this post was submitted on 27 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
 

My main usecase for LLMs is literally as an auto-complete, mainly via coding, so I was wondering whether anyone has played with/had any luck using the base model for use cases that are close to simply auto completing? I could imagine the instruction tuning adding a sycophancy bias in those areas

you are viewing a single comment's thread
view the rest of the comments
[–] phree_radical@alien.top 1 points 11 months ago (1 children)

I'm the local "examples/completion is better than chat/instruction" nut

I advise developers to learn how to use few-shot examples and completion instead of writing programs that beg chatbots to do a task. Chat/instruction imposes severe limitations, while examples/completion can peform virtually any task you can think of without need for fine-tuning

Here are some examples:  classificationrewrite sentence copying styleclassifybasic Q&A examplefact check yes/norewrite copying style and sentimentextract list of musiciansclassify user intenttool choicerewrite copying style againflag/filter objectionable contentdetect subject changesclassify professionextract customer feedback into jsonwrite using specified wordsfew-shot cheese informationanswer questions from contextclassify sentiment w/ probabilitiessummarizereplace X in conversation

[–] wojcech@alien.top 1 points 11 months ago (1 children)

Just to be clear, you aren't doing fine tuning here as in gradient updates, you are using the base model + ICL?

[–] phree_radical@alien.top 1 points 11 months ago

Yep, basically like taking a few samples from a dataset and turning them into a short text "document" with an obvious pattern so the LLM will complete it

Few-shot vs fine-tuning comparison:

Pros:

  • converge behavior with much fewer examples
  • dynamic. changes to "dataset" applied without modifying model weights
  • no worry about whether important information is lost
  • can do things like average logits of single-token classification problems from multiple inferences (work around context length limitations)

Cons:

  • needs context length, so can't provide too many examples or too large
  • sometimes need "adversarial" examples to discourage repetition of text from other examples
  • models that are too small have worse ICL