Closed shumoLR closed 1 month ago
Hello, in the process of image to text, the text content does not match the image, please look at the image below, where do I set the problem?
yes you need to use a llava model or other model that supports vision like the ones suggested on the repo readme ollama run llava:7b-v1.6-mistral-q5_K_M
yes you need to use a llava model or other model that supports vision like the ones suggested on the repo readme
ollama run llava:7b-v1.6-mistral-q5_K_M
Ok, thank you very much. I'll try