Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ...
by cuu508 on Wednesday May 29, 2024 @02:11AM
(#40508988)
This is the out of the box thinking I love about HN. What do you do with the mermaid?
[ Parent
| on HN ]
Re:Llama 3-V: Matching GPT4-V with a 100x smaller model and ...
by SparkyMcUnicorn on Wednesday May 29, 2024 @10:37AM
(#40512444)
The resulting mermaid is used for... more LLM processing. Converting to mermaid first is more cost-effective, consistent, and accurate for my purposes.