Teaching an LLM a Niche Diagraming Language
Text-to-diagram seems to be an area that has been solved perfectly by LLMs, but only with popular languages like Mermaid or PlantUML. There are many other less popular diagramming languages like D2, Structurizr, or Pintora. I want to see how far I can go teaching an LLM one of these languages, and Pintora◹ seems like a nice option to pick because I know there will not be a lot of LLMs trained with this language. At least, not the small ones. So, I set out the goal for this training project. It will be an LLM that has the ability to work with Pintora diagrams, for the following tasks: I also limit the scope of this project to models that are smaller than 30B, simply because I do not have enough resources to train anything bigger than that. Having experimented with 4B models and smaller, I found that these models are not really suitable for either a code-generating task or instruction following in a long conversation. A 7B-14B would be a good choice. I also want to base it off a coding m
Text-to-diagram seems to be an area that has been solved perfectly by LLMs, but only with popular languages like Mermaid or PlantUML. There are many other less popular diagramming languages like D2, Structurizr, or Pintora. I want to see how far I can go teaching an LLM one of these languages, and Pintora ◹ seems like a nice option to pick because I know there will not be a lot of LLMs trained with this language. At least, not the small ones. Project goal So, I set out the goal for this training project. It will be an LLM that has the ability to work with Pintora diagrams, for the follow
saved by
related reading
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- PiTorch: ML on Baremetal Raspberry Pis | projectsmasonjwang.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- GitHub - rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by stepgithub.com
- Productizing Large Language Modelsblog.replit.com
- Efficient LLM inferencefinbarrtimbers.substack.com
- LLM Resourcesforrestbicker.com
- Program Synthesis with Large Language Modelsarxiv.org
- The Llama Hitchiking Guide to Local LLMs – hackerllamaosanseviero.github.io
- Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
- Here’s how I use LLMs to help me write codesimonwillison.net