Model Architecture Update
Alex and Vic discuss the model's upgrade to Mistral 7B and the use of higher resolution images for better understanding. The new backbone and fine-tuned Yi brain in the model have significantly improved OCR performance, making it state-of-the-art.In this clip
From this podcast
ThursdAI
ThursdAI - Jan 31, 2024- Code LLama, Bard is now 2nd best LLM?!, new LLaVa is great at OCR, Hermes DB is public + 2 new Embed models + Apple AI is coming 👀
Related Questions
How are Large Language Models (LLMs) fine-tuned post-training as discussed in the episode #174 - Odyssey Text-to-Video, Groq LLM Engine, OpenAI Security Issues, and the clip Covert Model Manipulation?
How are Large Language Models (LLMs) fine-tuned post-training as discussed in the episode #174 - Odyssey Text-to-Video, Groq LLM Engine, OpenAI Security Issues and the clip Covert Model Manipulation?