continuous finetuning can be used, but complex tasks can be offloaded to a large LLM in the cloud.

4. I also wrote about more use-cases below on the post - DoorDash, Vercel, Mercor, Stripe, NASA, Perplexity, Cursor and many others all do finetuning - for eg Cursor, Perplexity finetune large OSS LLMs themselves for their specific product lines - so there is definitely value if you have the data for it.

Re: Qwen3.5 Fine-Tuning Guide

#13

Post by antirez »

ranger_danger wrote: post #7
antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

where it makes sense IMO is when you need it to know about a large amount of information that's not already in the model, such as a company knowledgebase, code repositories or a trove of specialized legal documents... in that case it's not realistic to try to stuff the context window every time with that information, especially if you're trying to make a responsive chat bot.

With the current context windows and the ability those models did RL to work as agents, it's much faster and reliable for them to use tools and find the information before replying. Much better, no hallucinations problems (or a lot less), no fine tuning needed when information changes. I believe it is exactly in this case that fine tuning is no longer useful, and even in the past worked at very different degrees of quality.

Re: Qwen3.5 Fine-Tuning Guide

#14

Post by dotancohen »

ranger_danger wrote: post #7
antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

where it makes sense IMO is when you need it to know about a large amount of information that's not already in the model, such as a company knowledgebase, code repositories or a trove of specialized legal documents... in that case it's not realistic to try to stuff the context window every time with that information, especially if you're trying to make a responsive chat bot.

Wouldn't a RAG make more sense for this use case?

Re: Qwen3.5 Fine-Tuning Guide

#15

Post by derwiki »

prettyblocks wrote: post #8
antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

I think the biggest case for fine tuning is probably that you can take small models, fine tune them for applications that require structured output, and then run cheap inference at scale. "Frontier LLMs can do it with enough context" is not really a strong argument against fine-tuning, because they're expensive to run.

Exactly, inference cost is a very good reason to fine tune with something like Qwen

Re: Qwen3.5 Fine-Tuning Guide

#16

Post by butILoveLife »

prettyblocks wrote: post #8
antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

I think the biggest case for fine tuning is probably that you can take small models, fine tune them for applications that require structured output, and then run cheap inference at scale. "Frontier LLMs can do it with enough context" is not really a strong argument against fine-tuning, because they're expensive to run.

This is literally what I'm waiting for. I want a ~8B model that works well with OpenClaw.

Re: Qwen3.5 Fine-Tuning Guide

#17

Post by KronisLV »

antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

> But now, why?

Because these models are good in general but their Latvian output is half-drivel, like the roots of the words are usually the right ones, but not the rest.

That, and EuroLLM is really slow to release new models that would be similarly good off the shelf.

Re: Qwen3.5 Fine-Tuning Guide

#18

Post by canyon289 »

danielhanchen wrote: post #12
antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

These are fair points considering LLMs are getting smarter and better every week - but to be fair the biggest benefits of finetuning / RL are still not yet realized: 1. If we have robots at home, they need some sort of efficient continual learning, which could be on the go finetuning / RL via some small LoRA - this will need to do multimodal finetuning with sparse reward signals - one could also imagine all data is a…

I work on Gemma and Gemini models I want to echo Daniel's point here. Small finetuned models have their place even with larger general purpose models.

For example last year with Daniel/Unsloth's help we released a tiny specialized model that can get equivalent to Gemini level purpose specifically for FC. For folks that need efficient limited purpose models small models like this can fit a specific need.

https://blog.google/innovation-and-ai/technology/developers-...

Especially on device. https://developers.googleblog.com/on-device-function-calling...

It's the same with chips, we have general purpose CPUs but we still have specialized silicon for tasks that are smaller, more power efficient, cheaper, and because they're single purpose it simplifies and derisks certain designs.

And I have to add, if you want to learn about finetuning models efficiently the Unsloth guides are at the top of my list. They're practical, have all the technical details, and most importantly Daniel and the others are working around the clock to keep it up to date in what is an incredibly fast moving space of models and hardware. I am continually astounded by their work.

Re: Qwen3.5 Fine-Tuning Guide

#19

Post by abhgh »

antirez wrote: post #6

Fine tuning is a story that is nice to tell but that with modern LLMs makes less and less sense. Modern LLMs are so powerful that they are able to few shot learn complicated things, so a strong prompt and augmenting the generation (given the massive context window of Qwen3.5, too) is usually the best option available. There are models for which fine tuning is great, like image models: there with LoRa you can get good…

They are great for specialized use-cases: (a) where the problem is not hard enough (you don't need reasoning), or (b) diverse enough (you don't need a world model), (c) you want cheap inference (and you can make it happen hardware-wise) and (d) you either have enough data or a workflow that accumulates data (with fine tuning with enough data you can sometimes beat a premier model while ensuring low latency - ofc, assuming (a) and (b) apply).

I make it sound like a rare perfect storm needs to exist to justify fine tuning, but these circumstances are not uncommon - to an extent (a), (c) and (d) were already prerequisites for deploying traditional ML systems.

Re: Qwen3.5 Fine-Tuning Guide

#20

Post by prettyblocks »

butILoveLife wrote: post #16
prettyblocks wrote: post #8

Earlier quoted context omitted.

I think the biggest case for fine tuning is probably that you can take small models, fine tune them for applications that require structured output, and then run cheap inference at scale. "Frontier LLMs can do it with enough context" is not really a strong argument against fine-tuning, because they're expensive to run.

This is literally what I'm waiting for. I want a ~8B model that works well with OpenClaw.

I don't think you will get that anytime soon because for a model to work well with something like openclaw it needs a massive context window.
Post reply on HN