Eliran Wong

Why Ollama is so terribly slow when I set format="json"

6

When I use format="json" the speed is extremely slow. However, I just tried llamafile with JSON output with the same prompt. What takes Ollama to response in two minutes, takes...

add parallel text editor to facilitate bible translation

2

add text editor to facilitate bible translation parallel to bible window

may integrate macula-hebrew project https://github.com/Clear-Bible/macula-hebrew

Qt5 GUI on Android

1

Currently, UBA terminal is supported on Android Termux. As termux 'pyqtwebengine' package is completed just now https://github.com/termux/termux-packages/pull/14619 , Qt5 interface should be able to run on Android too. However, the...

Does LLaMA-Factory support AMD graphic cards?

7

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction A question. Does LLaMA-Factory support AMD graphic cards? LLaMA-Factory 支援 AMD cards 嗎？不好意思，我在你 repo，找不到相關說明，如何...

Cross-platform GUI

2

Cross-platform GUI, will add a qt-based one. Will keep tui as an option

Integrate Tavily API to enhance researches

Hi, I would like to reopen the issue, as the suggestion does not work, thanks: https://github.com/ollama/ollama-python/issues/84

screenshots for documentation

7

screenshots for documentation are placed here

support using llama.cpp & chatgpt on Android

1

support using llama.cpp & chatgpt on Android