Discussing the article: "Integrate Your Own LLM into EA (Part 5): Develop and Test Trading Strategy with LLMs (III) – Adapter-Tuning"
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Check out the new article: Integrate Your Own LLM into EA (Part 5): Develop and Test Trading Strategy with LLMs (III) – Adapter-Tuning.
With the rapid development of artificial intelligence today, language models (LLMs) are an important part of artificial intelligence, so we should think about how to integrate powerful LLMs into our algorithmic trading. For most people, it is difficult to fine-tune these powerful models according to their needs, deploy them locally, and then apply them to algorithmic trading. This series of articles will take a step-by-step approach to achieve this goal.
In the previous article, we introduced how to fine-tune the GPT-2 pre-trained model using the LoRA method and compared it with the fully fine-tuned model from several aspects we are concerned about, including but not limited to training overhead, inference overhead, and model performance.
In this article, we will use the Adapter-tuning method to fine-tune the GPT-2 pre-trained model and compare it with the fine-tuning methods already introduced. Of course, we will not continue to introduce various methods of fine-tuning large language models because new fine-tuning methods are constantly emerging. To reproduce each method one by one, I am afraid you will not have the patience to read them all, so I will only introduce a few of the most basic fine-tuning methods (for example, we have already introduced LoRA-tuning and will not spend a lot of space introducing QLoRA-tuning, a method extended from LoRA).
This means that this will be the last article on fine-tuning large language models. If you want to try other methods, you can refer to the logic of fine-tuning mentioned in this series of articles and apply it to other fine-tuning methods to continue exploring. Starting from the next article, we will focus on combining the trained model with EA development to develop trading strategies and conduct back testing.
Chart visualization for comparison:
Author: Yuqiang Pan