update livestock model, add contributor and update hugging face docs (#910)

* update livestock model, add contributor and update hugging face docs

Author: bw4sz

AUTHORS.rst

@@ -33,5 +33,9 @@ Primary Authors
 Other Contributors
 ==================
 
+Special thanks to:
+
+* Cameron Appel (https://github.com/camappel) for help improving the livestock model.
+
 Check GitHub for recent `contributors <https://github.com/weecology/DeepForest/graphs/contributors>`_.
-We would like to thank everyone who has contributed to the project in any way.
+We would like to thank everyone who has contributed to the project in any way.

CONTRIBUTING.rst

@@ -182,3 +182,32 @@ Note:
 Do not commit the build directory after making html.
 
 This version correctly follows reStructuredText (reST) conventions and includes code blocks, inline literals, and proper linking. Let me know if you need further adjustments!
+
+
+Upload to Hugging Face Hub
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+To upload a trained model to the weecology organization space on Hugging Face Hub:
+
+1. Train or load your model checkpoint
+2. Set the label dictionary to match your classes
+3. Use push_to_hub with the weecology organization name
+
+For example:
+
+.. code-block:: python
+
+   from deepforest import main
+   
+   # Load model from checkpoint
+   model = main.deepforest.load_from_checkpoint("path/to/checkpoint.ckpt")
+   
+   # Set label dictionary mapping class names to indices
+   model.label_dict = {"Livestock": 0}
+   
+   # Push to weecology organization space
+   model.push_to_hub("weecology/deepforest-livestock")
+
+The model will be uploaded to https://huggingface.co/weecology/[model-name]
+
+Note: You must have appropriate permissions in the weecology organization to upload models.

docs/user_guide/02_prebuilt.md

@@ -52,10 +52,14 @@ For more information, or specific questions about the bird detection, please cre
 
 ## Livestock Detectors model
 
-This model has a single label 'cattle' trained on drone imagery of cows, sheep and other large mammals in agricultural settings. The model was trained on data from [insert countries and other metadata about landscapes].
+This model has a single label 'cattle' trained on drone imagery of cows, sheep and other large mammals in agricultural settings. 
 
 ![image](../../www/livestock-example.png)
 
+The model was improved by @camappel and a nice notebook illustrates its improvement here: https://edsbook.org/notebooks/gallery/95199651-9e81-4cae-a3a7-66398a9a5f62/notebook.
+
+![alt text](../../www/finetune_cattle_predictions.png)
+
 ```
 # Load deepforest model and set bird label
 m = main.deepforest()

docs/user_guide/10_better.rst

@@ -68,7 +68,8 @@ Annotate local training data
 Ultimately, training a proper model with local data is the best chance
 at getting good performance. See ``DeepForest.train()``
 
-Issues
+Here is a nice example of training a model on local data from a user in [cattle detection](https://edsbook.org/notebooks/gallery/95199651-9e81-4cae-a3a7-66398a9a5f62/notebook).
+
 ------
 
 We welcome feedback on both the python package as well as the algorithm