We're thrilled to have you join our community of analytics enthusiasts and professionals. To enhance your experience and foster meaningful interactions, we encourage you to personalize your profile by setting up a display name and uploading a profile picture. Your display name will be how others recognize and engage with you in discussions, while a profile picture adds a personal touch to your forum presence.
Take a moment to update your profile with a display name and an image representing you. Let's create a vibrant and engaging community together!
How can we effectively fine-tune an OCI AI LLM for Code Generation?
We wish to use a model (LLM) capable of generating code in JSON format. To achieve this, we plan to train the model with a collection of scripts of the types of code we want to generate, which will serve as examples to fit specific scenarios defined by the user. The main issue lies in the training dataset for fine-tuning, as being limited to words restricts the model's ability to learn code. The ultimate goal of using OCI AI services is to automate 5G use cases or testing. Another idea we have is to obtain information from 3GPP, where all use cases or tests are documented by Network Function and Interface, to train an AI model that can generate Ansible code or code in another programming language to model these scenarios as automated tests. The problem we see is that OCI does not offer an AI service capable of generating code from a traditional language prompt or input. If there is an expert in this field, we would greatly appreciate their insights and vision on this topic.
Best Answer
-
Hi @User_OX3M0 ,
Thank you for visiting and posting your question in Fusion Data Intelligence (FDI) Community. Please update your Display Name, so that the Community knows which whom they are interacting with.
I would recommend you to post your question in :
Also Please refer to Generative AI documentation for further information.
Thanks
Subha
0
