Add model management functionality for local caches (#736)

* Add model management functionality for local caches

This commit introduces a set of command-line utilities for managing MLX models downloaded and saved locally in Hugging Face cache. The functionalities include scanning existing models, retrieving detailed information about a specific model, and deleting a model by its name.

* Added mlx_lm.model to setup.py

* nits

---------

Co-authored-by: Awni Hannun <awni@apple.com>

llms/mlx_lm/MANAGE.md

@@ -0,0 +1,22 @@
+# Managing Models
+
+You can use `mlx-lm` to manage models downloaded locally in your machine. They
+are stored in the Hugging Face cache.
+
+Scan models: 
+
+```shell
+mlx_lm.manage --scan
+```
+
+Specify a `--pattern` to get info on a single or specific set of models:
+
+```shell
+mlx_lm.manage --scan --pattern mlx-community/Mistral-7B-Instruct-v0.2-4bit
+```
+
+To delete a model (or multiple models):
+
+```shell
+mlx_lm.manage --delete --pattern mlx-community/Mistral-7B-Instruct-v0.2-4bit
+```