GitLab

create remote models

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

* faq: does ollama share my prompts
Signed-off-by: Matt Williams <m@technovangelist.com>

* faq: ollama and openai
Signed-off-by: Matt Williams <m@technovangelist.com>

* faq: vscode plugins
Signed-off-by: Matt Williams <m@technovangelist.com>

* faq: send a doc to Ollama
Signed-off-by: Matt Williams <m@technovangelist.com>

* extra spacing
Signed-off-by: Matt Williams <m@technovangelist.com>

* Update faq.md

* Update faq.md

---------
Signed-off-by: Matt Williams <m@technovangelist.com>
Co-authored-by: Michael <mchiang0610@users.noreply.github.com>

replace go-humanize with format.HumanBytes

Previously, `ollama run` treated a non-terminal stdin (such as `ollama run model < file`) as containing one prompt per line. To run inference on a multi-line prompt, the only non-API workaround was to run `ollama run` interactively and wrap the prompt in `"""..."""`.

Now, `ollama run` treats a non-terminal stdin as containing a single prompt. For example, if `myprompt.txt` is a multi-line file, then `ollama run model < myprompt.txt` would treat `myprompt.txt`'s entire contents as the prompt.
Co-authored-by: Quinn Slack <quinn@slack.org>

This field is optional and should be under the `Advanced parameters` header

* New big-AGI integration

Ollama works great in big-AGI, and this document explains how to link the two projects.

* Update README.md

Fixed incorrect base model name

Resume chunk download on UnexpectedEOF errors

If the chunk download is interrupted, resume from where we left off

docs: add examples using bash to compare models

* add `"format": "json"` as an API parameter
---------
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>