GitLab

* update streaming request accept header
* add optional stream param to request bodies

* prevent waiting on exited command
* close llama runner once

* check free memory not total
* wait for subprocess to exit

handle upstream proxies

add the example for ask the mentors

Avoid triple ticks in visual editor and also copied in clipboard.

parallel chunked downloads

`Modelfile` syntax highlighting

glob returns files in lexical order which is not appropriate when
rebuilding the parts list

- this makes it easier to see that the subprocess is associated with ollama

decode starcoder

* include seed in params for llama.cpp server and remove empty filter for temp

* relay default predict options to llama.cpp

- reorganize options to match predict request for readability

* omit empty stop

---------
Co-authored-by: hallh <hallh@users.noreply.github.com>

add community project: Chatbot Ollama by @ivanfioravanti