Category: numpy

Today, I’m very excited to demonstrate an effortless & new way to fine-tune the GPT-3 model using Python with the help of my new build (unpublished) PyPi package. In this post, I plan to deal with the custom website link as a response from this website depending upon the user queries with the help of the OpenAI-based tuned model.

In this post, I’ve directly subscribed to OpenAI & I’m not using OpenAI from Azure. However, I’ll explore that in the future as well.

Before I explain the process to invoke this new library, why not view the demo first & then discuss it?

Isn’t it exciting? Finally, we can efficiently handle your custom website URL using OpenAI tuned model.

What is ChatGPT?

ChatGPT is an advanced artificial intelligence language model developed by OpenAI based on the GPT-4 architecture. As an AI model, it is designed to understand and generate human-like text-based on the input it receives. ChatGPT can engage in various tasks, such as answering questions, providing recommendations, creating content, and simulating conversation. While it is highly advanced and versatile, it’s important to note that ChatGPT’s knowledge is limited to the data it was trained on, with a cutoff date of September 2021.

When to tune GPT model?

Tuning a GPT or any AI model might be necessary for various reasons. Here are some common scenarios when you should consider adjusting or fine-tuning a GPT model:

1. Domain-specific knowledge: If you need your model to have a deeper understanding of a specific domain or industry, you can fine-tune it with domain-specific data to improve its performance.
2. New or updated data: If new or updated information is not part of the original training data, you should fine-tune the model to ensure it has the most accurate and up-to-date knowledge.
3. Customization: If you require the model to have a specific style, tone, or focus, you can fine-tune it with data that reflects those characteristics.
4. Ethical or safety considerations: To make the model safer and more aligned with human values, you should fine-tune it to reduce biased or harmful outputs.
5. Improve performance: If the base model’s performance is unsatisfactory for a particular task or application, you can fine-tune it on a dataset more relevant to the job, often leading to better results.

Remember that tuning or fine-tuning a GPT model requires access to appropriate data and computational resources and an understanding of the model’s architecture and training techniques. Additionally, monitoring and evaluating the model’s performance after fine-tuning is essential to ensure that the desired improvements have been achieved.

FLOW OF EVENTS:

Let us look at the flow diagram as it captures the sequence of events that unfold as part of the process.

The initial Python-based client interacts with the tuned OpenAI models. This process enables it to get a precise response with custom data in a very convenient way. So that anyone can understand.

SOURCE DATA:

Let us understand how to feed the source data as it will deal with your website URL link.

The first data that we are going to talk about is the one that contains the hyperlink. Let us explore the sample here.

From the above diagram, one can easily understand that the application will interpret a unique hash number associated with a specific URL. This data will be used to look up the URL after the OpenAI response from the tuned model as a result of any user query.

Now, let us understand the actual source data.

If we closely check, we’ll see the source file contains two columns – prompt & completion. And the website reference is put inside the curly braces as shown – “{Hash Code that represents your URL}.”

During the response, the newly created library replaces the hash value with the correct URL after the successful lookup & presents the complete answer.

CODE:

Why don’t we go through the code made accessible due to this new library for this particular use case?

• clsConfigClient.py (This is the main calling Python script for the input parameters.)

Some of the important entries that will require later are as follows –

'FILE_NAME': '2023-4-14-WP.csv',
'LKP_FILE_NAME': 'HyperDetails.csv',
'OPEN_API_KEY': 'sk-hdhrujfrkfjfjfjfhjfjfisososT&jsdgL6KIxx',
'MODEL_CD':'davinci',
'URL': 'https://api.openai.com/v1/fine-tunes/',
'EXIT_KEYWORD': 'bye'

We’ll discuss these entries later.

• trainChatGPTModel.py (This is the main calling Python script that will invoke the newly created fine-tune GPT-3 enabler.)

Following are the key snippet from the above script –

data_path = cf.conf['DATA_PATH']
data_file_name = cf.conf['FILE_NAME']

And, then –

tModel = tm.clsTrainModel3()
FullFileName = data_path + data_file_name
r1 = tModel.trainModel(FullFileName)

As one can see, the package needs only the source data file to fine-tune GPT-3 model.

• checkFineTuneChatGPTModelStat.py (This is the main Python script that will check the status of the tuned process that will happen inside the OpenAI-cloud environment.)

To check the status of the fine-tuned job inside the OpenAI environment, one needs to provide the fine tune id, which generally starts with -> “ft-*.” One would get this value after the train script’s successful run.

Some of the other key snippets are –

tmodel = tm.clsTestModel3()

url_part = cf.conf['URL']
open_api_key = cf.conf['OPEN_API_KEY']

And, then –

input_text = str(input("Please provide the fine tune Id (Start with ft-*): "))
url = url_part + input_text
print('URL: ', url)

r1 = tmodel.checkStat(url, open_api_key)

The above snippet is self-explanatory as one is passing the fine tune id along with the OpenAI API key.

• testChatGPTModel.py (This is the main testing Python script that will invoke the newly created fine-tune GPT-3 enabler to get a response with custom data.)

Some of the key entries from the above snippet are as follows –

tmodel = tm.clsTestModel3()

open_api_key = cf.conf['OPEN_API_KEY']
lkpDataPath = cf.conf['DATA_PATH']
lkpFileName = cf.conf['LKP_FILE_NAME']

And, then –

LookUpFileName = lkpDataPath + lkpFileName
r1 = tmodel.testModel(LookUpFileName, open_api_key)

In the above lines, the application gets the correct URL value from the look file we’ve prepared for this specific use case.

• deleteChatGPTModel.py (This is the main Python script that will delete the old intended tuned model, which is no longer needed.)

Some of the key snippets from the above scripts are –

tmodel = tm.clsTestModel3()

open_api_key = cf.conf['OPEN_API_KEY']

And, then –

r1 = tmodel.delOldModel(open_api_key)

We’ve demonstrated that using a straightforward method, one can delete any old tuned model from OpenAI that is no longer required.

KEY FEATURES TO CONSIDER DURING TUNING:

• Data quality: Ensure that the data used for fine-tuning is clean, relevant, and representative of the domain you want the model to understand. Check for biases, inconsistencies, and errors in the dataset.
• Overfitting: Be cautious of overfitting, which occurs when the model performs exceptionally well on the training data but poorly on unseen data. You can address overfitting by using regularization techniques, early stopping, or cross-validation.
• Model size and resource requirements: GPT models can be resource-intensive. Be mindful of the hardware limitations and computational resources available when selecting the model size and the time and cost associated with training.
• Hyperparameter tuning: Select appropriate hyperparameters for your fine-tuning processes, such as learning rate, batch size, and the number of epochs. Experiment with different combinations to achieve the best results without overfitting.
• Evaluation metrics: Choose suitable evaluation metrics to assess the performance of your fine-tuned model. Consider using multiple metrics to understand your model’s performance comprehensively.
• Ethical considerations: Be aware of potential biases in your dataset and how the model’s predictions might impact users. Address ethical concerns during the fine-tuning process and consider using techniques such as data augmentation or adversarial training to mitigate these biases.
• Monitoring and maintenance: Continuously monitor the model’s performance after deployment, and be prepared to re-tune or update it as needed. Regular maintenance ensures that the model remains relevant and accurate.
• Documentation: Document your tuning process, including the data used, model architecture, hyperparameters, and evaluation metrics. This factor will facilitate easier collaboration, replication, and model maintenance.
• Cost: OpenAI fine-tuning can be extremely expensive, even for a small volume of data. Hence, organization-wise, one needs to be extremely careful while using this feature.

COST FACTOR:

Before we discuss the actual spending, let us understand the tested data volume to train & tune the model.

So, we’re talking about a total size of 500 KB (at max). And, we did 10 epochs during the training as you can see from the config file mentioned above.

So, it is pretty expensive. Use it wisely.

So, finally, we’ve done it.

I know that this post is relatively bigger than my earlier post. But, I think, you can get all the details once you go through it.

You will get the complete codebase in the following GitHub link.

I’ll bring some more exciting topics in the coming days from the Python verse. Please share & subscribe to my post & let me know your feedback.

Till then, Happy Avenging! 🙂

Note: All the data & scenarios posted here are representational data & scenarios & available over the internet & for educational purposes only. Some of the images (except my photo) we’ve used are available over the net. We don’t claim ownership of these images. There is always room for improvement & especially in the prediction quality.