add training set argument types to readme

README.md

@@ -104,7 +104,7 @@ Example with a system message:
 ```
 Notice that the function block is placed at the very start of the sequence, before 'B_INST'.
 
-## Function Metadata Template
+### Function Metadata Template
 
 functionMetadata should be a string representation of a JSON object, like this:
 
@@ -138,7 +138,7 @@ It is recommended to handle cases where:
 - There is no json object in the response
 - The response contains text in addition to the json response
 
-## Sample functionList
+### Sample functionList
 
 ```
 {
@@ -166,6 +166,18 @@ It is recommended to handle cases where:
 }
 ```
 
+### Training Set Argument Types
+Models were fine-tuned on argument types including strings, numbers and arrays. The training set includes function calls with 0, 1, 2 or 3 arguments. The larger the model the better it will generalise beyond these types.
+
+Here is a function call with an array:
+```
+{ "function": "delete_file", "arguments": { "fileNames": [ "Dissecting Transformer Length Extrapolation via The Lens of Receptive Field Analysis", "Luna- Linear Unified Nested Attention", "Substack_Inc_2021_2020_GAAP_Audited_Financials" ] } }
+```
+Here is a function call with three arguments:
+```
+{ "function": "save_chat", "arguments": { "fileName": "KiteDiscussion", "fileDescription": "Notes on one and two stringed kites", "fileContent": "--- **Types of Kite** There are one and two string kites. The two string ones are easier to control, although you can get the cords tangled. The one-stringed ones are sometimes used for kite fights, and you lose the kite and have to run after it if the string breaks. ---" } }
+```
+
 ~
 
 Below follows information on the original Llama 2 model...