Kim Hallberg

Took a cursory glance at the technical report[^1] and I'm new to AI in general but it looks to me like Phi3 wasn't trained with a system prompt in mind,...

Circling back to this after some testing. From my testing, I get that it kinda supports it but not really. The results are not consistent at all. I've tried different...

So basically the system prompts I was testing with were just bad. 😂 Time to learn how to write better prompts. 👍

What error do you get when not explicitly setting the `-X` flag? Using the `-d` flag already sends the request as POST[^1]. [^1]: https://curl.se/docs/manpage.html#-d

That information can be found in the FAQ: https://github.com/ollama/ollama/blob/main/docs/faq.md#where-are-models-stored For Windows it's: `C\Users\\.ollama\models`

The installation command is written in the input to the right of the tag drop-down. It's `ollama run ` for an interactive session and `ollama pull ` to just download...

> Not visible in a mobile device Not sure why you'd use a mobile device to access the website given Ollama is a desktop/server app. But either way, `ollama run...

> The latter should look like: > > ``` > % ./ollama ls | grep gemma:7b > gemma:7b 430ed3535049 5.2 GB 3 weeks ago > ``` Running Ollama 0.1.32, Mac...

`XLMRobertaModel` is not yet a supported model architecture. Afaik Ollama currently only supports `bert` and `nomic-bert` embedding architectures. According to the [Embedding models](https://ollama.com/blog/embedding-models) blog post, more should be available later....

> Is possible to use this Bert model in ollama? > > > > jinaai/jina-embeddings-v2-base-es No because JinaAI uses a modified version of Bert they created called JinaBert and that...