hollama
hollama copied to clipboard
A minimal web-UI for talking to Ollama servers
> To calculate how fast the response is generated in tokens per second (token/s), divide `eval_count` / `eval_duration`. https://github.com/ollama/ollama/blob/main/docs/api.md#response
Implemented on #155 After submitting a prompt the page scrolls but not all the way down. This causes the AI response to stay hidden behind the prompt form: https://github.com/user-attachments/assets/226b51a8-d145-4cbe-ae38-fe1bf34326d6
Closes #150