Igor Schlumberger

When you use a LLM for an experiment, you can do it with docker and keep both the current Ollama version and the LLM version to reproduce the experiment. Be...

Hi @joliss I have a Mac Station M1 with 192 GB of RAM and can launch the ollama run mixtral:8x22b-instruct-v0.1-q4_0 'Hi!' command without any trouble. I'm using version 0.1.36 of...

Hi @Elminsst is working on MacOS. Can you try with version 0.1.37?

@lyfuci Ollama only support OpenSource models. Before adding a model to Ollama, it is often available on Hunging Face.

Hi @frankhart2018 I can do that on MacOS, I open two Terminal Windows and type ollama pull llama3 on the first one and ollama pull llama2 on the second one....

@frankhart2018 do you want to increase or decrease this number of threads? For what goal?

Hi @lestan SQLcoder2 seams to be a valid model. It's bigger than SQLCoder (9 GB instead of 4.1). It could be a copy of sqlcoder:15b what has the same size....

For me it's working without specifying json in the prompt. (I have 32Gb on M1Pro MacBook) (base) igor@macIgor ~ % ollama run llama2 --format json >>> give me 10 emojis...

I have the same issue with autocomplete on MacOS (Safari). Mac try to past the +33 666600000 phone number, but instead of recognizing the +33 aera code, the +66 Area...

I purchased a 192 GB RAM MacStation to run Ollama with various LLMs. I concur that it would be advantageous to keep them resident in memory if possible.