How much data do you need to fine tune a model?
[flagged]
Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
11–20 of 47 posts
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#12Why is there still a hard VRAM requirement that's dependent on the model size? Isn't that exactly what this project is supposed to solve?
[flagged]
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#13This seems really interesting - I was curious about this line from the website. “The whole post-training stack in one CLI. Soup doctors your data pre-flight, picks the method, writes the config, derives evals from your own data, gates every save, and self-corrects reward hacking mid-run instead of just halting.” How does soup auto tune the hyper parameters and make some of these more complex training decisions?
[flagged]
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#14Looks cool, I'll try this when I get home. I have a couple of comments about https://trysoup.dev > Get Started for Free Does this mean that this will not be free at some point? The website is difficult to read (gray on black doesn't work well for me).
[dead]
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#15How much data do you need to fine tune a model?
[flagged]
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#16I run a fine-tuned 4B for AML compliance at community banks — the ROI math is exactly this
[flagged]
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#17Small open weight local models are the future. While hosted mega models make headlines for doing cool stuff, the vast majority of applications for AI simply don't need all that power, and thus cost. That’s a big part of why businesses are screaming that there’s no ROI from AI. Brining this tech down into small local models is likely where this all converges for the vast majority of use cases and what solves the prese…
[dead]
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#18Small open weight local models are the future. While hosted mega models make headlines for doing cool stuff, the vast majority of applications for AI simply don't need all that power, and thus cost. That’s a big part of why businesses are screaming that there’s no ROI from AI. Brining this tech down into small local models is likely where this all converges for the vast majority of use cases and what solves the prese…
If you are into small local models I highly recommend vibe thinker. It's a model trained specifically for reasoning. Basically a problem solver. When compared with other models, on math problems benchmarks, it's closer to models hundred times its size than ten times its size which it beats comfortably. It supports long contexts on limited VRAM and is blazing fast. https://github.com/WeiboAI/VibeThinker
Wat. Those are some crazy benchmark scores for a 3B model
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#19This looks cool - what 4 GB GPU laptop do you recommend?
Re: Show HN: Fine-tune an 8B model on a 4 GB laptop GPU
#20This looks cool - what 4 GB GPU laptop do you recommend?
[flagged]