GitLab

Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>

- defer closing llm on embedding
- do not override licenses
- remove debugging print line
- reformat model file docs

Fixes #282

- default to embeddings enabled
- move embedding logic for loaded model to request
- allow embedding full directory
- close llm on reload

automatically set num_keep if num_keep < 0

Fixes #297
Fixes #296

Fixes #295

num_keep defines how many tokens to keep in the context when truncating
inputs. if left to its default value of -1, the server will calculate
num_keep to be the left of the system instructions