[HN Gopher] How to Fine-Tune Llama 3 for Customer Service
___________________________________________________________________
How to Fine-Tune Llama 3 for Customer Service
Author : makaimc
Score : 46 points
Date : 2024-07-24 14:10 UTC (9 hours ago)
(HTM) web link (symbl.ai)
(TXT) w3m dump (symbl.ai)
| sixhobbits wrote:
| There are some interesting challenges in fine tuning LLMs but
| this doesn't seems to address them.
|
| I'm not sure if the code samples actually work but they look
| super generic, and eg it talks about using "accuracy" to evaluate
| and a test split of 10% in a way that doesn't make sense to me.
|
| An LLM is never going to perfectly generate the same answer as
| your gold standard answer, so evaluating your model is a
| challenge on its own that would have been great to address here,
| but was skipped over in favour of an ad.
|
| Also a lot of the stuff under "why fine tune" seems off. You can
| do most of that stuff with an LLM directly without fine tuning.
|
| Overall this post _looks_ a lot like the in depth, long form
| content I usually love seeing on HN, but I am suspicious that it
| is actually vapourware that follows the form of a technical guide
| without actually being one (eg written by someone nontechnical or
| partially auto generated)
___________________________________________________________________
(page generated 2024-07-24 23:15 UTC)