Can you share a bit more on which tasks are you discussing about?
Re:Mistral Fine-Tune
by anon373839 on Saturday May 25, 2024 @06:57AM
(#40474169)
Not the OP, but you can take a look at https://spacy.io/usage/spacy-101 to get a sense of what traditional NLP tasks look like. These things can be done much faster than LLMs with appropriate tooling (such as spaCy) and they don’t risk hallucination.
Re:Mistral Fine-Tune
by maaaaattttt on Saturday May 25, 2024 @07:44AM
(#40474313)
I’ve tried PII anonymization with standard NLP approaches and LLMs have been (way) better at this task in my experience.
Also you can do it at scale with SparkNLP: https://sparknlp.org
Many of the use cases I've seen for LLMs would actually be better with NLP.
Re:Mistral Fine-Tune
by meandmycode on Saturday May 25, 2024 @07:52AM
(#40474362)
Which kinds of use cases?
In this comment I was referring to POS tagging and feature extraction.
Another use case for fine tuning we have as well is to reduce a 5-shot prompt that we have to run hundreds of times per request down to a “0-shot” (heavy emphasis on the double quotes.
Run five shot on gpt-4o a couple thousand times, then fine tune on cohere’s command-r or haiku or llama3 8b or whichever small but mighty llm. You can reduce costs by 99%, or somewhere in that ballpark, without really sacrificing quality on 99% of the queries.
It's a narrow domain, but so is most of programming. I think if you're just training a general purpose LLM to be more inclined towards your data -- no, fine tuning is probably not very relevant. But if you're trying to solve a very specific yet fuzzy problem, and LLMs can get you _part_ of the way there, fine tuning is likely your best bet.