Recently, I came across a LinkedIn post by Armand Ruiz, VP of Product - AI Platform at IBM, discussing the differences between chatbots, copilots, and agents. While the post provided a general overview of these AI categories, it prompted me to inquire about a more specific topic: IBM’s Granite models.
Having recently participated in the NVIDIA AI Agent contest with my project Aileen 2, I was particularly interested in the potential applications of IBM’s Code Granite models. During the development of Aileen 2, I had initially considered using these models to power the agent’s Python code generation capabilities. However, due to limitations in model availability on the NIM catalog, I ultimately opted for Llama-3 8B as the core agent model.
Aileen 2, my entry for the contest, integrates four distinct AI/ML models:
- Core Agent: Llama-3 8B
- Summarization: Gemma 7B
- Vision: PaliGemma 3B Mix
- OCR: EasyOCR CRAFT-CRNN
Given this context, I was eager to learn more about IBM’s Granite models and their potential applications. I asked Armand which IBM Granite models he would recommend for specific use cases, expressing my interest in considering the full range of Granite models for future projects.
Unfortunately, as of now, I haven’t received a response to my inquiry.