Michael Yang

This is likely a bug with rendering. I've noticed similar behaviour with other processes, things like ssh or tailing logs won't update the screen without some user action. It should...

I'm unable to reproduce this on Windows 11 with cmd in Windows Terminal. Can you elaborate on your environment? Namely ollama version and model. From the screenshot, it looks like...

There's currently no plans to provide official docker images with predownloaded models although you can always augment it to include this functionality

Looking at the request both from the error in your description and the server access logs, it appears the request is getting mangled somehow. This is being sent ``` https://ollama.com/token?nonce=A-QmGZFS0za-Kv0GKrDy3Q&scope=repository%!A(MISSING)library%!F(MISSING)llama2%!A(MISSING)pull&service=ollama.com&ts=1710339130...

I'm not sure what @pdevine's thoughts are but I would prefer to change the prefix (`sha256: --> sha256-`) only when referencing the file on disk. It would reduce the surface...

This is fixed by https://github.com/ollama/ollama/pull/3988 which was released in 0.1.35

Closing this since it's been 2 months of inactivity

@davep I'm happy to merge this if you can remove the pyproject.toml change since poetry includes it

I missed a word "remove"

@wangyeye66 can you paste the output you get from the cli and the output from the `ollama.chat`? from what I can tell, this behavior is expected. [llama2:7b](https://ollama.com/library/llama2:7b) implements a chat...