SebastianGode
SebastianGode
I'd try to use as few accounts as possible. It's not a good practice to do that. It's better to optimize the code so that less API calls are need....
@Freekers Is there a way to set this to something lower than one minute? During the intial setup via the app you can easily set it to one minute, but...
I've got same issue when tryaing to generate embeddings with multiple threads running on an Nvidia T4. ``` ollama | GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/llama.cpp:12095: seq_id < n_tokens && "seq_id cannot be larger...
This is an hardware issue of your PC. In the statistics tab check whether "Client FPS" and "Streamer FPS" are matched. With the jittery video I assume that isn't the...
You know that on normal phones you are running 2x 1440p, right? That's literally 4x the GPU power which you need compared to your 1080p monitor. Additionally you likely set...
@EdLovecraft You need a faster GPU. That only happens if your PC is unable to render the selected fps.
We really need to have an ARM64 build now. A lot of laptops with Snapdragons are shipping right now.
@AndreasKunar Importing the Q4_0_4_8 build under WSL to native ARM of Ollama doesn't seem to work. Ollama doesn't support Q4_0_4_8 yet, correct?
@AndreasKunar Yes, that is the exact same issue for me. Good that you could verify that and that I wasn't too dumb to use Ollama. Please go ahead and open...
So seemingly Umami v3.0.0 was released. Wuhu! Now this feature would be cool to be included in a subversion :)