search

lamini-ai / lamini

The Official Python Client for Lamini's API
https://lamini.ai/
Apache License 2.0
2.52k stars 151 forks source link

How to fine tune the model ? #14

Closed imrankh46 closed 1 year ago

imrankh46 commented 1 year ago

I fine tune the model with instructions using peft but they performance are not good. Is there any other way to fine tune? Without instructions I try small model and they work well but I want to do instructions....

MooTong123 commented 1 year ago

same question, is there any suggested README.md file to show how to fine tune the model?

datalee commented 1 year ago

and which methods to use in the lamini

ninazwei90 commented 1 year ago

Hey all! @imrankh46 @MooTong123 @datalee Thanks for your understanding of our delayed responses. We've been cooking up a lot of exciting features. Re: how to fine-tune, here is a list of resources to help you fine-tune with Lamini and also learn more about fine-tuning:

  1. Many walkthroughs in our docs for finetuning: https://lamini-ai.github.io/Examples/llama_v2_example/
  2. How to finetune with Lamini: https://www.lamini.ai/blog/free-fast-and-furious-finetuning
  3. Finetuning course: https://www.lamini.ai/blog/finetuning-llms-with-our-ceo-sharon-zhou-andrew-ng

Please let us know if you still need help! Also, thanks so much for using Lamini and reporting issues! We'd love to learn from you and see how we can improve Lamini for you! If you're open to a 20-30 min chat (in exchange for Lamini free credits), please email me at nina@lamini.ai. Looking forward!!

ShreyaGupta08 commented 1 year ago

@datalee depending on the runner you were using to instantiate the LLM, you can checkout the docs for the methods and arguments.